Disclosed herein are embodiments for a control module cooling system. For example, the control module is provided with a chassis and a circuit board assembly that is mounted to the chassis and includes electronics that generate heat during operation. A cold plate is mounted to the chassis and adjacent to the circuit board assembly and defines an opening. A cold block is coupled to the cold plate and comprises: a base disposed within the opening and coupled to the electronics; a plurality of fins extending from the base and spaced apart from each other to form channels; and a plate that is spaced apart from the base to form a cavity. The plate defines an inlet that is arranged over a central portion of the plurality of fins to receive a liquid therethrough to facilitate impinging flow of the liquid through the channels to transfer heat from the electronics.
Disclosed herein are system, method, and computer readable medium embodiments for sensor relative alignment verification. The vehicle system includes a sensor configured to capture range data with a body defining a sensor coordinate frame with three axes. At least three first motion sensors are coupled to the body, each being configured to capture first motion data along a first sensor axis arranged non-orthogonally relative to the first axis and the second axis, wherein the first motion data is indicative of a first rotational degree of freedom about the first axis, and a second rotational degree of freedom about the second axis. At least two second motion sensors are coupled to the body, each being configured to capture second motion data along a second sensor axis arranged non-orthogonally relative to the third axis, wherein the second motion data is indicative of a third rotational degree of freedom about the third axis.
Disclosed herein are methods, systems, and computer program products for automated delivery of goods that include: a deployment vehicle; and an autonomous delivery vehicle contained within the deployment vehicle, where the delivery vehicle secures a package, where the delivery vehicle is programmed or configured to: deploy the delivery vehicle from the deployment vehicle; autonomously navigate the delivery vehicle from the deployment vehicle to a delivery location; park the delivery vehicle at the delivery location; and in response to an authorization protocol being satisfied, release the package.
G06Q 10/04 - Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
4.
METHOD AND SYSTEM FOR DYNAMIC ALLOCATION OF VEHICLES TO FLEETS
This document discloses system, method, and computer program product embodiments for dynamically assigning vehicles or other objects to fleets of multiple tenants. Each tenant will be assigned a primary fleet of objects (such as vehicles) and will be associated with a minimum service level requirement and parameters governing operation of each object that is assigned to that primary fleet. The system will maintain a common fleet of vehicles, from which objects may be temporarily assigned to the primary fleets. When one of the tenants submits a service request, the system will select an object from the common fleet, assign the selected object to the primary fleet of that tenant's primary fleet, and cause the object to fulfill the first trip request in accordance with the set of parameters governing operation of each object that is assigned to the primary fleet of that tenant.
Disclosed herein are system, method, and computer program product embodiments for an asymmetrical Autonomous Vehicle Systems (AVS). A backup AVS is implemented on a vehicle to serve as a failover system for one or more of the primary AVS components or processes (e.g., steering, braking, etc.). In this way, during primary AVS failures, the backup AVS can dynamically handle a subset of vehicle operations in various component configuration levels based on a desired mission level.
This document discloses system, method, and computer program product embodiments for managing data generated by one or more systems of a vehicle. In various embodiments, a processor onboard a vehicle receives messages generated by one or more onboard systems of the vehicle. The system saves a first set of the messages to a first storage location on the vehicle according to a first data logging policy. The system processes a second set of the messages to reduce data elements and yield offboard data that is designated for offboard use. The first and second sets of messages may or may not overlap with each other. The system saves the offboard data to a second storage location that is onboard the vehicle and subject to a second data logging policy. The second data logging policy differs from the first data logging policy.
H04L 41/069 - Management of faults, events, alarms or notifications using logs of notificationsPost-processing of notifications
H04L 41/0604 - Management of faults, events, alarms or notifications using filtering, e.g. reduction of information by using priority, element types, position or time
Disclosed herein are system, method, and computer program product embodiments for detecting anomalies during software testing. The methods include generating a plurality of test reports for the software program by executing one or more test cases on a plurality of versions of the software program, generating a control chart based on the plurality of test reports, generating an alert when at least one testing characteristic includes an anomaly over the plurality of versions of the software program as determined based on the control chart. The control chart includes a plot associated with at least one testing characteristic of the software program, and a historical context associated with execution of the one or more test cases on the plurality of versions of the software program.
This document discloses system, method, and computer program product embodiments for determining an intermediate (i.e., alternate) stopping location (ISL) for a ride service request when a desired stopping location (DSL) is not reachable. The system will map and sensor data to select an ISL. In response to determining that the passenger has approved the ISL as a final stopping location (FSL), the vehicle will move along a route to the FSL.
Disclosed herein are system, method, and computer program product embodiments for clustering lane segments of a roadway in order to improve and simplify autonomous vehicle behavior testing. The approaches disclosed herein provide a hybrid methodology of dividing lane segments into hard features and soft features, and using a metric learning model trained in a supervised process on the entirety of lane segment features to cluster the lane segments based on the soft features. These clustered lane segments can then be assigned to what is termed as protolanes, where a single set of tests applied to a given protolane is considered valid across all of the lane segments assigned to the protolane.
G06F 18/2413 - Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
G06F 18/21 - Design or setup of recognition systems or techniquesExtraction of features in feature spaceBlind source separation
Methods and systems for calibrating sensors of an autonomous vehicle are disclosed. The method includes using a target that includes a plurality of uniquely identifiable fiducials positioned on a panel to form a pattern, and at least one tag. Each tag correposnds to and is positioned relative one of the plurality of uniquely identifiable fiducials and includes information for determing a location of its correpsonding uniquely identifiable fiducial with respect to the panel.
Methods and systems for calibrating sensors of an autonomous vehicle are disclosed. The method includes using a target that includes a plurality of uniquely identifiable fiducials positioned on a panel to form a pattern, and at least one tag. Each tag corresponds to and is positioned relative one of the plurality of uniquely identifiable fiducials and includes information for determining a location of its corresponding uniquely identifiable fiducial with respect to the panel.
B60W 60/00 - Drive control systems specially adapted for autonomous road vehicles
G06V 20/58 - Recognition of moving objects or obstacles, e.g. vehicles or pedestriansRecognition of traffic objects, e.g. traffic signs, traffic lights or roads
G06V 20/56 - Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
12.
Systems and Methods for Autonomous Vehicle Sensor Calibration and Validation
Methods and systems for determining whether a camera of an autonomous vehicle (AV) is calibrated are disclosed. The method includes determining a relative positional range for a calibration target with respect to the AV, capturing a plurality of images of the calibration target, using the camera when the calibration target and the AV are positioned within the relative positional range, measuring a camera-based calibration factor and a motion-based validation factor based on the plurality of images for generating a confidence score, and generating a signal indicating that the camera is not calibrated when the confidence score is below a threshold.
A mounting device includes an elongated beam having a first end portion, a second end portion, and a side surface extending between the first end portion and the second end portion. The mounting device also includes a first camera mount attached to the first end portion configured to support a first camera, a second camera mount attached to the second end portion configured to support a second camera, and a bracket for fixedly connecting the elongated beam to a vehicle. The bracket is positioned between the first end portion and the second end portion. The bracket includes at least one base configured to be attached to the vehicle and a wall extending from the at least one base comprising an opening sized to receive the elongated beam, such that engagement between the wall and the elongated beam restricts rotation of the elongated beam about multiple axes.
G03B 35/18 - Stereoscopic photography by simultaneous viewing
H04N 23/90 - Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums
H04N 13/282 - Image signal generators for generating image signals corresponding to three or more geometrical viewpoints, e.g. multi-view systems
H04N 13/243 - Image signal generators using stereoscopic image cameras using three or more 2D image sensors
F16M 13/02 - Other supports for positioning apparatus or articlesMeans for steadying hand-held apparatus or articles for supporting on, or attaching to, an object, e.g. tree, gate, window-frame, cycle
B60R 11/04 - Mounting of cameras operative during driveArrangement of controls thereof relative to the vehicle
B60R 1/27 - Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles for viewing an area outside the vehicle, e.g. the exterior of the vehicle with a predetermined field of view providing all-round vision, e.g. using omnidirectional cameras
A test module is provided with a housing for mounting within a cabin of an autonomous vehicle (AV). At least two user input devices are supported by the housing. A controller is disposed within the housing and programmed to: generate a first request to control an AV system of the AV based on manual activation of one of the at least two user input devices, and generate a second request to control the AV system based on manual activation of the other of the at least two user input devices. At least one transceiver provides the first request to the AV on a first communication interface and provides the second request to the AV system on a second communication interface.
Disclosed herein are system, method, and computer program product embodiments for cleaning one or more sensors of an autonomous vehicle (AV) system. For example, the system includes a tank to store a solvent. A heat exchanger is disposed in the tank to transfer heat from a heated fluid to the solvent. A first actuator is provided to enable and disable fluid communication of the heated fluid from a coolant system to the heat exchanger. A nozzle is in fluid communication with the tank to spray the solvent on a sensor of an autonomous vehicle (AV) system to remove debris. A controller is programmed to control the first actuator to enable the fluid communication of the heated fluid to the heat exchanger to increase at least one of a temperature and a pressure of the solvent within the tank.
Disclosed herein are systems, methods, and computer program products for controlling data collection by resources. The methods comprise: receiving real-world data collected by the resources in accordance with data collection mission (DCM) parameters; receiving user defined DCM goal(s); updating goal(s) for DCM mission(s) based on the real-world data and the user defined DCM goal(s); modifying the data DCM parameter(s) based on the updated goal(s) and which ones of the resources are still available for DCMs; and causing data collection operations (which are currently being performed by the resource(s)) to change in accordance with the modified DCM parameter(s).
A test module is provided with a housing for mounting within a cabin of an autonomous vehicle (AV). At least two user input devices are supported by the housing. A controller is disposed within the housing and programmed to: generate a first request to control an AV system of the AV based on manual activation of one of the at least two user input devices, and generate a second request to control the AV system based on manual activation of the other of the at least two user input devices. At least one transceiver provides the first request to the AV on a first communication interface and provides the second request to the AV system on a second communication interface.
Disclosed herein are system, method, and computer program product aspects for enabling an autonomous vehicle (AV) to detect objects and forecast their predicted positions. The system can monitor an object within a vicinity of the AV. A plurality of trajectories predicting paths the object will take at a future time can be generated, the plurality of trajectories being based on a generated three-dimensional (3D) point cloud map indicating current and past characteristics of the object. Using a learned model, a forecasted position of the object at an instance in time can be generated along one or more of the plurality of trajectories. A maneuver for the AV can be performed based on the forecasted position.
Disclosed herein are systems, methods, and computer program products for generating and using map information. For example, the method includes: identifying data collection mission area(s) (DCMAs) within a geographic location that is to be covered by robotic device(s) during a data collection mission (DCM); generating a route to be traversed by robotic device(s) in DCMAs (the route being configured to cause robotic device(s) to traverse each two-way road at least one time in two opposing directions); causing robotic device(s) to perform DCM by following the route and collecting data; causing robotic device(s) to discontinue collecting data in response to a trigger event; and using the data collected during DCM to generate or update the map information. The map information may be used to facilitate controlled movement of a vehicle.
Systems and methods for generating a panoptic segmentation mask for an input image. The methods include receiving the input image comprising a plurality of pixels, generating a semantic mask and an instance mask from the input image, and combining the semantic mask and the instance mask to generate a panoptic mask for the input image. The semantic mask includes a single-channel mask that associates each pixel in the input image with a corresponding one of a plurality of labels. The instance mask includes a plurality of masks, where each of the plurality of masks identifies an instance of a countable object in the input image, and is associated with an indication of whether that instance of the countable object is hidden behind another object in the input image.
G06N 3/04 - Architecture, e.g. interconnection topology
G06V 10/26 - Segmentation of patterns in the image fieldCutting or merging of image elements to establish the pattern region, e.g. clustering-based techniquesDetection of occlusion
21.
SYSTEM, METHOD, AND COMPUTER PROGRAM PRODUCT FOR ONLINE SENSOR MOTION COMPENSATION
Disclosed herein are system, method, and computer program product embodiments for online sensor motion compensation. For example, the method includes: applying a random mechanical excitation to a support structure, wherein a plurality of image capture devices and a plurality of sets of strain gauges are coupled to the support structure; measuring, with each set of strain gauges of the plurality of sets of strain gauges, simultaneous to the application of the random mechanical excitation, a strain; capturing, with each image capture device of the plurality of image capture devices, simultaneous to the application of the random mechanical excitation, a series of images of a calibration target; and generating, based on the strain and the series of images, a mapping between the strain and a displacement between the plurality of image capture devices.
This document discloses system, method, and computer program product embodiments for mitigating the addition of false object information to a track that provides a spatial description of an object, such as a track of radar data or lidar data. The system will analyze two or more frames captured in a relatively small time period and determine whether one or more parameters of an object detected in the frames remain consistent in a specified model. Models that the system may consider include a constant velocity model, a surface model, a constant speed rate model or a constant course rate model. If one or more parameters of the detected object are not consistent over the sequential frames in the specified model, the system may prune the track to exclude one or more of the sequential frames from the track.
G06V 20/40 - ScenesScene-specific elements in video content
G06V 10/62 - Extraction of image or video features relating to a temporal dimension, e.g. time-based feature extractionPattern tracking
G06V 10/75 - Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video featuresCoarse-fine approaches, e.g. multi-scale approachesImage or video pattern matchingProximity measures in feature spaces using context analysisSelection of dictionaries
G01S 13/58 - Velocity or trajectory determination systemsSense-of-movement determination systems
23.
DETERMINING PERCEPTUAL SPATIAL RELEVANCY OF OBJECTS AND ROAD ACTORS FOR AUTOMATED DRIVING
Disclosed herein are system, method, and computer program product embodiments for determining objects that are kinematically capable, even if non-compliant with rules-of-the-road, of affecting a trajectory of a vehicle. The computing system (e.g., perception system, etc.) of a vehicle may generate a trajectory for the vehicle and a respective trajectory for each object of a plurality of objects within a field of view (FOV) of the sensing device associated with the vehicle. The computing system may identify objects of the plurality of objects with trajectories that intersect the trajectory for the vehicle and remove from such objects, objects with trajectories that at least one of exit the FOV or intersect with other objects of the plurality of objects within the FOV. The computing system may select, from remaining objects with trajectories that intersect the trajectory for the vehicle, objects with trajectories that indicate a respective collision between the object and the vehicle and assign a severity of the respective collision.
B60W 30/08 - Predicting or avoiding probable or impending collision
B60W 60/00 - Drive control systems specially adapted for autonomous road vehicles
B60W 40/02 - Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit related to ambient conditions
Disclosed herein are system, method, and computer program product embodiments for generating and refining simulation scenarios. For example, the method includes generating multiple base scenarios, each including one or more constant and one or more variable parameters. For each of the base scenarios, the method includes generating scenario variations, each of which is associated with a unique combination of values assigned to its base scenario's parameters. The method further includes determining a system boundary in a parameter space defined by the variable parameters, wherein the system boundary divides the parameter space into a region including successful scenario variations and a region including unsuccessful scenario variations, and generating additional scenario variations within a threshold distance of the system boundary. The method further includes simulating operation of an autonomous vehicle (AV) using one or more generated scenario variations.
Disclosed herein are system and method embodiments to implement a validation of a vector map. The validation process may merge proposed and persisted high-definition mapping data, evaluate the high-definition mapping data with a set of customizable validation rules, return/persist validation results, and provide a means to acknowledge validation failures to minimize creation of problematic vector map content.
B60W 50/04 - Monitoring the functioning of the control system
B60W 50/14 - Means for informing the driver, warning the driver or prompting a driver intervention
B60W 40/08 - Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit related to drivers or passengers
B60W 60/00 - Drive control systems specially adapted for autonomous road vehicles
G01C 21/00 - NavigationNavigational instruments not provided for in groups
B60W 50/00 - Details of control systems for road vehicle drive control not related to the control of a particular sub-unit
26.
METHOD FOR ASSIGNING A LANE RELATIONSHIP BETWEEN AN AUTONOMOUS VEHICLE AND OTHER ACTORS NEAR AN INTERSECTION
Disclosed herein are system, method, and computer program product embodiments for assigning a lane relationship between an autonomous vehicle (102) and other actors (104, 114, 116) near an intersection (410). For example, the method includes executing a simulation scenario that includes features of a scene through which a vehicle (102) may travel, the simulation scenario including one or more actors (104, 114, 116). The method further includes identifying an intersection (410) between a first road and a second road in the simulation scenario, wherein the intersection (410) is in a planned path of the vehicle (102). In response to one of the actors (104, 114, 116) occupying a lane (402) of either the first road or the second road, the method includes classifying the interaction between the vehicle (102) and the actor (104, 114, 116) based on the intersection (410), the path of the vehicle (102), and the lane (402) occupied by the actor (104, 114, 116).
G06V 20/58 - Recognition of moving objects or obstacles, e.g. vehicles or pedestriansRecognition of traffic objects, e.g. traffic signs, traffic lights or roads
27.
Uncertainty Based Scenario Simulation Prioritization and Selection
Disclosed herein are system, method, and computer program product embodiments for prioritizing scenario simulations. For example, the method includes generating a base scenario including constant parameters and variable parameters and generating multiple scenario variations, each of which is associated with a unique combination of values assigned to the variable parameters. The method further includes executing at least some scenario variations to determine scenario outcomes. The method further includes generating, using the at least some of the scenario variations and some of the scenario outcomes, a model for predicting the outcome of a scenario variation. The method further includes assigning, to each of the scenario variations, a priority based on the uncertainty associated with the predicted outcome for teach scenario variation, wherein a higher priority is associated with a predicted outcome having greater uncertainty.
G06F 30/27 - Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
G06K 9/62 - Methods or arrangements for recognition using electronic means
28.
INTEGRATED TRAJECTORY FORECASTING, ERROR ESTIMATION, AND VEHICLE HANDLING WHEN DETECTING AN OBSERVED SCENARIO
Disclosed herein are system, method, and computer program product aspects for enabling an autonomous vehicle (AV) to react to objects posing a risk to the AV. The system can monitor an object within a vicinity of the AV. A plurality of trajectories predicting paths the object will take can be generated, the plurality of trajectories being based on a plurality of inputs indicating current and past characteristics of the object. Using a learned model, a forecasted position of the object at an instance in time can be generated. An error value representing how accurate the forecasted position is versus an observed position of the object can be stored. Error values can be accumulated over a period of time. A risk factor can be assigned for the object based on the accumulated error values. A maneuver for the AV can be performed based on the risk factor.
A traffic light control system configured to provide instructions to a traffic light for testing performance of an autonomous vehicle as it approaches the traffic light includes a controller. The controller includes a transceiver in communication with the traffic light and a computer-readable memory storing a plurality of operation routines for the traffic light. The controller is configured to: select an operation routine of the plurality of operation routines on the computer-readable memory; and provide a control signal via the transceiver to the traffic light to control operation of the traffic light according to the selected operation routine. Controlling operation of the traffic light includes turning on or off at least one of a plurality of light emitters of the at least one traffic light and/or changing a brightness, frequency, or intensity of at least one of the plurality of light emitters of the traffic light.
G08B 5/36 - Visible signalling systems, e.g. personal calling systems, remote indication of seats occupied using electric transmissionVisible signalling systems, e.g. personal calling systems, remote indication of seats occupied using electromagnetic transmission using visible light sources
Disclosed herein are system, method, and computer program product embodiments for automated autonomous vehicle pose validation. An embodiment operates by generating a range image from a point cloud solution comprising a pose estimate for an autonomous vehicle. The embodiment queries the range image for predicted ranges and predicted class labels corresponding to lidar beams projected into the range image. The embodiment generates a vector of features from the range image. The embodiment compares a plurality of values to the vector of features using a binary classifier. The embodiment validates the autonomous vehicle pose based on the comparison of the plurality of values to the vector of features using the binary classifier.
B60W 40/12 - Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit related to parameters of the vehicle itself
G01S 17/89 - Lidar systems, specially adapted for specific applications for mapping or imaging
B60W 60/00 - Drive control systems specially adapted for autonomous road vehicles
B60W 50/00 - Details of control systems for road vehicle drive control not related to the control of a particular sub-unit
31.
AUTOMATIC BOOTSTRAP FOR AUTONOMOUS VEHICLE LOCALIZATION
An automated bootstrap process implemented as a simple state machine generates an initial pose for an autonomous vehicle, without reliance on human intervention. To trigger initiation of the bootstrap process automatically, the autonomous vehicle remains stationary. A GPS-derived position estimate, combined with lidar sweep data and HD map reference point cloud data, can be used to generate a pose using an iterative closest point algorithm. The bootstrap solution can then be automatically validated by a machine learning-based binary classifier trained with appropriate features. Full automation of the bootstrap process may facilitate launching a fleet service of autonomous vehicles.
B60W 60/00 - Drive control systems specially adapted for autonomous road vehicles
B60W 40/02 - Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit related to ambient conditions
Systems and methods for mutual discovery in autonomous rideshare between passengers and vehicles may receive a pick-up request to pick-up a user with an autonomous vehicle and interact with the user to perform an operation associated with the autonomous vehicle and/or update a user profile associated with the user.
B60W 60/00 - Drive control systems specially adapted for autonomous road vehicles
B60W 40/08 - Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit related to drivers or passengers
B60Q 5/00 - Arrangement or adaptation of acoustic signal devices
B60Q 1/50 - Arrangement of optical signalling or lighting devices, the mounting or supporting thereof or circuits therefor the devices being primarily intended to indicate the vehicle, or parts thereof, or to give signals, to other traffic for indicating other intentions or conditions, e.g. request for waiting or overtaking
Provided are systems, methods, and computer program products for severity classification of simulated collisions in self-driving systems of simulated environments, comprising controlling a simulated autonomous vehicle (AV) in a road during a plurality of simulated driving scenarios involving a road actor, automatically detecting a collision based on an intersection between affected portions of a simulated AV and affected portions the road actor, generating a plurality of collision impact scores, wherein each impact score of the plurality of collision impact scores signals a severity of a different impact type of collision, and classifying the severity of the collision based on the plurality of collision impact scores for the affected portion of the simulated AV and road actor.
H04L 67/289 - Intermediate processing functionally located close to the data consumer application, e.g. in same machine, in same home or in same sub-network
34.
METHOD, SYSTEM, AND COMPUTER PROGRAM PRODUCT FOR PARALLAX ESTIMATION FOR SENSORS FOR AUTONOMOUS VEHICLES
Methods, systems, and products for parallax estimation for sensors for autonomous vehicles may include generating a two-dimensional grid based on a field of view of a first sensor. For each respective point in the grid, a three-dimensional position of an intersection point between a first ray from the first sensor and a second ray from a second sensor may be determined. For each respective intersection point, a respective solid angle may be determined based on a first three-dimensional vector from the first sensor and a second three-dimensional vector from the second sensor to the intersection point. A matrix may be generated based on a distance from the first sensor, a distance from the second sensor, and the solid angle for each respective intersection point. At least one metric may be extracted from the matrix. An arrangement of the first and second sensors may be adjusted based on the metric(s).
B60W 40/02 - Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit related to ambient conditions
Disclosed herein are system and method embodiments to implement a validation of an SfM map. An embodiment operates by receiving a motion-generated map corresponding to a digital image, generating a first depth map, wherein the first depth map comprises depth information for one or more triangulated points located within the motion generated image. The embodiment further receives a light detection and ranging (lidar) generated point cloud including at least a portion of the one or more triangulated points, splats the lidar point cloud proximate to the portion of the one or more triangulated points and generates a second depth map for the portion and identifies an incorrect triangulated point, of the one or more triangulated points, based on comparing the first depth information to the second depth information. The incorrect triangulated points may be removed from the SfM map or marked with a low degree of confidence.
Systems may include a processor to, in response to determining at least one segment of a field of view (FOV) of a first sensor of an autonomous vehicle that overlaps with a FOV of at least one second sensor of the autonomous vehicle, calculate a scaling factor for diagnostic coverage for the at least one segment based on a value of modality overlap (MoD) for the at least one segment, calculate, based on the scaling factor, a value of a metric of hardware failure for the first sensor, and compare the value of the metric of hardware failure to a threshold value to determine whether to increase a diagnostic coverage of the first sensor. Methods, computer program products, and autonomous vehicles are also disclosed.
B60W 50/02 - Ensuring safety in case of control system failures, e.g. by diagnosing, circumventing or fixing failures
B60W 50/023 - Avoiding failures by using redundant parts
B60W 40/02 - Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit related to ambient conditions
37.
SYSTEM AND METHOD FOR DIFFERENTIAL COMPARATOR-BASED TIME-OF-FLIGHT MEASUREMENT WITH AMPLITUDE ESTIMATION
A signal delay component may be configured to receive a LiDAR output signal including an analog waveform from a LiDAR system, and provide a time-delayed LiDAR output signal including a time-delayed analog waveform. A differential comparator may be configured to receive the LiDAR output signal including the analog waveform and the time-delayed LiDAR output signal including the time-delayed analog waveform, and to provide a digital output signal. A processor may be configured to generate LiDAR data including a distance associated with the LiDAR output signal and an amplitude associated with the LiDAR output signal, the distance being based on a first time associated with a rising edge of the digital output signal, and the amplitude being based on a time difference between the first time associated with the rising edge of the digital output signal and a second time associated with a falling edge of the digital output signal.
Systems and methods for managing, accessing and/or using a service supported by a computing device. In some scenarios, the methods comprise by a computing device: intercepting a request to access the service sent along with a certificate including a first tenant identifier (the first tenant identifier identifying a first business entity other than a second business entity providing the service); using the first tenant identifier to obtain permission information from a datastore (the permission information specifying which resources of a plurality of resources can be returned in response to requests from the first business entity); generating a web authentication token including the first tenant identifier and the permission information; and initiating operations of the service in response to a validation of the web authentication token.
A system and method for transmitting data using an autonomous vehicle's LIDAR system. The autonomous vehicle may transmit the data by disengaging the LIDAR system' s transmitters and receivers from operating to detect external objects. The autonomous vehicle may also rotate the LIDAR system to locate one of a plurality of receivers external to the autonomous vehicle. Data stored within the autonomous vehicle may then be transmitted to an external system using a light-based communication path established between at least one of the LIDAR system's transmitters and an external receiver. The LIDAR system's transmitters and receivers may then be re-engaged so as to be operable to detect external objects.
This document describes methods by which a system determines a pickup / drop-off zone (PDZ) to which a vehicle will navigate to perform a ride service request. The system will define a PDZ that is a geometric interval that is within a lane of a road at the requested destination of the ride service request by: (i) accessing map data that includes the geometric interval; (ii) using the vehicle's length and the road's speed limit at the destination to calculate a minimum allowable length for the PDZ; (iii) setting, start point and end point boundaries for the PDZ having an intervening distance that is equal to or greater than the minimum allowable length; and (iv) positioning the PDZ in the lane at or within a threshold distance from the requested destination. The system will then generate a path to guide the vehicle to the PDZ.
G06V 20/58 - Recognition of moving objects or obstacles, e.g. vehicles or pedestriansRecognition of traffic objects, e.g. traffic signs, traffic lights or roads
G05D 1/02 - Control of position or course in two dimensions
41.
METHOD AND SYSTEM FOR CONFIGURING VARIATIONS IN AUTONOMOUS VEHICLE TRAINING SIMULATIONS
A method includes receiving a base simulation scenario that includes features of a scene through which a vehicle may travel and receiving a simulation variation for an object in the scene. The simulation variation defines multiple values for a characteristic of the object.
A method includes receiving a base simulation scenario that includes features of a scene through which a vehicle may travel and receiving a simulation variation for an object in the scene. The simulation variation defines multiple values for a characteristic of the object.
The method includes adding the simulation variation to the base simulation scenario to yield an augmented simulation scenario and applying the augmented simulation scenario to an autonomous vehicle motion planning model to train the motion planning model. The motion planning model iteratively simulates variations of the object based on values for the characteristic of the object. In response to each simulated variation of the object, the motion planning model selects a continued trajectory for the vehicle, wherein the continued trajectory is either the planned trajectory or an alternate trajectory.
Disclosed herein are system and method embodiments to implement a scout pulse LiDAR. An embodiment operates by emitting a leading sequence of two or more discrete pulses with a constant timing offset and large intensity ratio. These leading pulses are each called a 'scout pulse' because they scout ahead of the primary pulse to detect high intensity targets, which would otherwise saturate the detector. In the simplest configuration, there are only two pulses, one primary pulse (lagging, high power/intensity) and one scout pulse (leading, low power/intensity). In more complex configurations, there may be any number of multiple scout pulses, each with a unique time delay and intensity. In any configuration, the signals are emitted in order of ascending intensity, with the lowest intensity signal in front (first), and the highest intensity signal in the back (last) within the pulse train.
Method and systems for generating vehicle motion planning model simulation scenarios are disclosed. The method receives a base simulation scenario with features of a scene through which a vehicle may travel, defines an interaction zone in the scene, generates an augmentation element that includes an object and a behavior for the object, and adds the augmentation element to the base simulation scenario at the interaction zone to yield an augmented simulation scenario. The augmented simulation scenario is applied to a vehicle motion planning model to train the model.
A method includes receiving a base simulation scenario that includes features of a scene through which a vehicle may travel and receiving a simulation variation for an object in the scene. The simulation variation defines multiple values for a characteristic of the object. The method includes adding the simulation variation to the base simulation scenario to yield an augmented simulation scenario and applying the augmented simulation scenario to an autonomous vehicle motion planning model to train the motion planning model. The motion planning model iteratively simulates variations of the object based on values for the characteristic of the object. In response to each simulated variation of the object, the motion planning model selects a continued trajectory for the vehicle, wherein the continued trajectory is either the planned trajectory or an alternate trajectory.
B60W 40/00 - Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit
G05D 1/00 - Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
Systems and methods for complementary control of an autonomous vehicle are disclosed. A primary controller provides a first plurality of instructions to an AV platform for operating the AV in an autonomous mode along a planned path based on sensor data from a primary sensor system and a secondary sensor system, and provides information that includes a fallback monitoring region to a complementary controller. The complementary controller receives sensor data from the secondary sensor system that includes sensed data for a fallback monitoring region, analyzes the received sensor data to determine whether a collision is imminent with an object detected in the fallback monitoring region, and cause the AV platform to initiate a collision mitigation action if a collision is determined to be imminent.
Systems and methods for complementary control of an autonomous vehicle (AV) are disclosed. The methods include receiving information comprising an active trajectory of an AV that the AV intends to following for a planning horizon. The methods also include using the active trajectory to identify one or more regions in an environment of the AV such as a fallback monitoring region (FMR) and an active monitoring region (AMR), and generating one or more instructions for causing the AV to execute a collision mitigation action in response to an object being detected within the AMR. The methods further include transmitting the one or more instructions to an AV platform (AVP) for execution.
Methods, systems, and products for resolving level ambiguity for radar systems of autonomous vehicles may include detecting a plurality of objects with a radar system. Each first detected object may be associated with an existing tracked object based on a first position thereof. First tracked object data based on a first height determined for each first detected object may be stored. The first height may be based on the position of the detected object, the existing tracked object, and a tile map. Second tracked object data based on a second height determined for each second detected object not associated with the existing tracked object(s) may be stored. The second height may be based on a position of each second detected object, a vector map, and the tile map. A command to cause the autonomous vehicle to perform at least one autonomous driving operation may be issued.
Method and systems for generating vehicle motion planning model simulation scenarios are disclosed. The system receives a base simulation scenario with features of a scene through which a vehicle may travel. In some embodiments, the system generates an augmentation element that includes an object and a behavior for the object. In other embodiments, the system generates an augmentation element with a simulated behavior for an object in the scene by: (i) accessing a data store in which behavior probabilities are mapped to object types to retrieve a set of behavior probabilities for the object; and (ii) applying a randomization function to the behavior probabilities to select the simulated behavior. The system will add the augmentation element to the base simulation scenario at the interaction zone to yield an augmented simulation scenario. The system will then use the augmented simulation scenario to train an autonomous vehicle motion planning model.
A vehicle sensing system may include a housing for containing sensor electronics, the housing having at least one window being aligned with at least one of the sensor electronics within the housing, a fan arranged on the housing and configured to provide airflow through the housing, and a conditioning element having a plurality of fins forming configured to receive the airflow from the fan to cool the sensor electronics and to direct warmed air from the fins onto the window to provide the warmed air to the window.
Provided are systems, methods, and computer program products for monitoring, testing, or debugging transportation services, generating or transmitting an initiating message from a global manager cloud to an external service cloud, to invoke a transportation as a service (TaaS) message from external service clouds that comprise confirmation, also including generating or transmitting a simulated message from the global manager cloud to mirror the TaaS message, or a portion, transmitted on a TaaS link from the external service cloud to the on-vehicle modem, determining, a confidence threshold for a capability or security of the TaaS link, validating AV service data sent from the global manager cloud to a TaaS component in an on-vehicle black box of the autonomous vehicle system, validating AV compute data sent from the autonomous vehicle system to the TaaS component in the on-vehicle black box, validating TaaS message data received from the external service cloud.
H04L 41/082 - Configuration setting characterised by the conditions triggering a change of settings the condition being updates or upgrades of network functionality
Systems and methods for operating a mobile platform. The methods comprise, by a computing device: obtaining a LiDAR point cloud; using the LiDAR point cloud to generate a track for a given object in accordance with a particle filter algorithm by generating states of a given object over time (each state has a score indicating a likelihood that a cuboid would be created given an acceleration value and an angular velocity value); using the track to train a machine learning algorithm to detect and classify objects based on sensor data; and/or causing the machine learning algorithm to be used for controlling movement of the mobile platform.
Systems and methods for tracking an object. The method comprising: receiving, by a processor, a series of observations made over time for the object; selecting, by the processor, a plurality of sets of observations using the series of observations; causing, by the processor, the plurality of sets of observations to be used by at least one filter to generate a track for the object ( wherein the at least one filter uses sensor data associated with each of a plurality of frames of sensor data only once during generation of the track); and causing, by the processor, operations of an autonomous robot to be controlled based on the track for the object.
A system and method are disclosed for providing a bi-directional data communication link within a LIDAR assembly that has a stationary portion attached to an autonomous vehicle and a second portion rotatably connected to the stationary portion. The second portion may include one or more emitting/receiving devices (e.g., lasers) for detecting objects surrounding the autonomous vehicle. A first printed circuit board assembly (PCBA) having a first optical transceiver may be located within the stationary portion. A second PCBA having a second optical transceiver may be located within the second portion. A hollow shaft may be positioned so as to extend between the stationary portion and the second portion.
H04B 10/80 - Optical aspects relating to the use of optical transmission for specific applications, not provided for in groups , e.g. optical power feeding or optical transmission through water
G01S 17/931 - Lidar systems, specially adapted for specific applications for anti-collision purposes of land vehicles
G05D 1/02 - Control of position or course in two dimensions
54.
METHOD AND SYSTEM FOR PREDICTING BEHAVIOR OF ACTORS IN AN ENVIRONMENT OF AN AUTONOMOUS VEHICLE
Methods by which an autonomous vehicle may predict actions of other actors are disclosed. A vehicle will assign either a high priority rating or a low priority rating to each actor that it detects. The vehicle will then generate a forecast for each of the detected actors. Some of not all high priority actors will receive a high resolution forecast. Low priority actors, and optionally also some of the high priority actors, will receive a low resolution forecast. The system will the forecasts to predict actions for the actors. The autonomous vehicle will then use the predicted actions to determine its trajectory.
Methods of refining a planned trajectory of an autonomous vehicle are disclose. For multiple cycles as the vehicle moves along the trajectory, the vehicle will perceive nearby objects. The vehicle will use the perceived object data to calculate a set of candidate updated trajectories. The motion planning system will measure a discrepancy between each candidate updated trajectory and the current trajectory by: (i) determining waypoints along each trajectory; (ii) determining distances between at least some of the waypoints; and (iii) using the distances to measure the discrepancy between the updated trajectory and the current trajectory. The system will use the discrepancy to select, from the set of candidate updated trajectories, a final updated trajectory for the vehicle to follow.
Methods of determining relevance of objects that a vehicle detected are disclosed. A system will receive a data log of a run of the vehicle. The data log includes perception data captured by vehicle sensors during the run. The system will identify an interaction time, along with a look-ahead lane based on a lane in which the vehicle traveled during the run. The system will define a region of interest (ROI) that includes a lane segment within the look-ahead lane. The system will identify, from the perception data, objects that the vehicle detected within the ROI during the run. For each object, the system will determine a detectability value by measuring an amount of the object that the vehicle detected. The system will create a subset with only objects having at least a threshold detectability value, and it will classify any such object as a priority relevant object.
A system will generate a vector map of a geographic area using a method that includes receiving a birds-eye view image of a geographic area. The birds-eye view image comprises various pixels. The system will process the birds-eye view image to generate a spatial graph representation of the geographic area, and it will save the node pixels and the lines to a vector map data set. The processor may be a component of a vehicle such as an autonomous vehicle. If so, the system may use the vector map data set to generate a trajectory for the vehicle as the vehicle moves in the geographic area.
Systems for managing access to an autonomous vehicle includes an autonomous vehicle including a plurality of storage compartments, wherein each of the plurality of storage compartments comprises a locking mechanism and at least one processor to receive data associated with an item to be positioned in a storage compartment of the plurality of storage compartments, determine that one of the plurality of storage compartments has storage capacity for the item, designate one of the plurality of storage compartments for storage of the item, activate the locking mechanism of the designated storage compartment to lock the designated storage compartment after the item is positioned in the designated storage compartment, and activate the locking mechanism of the designated storage compartment to unlock the designated storage compartment to allow removal of the item from the designated storage compartment. Methods, computer program products, and autonomous vehicles are also disclosed.
Implementing systems and methods for operating a LiDAR system. The methods comprise: supplying current from a laser diode bar driver of the LiDAR system to a light source of the LiDAR system; passing the current through a laser diode bar of the light source (the laser diode bar comprising a plurality of laser diodes electrically connected in series); emitting a light beam from the light source when current is passing through the plurality of laser diodes; and/or receiving light reflected off an object.
H01S 5/40 - Arrangement of two or more semiconductor lasers, not provided for in groups
H01S 5/185 - Surface-emitting [SE] lasers, e.g. having both horizontal and vertical cavities having only horizontal cavities, e.g. horizontal cavity surface-emitting lasers [HCSEL]
Systems and methods for operating an autonomous vehicle. The methods comprising: obtaining, by a computing device, loose-fit cuboids overlaid on 3D graphs so as to each encompass LiDAR data points associated with a given object; defining, by the computing device, an amodal cuboid based on the loose-fit cuboids; using, by the computing device, the amodal cuboid to train a machine learning algorithm to detect objects of a given class using sensor data generated by sensors of the autonomous vehicle or another vehicle; and causing, by the computing device, operations of the autonomous vehicle to be controlled using the machine learning algorithm.
A ride service system will determine a stopping location for an autonomous vehicle (AV) before the AV picks up a passenger in response to a ride service request. The system will determine a pickup area for the request, along with a loading point within a pickup area, and the AV will navigate along the route toward the pickup area. Before the AV reaches the pickup area, the system will determine whether it received a departure confirmation indicating that the passenger is at the loading point. If the system received the departure confirmation, the AV will navigate into the pickup area and stop at the loading point; otherwise, the AV will either (a) navigate to an intermediate stopping location before reaching the pickup area or (b) pass through the pickup area.
This document describes methods and systems for enabling an autonomous vehicle (AV) to determine a path to a stopping location. The AV will determine a desired stop location (DSL) that is associated with a service request. The AV's motion control system will move the AV along a path to the DSL. While moving along the path, the AV's perception system will detect ambient conditions near the DSL. The ambient conditions will be parameters associated with a stopping rule. The AV will apply the stopping rule to the ambient conditions to determine whether the stopping rule permits the AV to stop at the DSL. If the stopping rule permits the AV to stop at the DSL, the motion control system will move the AV to, and stop at, the DSL. Otherwise, the motion control system will not stop the AV at the DSL.
Systems and methods for controlling navigation of an autonomous vehicle through an intersection are disclosed. The methods include determining a loiter pose of an autonomous vehicle for stopping at a point within the intersection before initiating an unprotected turn for traversing the intersection. One or more distinct classes of trajectories are then identified, each of which is associated with multiple trajectories that take the same combination of discrete actions with respect to the loiter pose. A constraint set for each of the one or more distinct classes of trajectories is then be computed based on the loiter pose, and a candidate trajectory is determined for each of the one or more distinct classes based on the corresponding constraint set. A trajectory for the autonomous vehicle for executing the unprotected turn for traversing the intersection is selected from amongst the candidate trajectories.
Systems and methods for controlling navigation of an autonomous vehicle for making an unprotected turn while traversing an intersection. The methods may include identifying a loiter pose of an autonomous vehicle for stopping at a point in an intersection before initiating an unprotected turn, initiating navigation of the autonomous vehicle to the loiter pose when a traffic signal is at a first state, determining whether the traffic signal has changed to a second state during or after navigation of the autonomous vehicle to the loiter pose, and in response to determining that the traffic signal has changed to the second state, generating a first trajectory for navigating the autonomous vehicle to execute the unprotected turn if the expected time for moving the autonomous vehicle from a current position to a position when the autonomous vehicle has fully exited an opposing conflict lane is less than a threshold time.
Methods and systems for enabling an autonomous vehicle (AV) to determine a path to a stopping location are disclosed. Upon receipt of a service request, the AV will determine a desired stop location (DSL) and state information for the service request. The AV using the DSL and the state information to define a pickup/ drop-off interval that comprises an area of a road that includes the DSL. When approaching the pickup/drop-off interval, the AV will uses its perception system to determine whether an object is occluding the DSL. If no object is occluding the DSL, the AV will continue along the path toward the DSL. However, if an object is occluding the DSL, the AV will identify and move to anon-occluded alternate stop location (ASL) within the pickup/drop-off interval. The ASL must satisfy one or more permissible stopping location criteria.
Systems, methods, and computer-readable media are disclosed for context aware verification for sensor pipelines. Autonomous vehicles (AVs) may include an extensive number of sensors to provide sufficient situational awareness to perception and control systems of the AV. For those systems to operate reliably, the data coming from the different sensors should be checked for integrity. To this end, the systems and methods described herein may use contextual clues to ensure that the data coming from the different the sensors is reliable.
B60W 40/02 - Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit related to ambient conditions
B60W 60/00 - Drive control systems specially adapted for autonomous road vehicles
Systems and methods for map quality assurance and/or vehicle control. The methods comprise: generating, by the computing device, a plurality of simulation routes for a vehicle to traverse in a map; simulating, by the computing device, operations of the vehicle along each route of the plurality of simulation routes in the map; analyzing, by the computing device, results from the simulating to validate whether or not a quality of the map is validated; causing, by the computing device, the map to be used to control autonomous or semi-autonomous operations of the vehicle, when a determination is made that the quality of the map is validated; and performing a given operation other than said causing, when a determination is made that the quality of the map is not validated.
A system and method for inferring a stop line for a vehicle at an intersection are provided. The system includes a processor configured to detect from accessed map data that a traffic control measure is positioned before an intersection and determine whether a stop line for the detected traffic control measure is painted. The processor, in response to determining that no stop line is painted, identifies a restricted lane and infers a stop line. The processor infers the stop line by identifying, as a nearest lane conflict, a lane segment of a second road intersecting the first road at the intersection and advancing a location of the entry line as an intermediate stop line a distance toward the nearest lane conflict, until the intermediate stop line is at a target distance from a nearest boundary of the nearest lane conflict to form an inferred stop line.
Devices, systems, and methods are provided for counter-steering penalization. A device may analyze, by one or more processors, lane geometry associated with one or more lanes at a geographic location. The device may identify one or more corners in the lane geometry. The device may select one or more desired maximum steering angles of a steering wheel of an autonomous vehicle. The device may select weight values associated with the one or more desired maximum steering angles. The device may execute a path planning optimization based on the one or more desired maximum steering angles and the weight values.
Methods, systems, and products for generating an updated map for use with an autonomous vehicle driving operation or a simulation thereof may include obtaining first map data associated with a first map of a geographic location including a roadway, and the first map data may include at least one first lane segment. Second map data associated with a second map of the geographic location may be obtained, and the second map data may include at least one second lane segment. A plurality of non-overlapping areas may be determined based on the first lane segment(s) and the second lane segment(s). A first non-overlapping and/or a first warp point within the first non-overlapping area may be selected. The first lane segment(s) may be warped around the first warp point to increase a total overlapping area based on the based on the second lane segment(s) and the first lane segment(s) after warping.
Systems, methods, and autonomous vehicles for automated lane conflict estimation may obtain map data associated with a map of a geographic location including a roadway, determine, based on the map data, a relative lane geometry between a first lane segment and a second lane segment of a pair of overlapping lane segments; process, with a machine learning model, the relative lane geometry and a type of a traffic signal or sign associated with the pair of overlapping lane segments to generate a prediction of whether the first lane segment yields to the second lane segment for a given state of the traffic signal or sign; and use the prediction to at least one of generate a map including the lane segment associated with the prediction, facilitate at least one autonomous driving operation of an autonomous vehicle, or any combination thereof.
Systems, methods, and computer-readable media are disclosed for closed-loop control of a motor in a LIDAR system over a wireless power interface using data feedback over a unidirectional data communications interface. An example method may include receiving, by a controller on a first portion in a LIDAR system, from a second portion including a second motor, and over a unidirectional data communication interface, data associated with the second motor, wherein the second portion is configured to rotate relative to the first portion. An example method may also include providing, over a wireless power transfer interface, to the second portion, and based on the data, a power signal, wherein the power signal is used to provide power to the second motor.
Systems, methods, and computer-readable media are disclosed for a systems and methods for remote guidance for autonomous vehicles. An example method may include capturing, at a first time and by a camera of an autonomous vehicle, at least one of: an image or video feed of a first traffic signal at an intersection. The example method may also include classifying, based on the image or the video feed of the first traffic signal, a state of a color of the first traffic signal as unknown. The example method may also include halting movement of the autonomous vehicle at the intersection based on classifying the state of the color of the first traffic signal as unknown. The example method may also include sending a request for guidance to a remote operator device, the request including the image or video feed of the first traffic signal. The example method may also include receiving, from the remote operator device, a first guidance. The example method may also include performing, based on the first guidance, a first action including at least one of: remaining halted at the intersection or proceeding through the intersection.
B60W 60/00 - Drive control systems specially adapted for autonomous road vehicles
B60W 40/02 - Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit related to ambient conditions
G05D 1/00 - Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
B60W 50/00 - Details of control systems for road vehicle drive control not related to the control of a particular sub-unit
Devices, systems, and methods are provided for enhanced rider pairing of an autonomous vehicle (AV). A system may pair a first user profile of a first user located at a first location with a first autonomous vehicle (AV) to complete a trip to a destination selected by the first user. The system may detect a second AV at the first location, wherein the second AV is associated with a second user profile. The system may connect the second AV with the first user using a connection mechanism. The system may select a profile status of the first user profile based on the connection to the second AV. The system may pair the first user profile with the second AV based on the profile status.
G06K 19/06 - Record carriers for use with machines and with at least a part designed to carry digital markings characterised by the kind of the digital marking, e.g. shape, nature, code
G06K 7/10 - Methods or arrangements for sensing record carriers by electromagnetic radiation, e.g. optical sensingMethods or arrangements for sensing record carriers by corpuscular radiation
75.
SYSTEMS AND METHODS FOR GENERATING OBJECT DETECTION LABELS USING FOVEATED IMAGE MAGNIFICATION FOR AUTONOMOUS DRIVING
Systems and methods for processing high resolution images are disclosed. The methods include generating a saliency map of a received high-resolution image using a saliency model. The saliency map includes a saliency value associated with each of a plurality of pixels of the high-resolution image. The method then includes using the saliency map for generating an inverse transformation function that is representative of an inverse mapping of one or more first pixel coordinates in a warped image to one or more second pixel coordinates in the high-resolution image, and implementing an image warp for converting the high-resolution image to the warped image using the inverse transformation function. The warped image is a foveated image that includes at least one region having a higher resolution than one or more other regions of the warped image.
Devices, systems, and methods are provided for reducing interference of light detection and ranging (LIDAR) emissions. A vehicle may identify location information associated with a location of the vehicle. The vehicle may select, based on the location information, a modulation code associated with a LIDAR photodiode of the vehicle. The vehicle may emit, using the LIDAR photodiode, one or more LIDAR pulses based on the modulation code.
Devices, systems, and methods are provided for compressive sensing using photodiode data. A device may identify light detecting and ranging (LIDAR) data detected by a sensor, the LIDAR data including a first time-of-flight (ToF) and a second ToF. The device may generate, based on the first ToF, a first frequency value. The device may generate, based on the second ToF, a second frequency value. The device may generate, based on the first value, a first sinusoid. The device may generate, based on the second value, a second sinusoid. The device may generate, based on the first sinusoid and the second sinusoid, a compressed signal in a domain incoherent with the time domain. The device may extract range information based on the compressed signal, and may control operation of a vehicle based on the range information.
Systems/methods for operating a LiDAR system. The methods comprise: receiving a waveform representing light which was reflected off of a surface of an object; generating timestamp values for photon detection events triggered by pulses in the waveform; generating a count histogram of the timestamp values; inferring a trials histogram from the count histogram (the trials histogram representing a number of times a photodetector of the LiDAR system was available during reception of the waveform); generating an estimated range distance from the LiDAR system to the at least one object and an estimated intensity value for a given pulse of the waveform, based on results from analyzing the count histogram and the trials histogram; determining a position using the estimated range distance from the LiDAR system to the at least one object; and producing a LiDAR dataset comprising a data point defined by the position and the estimated intensity value.
Systems, methods, and computer-readable media are disclosed for characterizing LIDAR point cloud quality. An example method may involve capturing a first point cloud for a test target including a retroreflective object, the first point cloud including a first region. The example method may also involve capturing, by a LIDAR system, a second point cloud for the test target. The example method may also involve applying a penalty function to a first point in the second point cloud, wherein the first point is within an acceptable error threshold based on the first region. The example method may also involve applying a penalty function to a second point in the second point cloud, wherein the second point is outside of the acceptable error threshold based on the first region. The example method may also involve generating a first score for the first point and a second score for the second point based on the penalty function. The example method may also involve combining the first score and the second score to produce a point cloud quality metric for the second point cloud. The example method may also involve calibrating, based on the point cloud quality metric, the LIDAR system for the retroreflective object.
Devices, systems, and methods are provided for indoor localization. A self-driving vehicle may detect a first fiducial marker located at a first location within a building, wherein the first fiducial marker comprises first fiducial marker information associated with the first location. The self-driving vehicle may retrieve the first fiducial marker information from the first fiducial marker. The self-driving vehicle may generate localization information of the self-driving vehicle based on the first fiducial marker information. The self-driving vehicle may utilize the localization information to transition to a second location within the building, wherein the second location comprises a second fiducial marker.
B60W 40/02 - Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit related to ambient conditions
B60W 60/00 - Drive control systems specially adapted for autonomous road vehicles
G06F 9/06 - Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
B60W 50/00 - Details of control systems for road vehicle drive control not related to the control of a particular sub-unit
81.
SYSTEMS AND METHODS FOR TRACKING A POSITION OF A ROTATING PLATFORM OF A LIDAR SYSTEM
Systems and methods are provided herein for improved short range object detection in LiDAR systems. The associated systems may include a first portion and a second portion configured to rotate relative to one another. The system may also include a first magnet located on the second portion and arranged with a north pole of the first magnet facing a first direction. The system may also include a second magnet located on the second portion and arranged with a south pole of the second magnet facing the first direction. The system may also include a first sensor located on the first portion, wherein the first sensor is further configured to measure a first magnetic field of the first magnet and a second magnetic field of the second magnet as the first portion and second portion rotate relative to one another.
G01R 33/00 - Arrangements or instruments for measuring magnetic variables
G01R 33/02 - Measuring direction or magnitude of magnetic fields or magnetic flux
G01D 5/12 - Mechanical means for transferring the output of a sensing memberMeans for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for convertingTransducers not specially adapted for a specific variable using electric or magnetic means
G01S 17/931 - Lidar systems, specially adapted for specific applications for anti-collision purposes of land vehicles
82.
ASSESSING PRESENT INTENTIONS OF AN ACTOR PERCEIVED BY AN AUTONOMOUS VEHICLE
Methods of forecasting intentions of actors that an autonomous vehicle (AV) encounters in are disclosed. The AV uses the intentions to improve its ability to predict trajectories for the actors, and accordingly making decisions about its own trajectories to avoid conflict with the actors. To do this, for any given actor the AV determines a class of the actor and detects an action that the actor is taking. The system uses the class and action to identify candidate intentions of the actor and evaluating a likelihood of each candidate intention. The system repeats this process over multiple cycles to determine overall probabilities for each of the candidate intentions. The AV's motion planning system can use the probabilities to determine likely trajectories of the actor, and accordingly influence the trajectory that the AV will itself follow in the environment.
Systems/methods for operating an autonomous vehicle. The methods comprise, by a computing device: using sensor data to track an object that was detected in proximity to the autonomous vehicle; classifying the object into at least one dynamic state class of a plurality of dynamic state classes; transforming the at least one dynamic state class into at least one goal class of a plurality of goal classes; transforming the at least one goal class into at least one proposed future intention class of a plurality of proposed future intention classes; determining at least one predicted future intention of the object based on the proposed future intention class; and/or causing the autonomous vehicle to perform at least one autonomous driving operation based on the at least one predicted future intention determined for the object.
Systems/methods for operating an autonomous vehicle. The methods comprise: detecting an object in proximity to the autonomous vehicle; determining a path of travel for the object that comprises a number of data points that is equal to a given number of vehicle locations selected based on a geometry of a lane in which the object; generating cost curves respectively associated with the data points, each cost curve representing a displacement cost to be at a particular location along a given cross line that (i) passes through a respective data point of said data points and (ii) extends perpendicular to and between boundary lines of the lane; determining a polyline representing displacements of the cost curves from a center of the lane; defining a predicted path of travel for the object based on the polyline; and using the predicted path of travel for the object to facilitate autonomous driving operation(s).
B60Q 1/00 - Arrangement of optical signalling or lighting devices, the mounting or supporting thereof or circuits therefor
B60R 1/06 - Rear-view mirror arrangements mounted on vehicle exterior
B60W 30/08 - Predicting or avoiding probable or impending collision
B60Q 1/26 - Arrangement of optical signalling or lighting devices, the mounting or supporting thereof or circuits therefor the devices being primarily intended to indicate the vehicle, or parts thereof, or to give signals, to other traffic
G06V 20/58 - Recognition of moving objects or obstacles, e.g. vehicles or pedestriansRecognition of traffic objects, e.g. traffic signs, traffic lights or roads
85.
RARE EVENT SIMULATION IN AUTONOMOUS VEHICLE MOTION PLANNING
Methods of identifying corner case simulation scenarios that are used to train an autonomous vehicle motion planning model are disclosed. A system selects a scene that includes data captured by one or more vehicles over a time period. The data includes one or more actors that the vehicle's sensors perceived over the time period in a real-world environment. The system selects a scene that includes a safety threshold violation, and it identifies the trajectory of an actor that participated in the violation. The system generates simulated scenes that alter the trajectory of the actor in the selected scene, selects simulated scenes that are more likely to occur in the real world and that may include safety threshold violations that go beyond any that may be found in the original scene, and uses the selected simulated scenes to train an autonomous vehicle motion planning model.
G05D 1/00 - Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
B60W 60/00 - Drive control systems specially adapted for autonomous road vehicles
B60W 30/00 - Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
86.
SYSTEM, METHOD, AND COMPUTER PROGRAM PRODUCT FOR TOPOLOGICAL PLANNING IN AUTONOMOUS DRIVING USING BOUNDS REPRESENTATIONS
Provided are autonomous vehicles and methods of controlling autonomous vehicles through topological planning with bounds, including receiving map data and sensor data, expanding a topological tree by adding a plurality of nodes to represent a plurality of actions associated with the plurality of constraints, generating a bound based on a constraint in the geographic area, the bound associated with an action for navigating the autonomous vehicle relative to the at least one constraint, storing the bound in a central bound storage, linking a set of bounds of a tree node to the bound via a bound identifier, wherein the first bound is initially linked as an active bound, or alternatively, as an inactive bound after determining it is not the most restrictive bound at any sample index, and control the autonomous vehicle based on the topological tree, to navigate the plurality of constraints.
B60W 60/00 - Drive control systems specially adapted for autonomous road vehicles
B60W 40/02 - Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit related to ambient conditions
Systems, methods, and autonomous vehicles may obtain sensor data associated with an environment surrounding an autonomous vehicle; provide the sensor data to a plurality of plugins; independently determine, with each plugin, based on the sensor data, whether to request a remote guidance session for the autonomous vehicle, each plugin of the plurality of plugins including a different model that is applied by that plugin to the sensor data to determine whether to request the remote guidance session; receive, from at least one plugin, a request to initiate the remote guidance session; and in response to receiving the request to initiate the remote guidance session, communicate with a computing device external to the autonomous vehicle to establish the remote guidance session.
B60W 60/00 - Drive control systems specially adapted for autonomous road vehicles
B60W 40/02 - Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit related to ambient conditions
B60W 50/14 - Means for informing the driver, warning the driver or prompting a driver intervention
G05D 1/00 - Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
Devices, systems, and methods are provided for communications between autonomous and emergency vehicles. A method may include identifying, by an autonomous vehicle (AV), a first message received from a first vehicle, and identifying, by the AV, in the first message, information associated with identifying the AV, a security key associated with identifying the first vehicle, and an instruction associated with causing the AV to perform an action. The method may include authenticating, by the AV, based on the security key, the first vehicle, and controlling operation, based on the instruction and the information associated with identifying the AV, of the AV to perform the action.
H04L 67/12 - Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
H04W 4/46 - Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for vehicle-to-vehicle communication [V2V]
H04W 4/90 - Services for handling of emergency or hazardous situations, e.g. earthquake and tsunami warning systems [ETWS]
Systems and methods for controlling navigation of an autonomous vehicle are disclosed. The system receives information relating to a geonet that represents a portion of a map area within which the autonomous vehicle is allowed to operate, and a lane-level map comprising a plurality of lane segments corresponding to the map area. For each of the plurality of lane segments, the system identifies a match geonet element from a plurality of geonet elements included in the geonet, determines a match distance between the match geonet element and that lane segment, and selects that lane segment for inclusion in the geonet upon determining that the match distance is less than a threshold distance. An updated lane-level map is generated using one or more lane segments selected for inclusion in the geonet for use by an autonomous vehicle to navigate between an origin location and a destination location within the geonet.
Systems and methods for designing a robotic system architecture are disclosed. The methods include defining a software graph including a first plurality of nodes, and a first plurality of edges representative of data flow between the first plurality of tasks, and defining a hardware graph including a second plurality of nodes, and a second plurality of edges. The methods may include mapping the software graph to the hardware graph, modeling a latency associated with a computational path included in the software graph for the mapping between the software graph and the hardware graph, allocating a plurality of computational tasks in the computational path to a plurality of the hardware components to yield a robotic system architecture using the latency, and using the robotic system architecture to configure the robotic device to be capable of performing functions corresponding to the software graph.
Systems and methods for operating an autonomous vehicle. The methods comprising: obtaining one or more candidate vehicle trajectories for the autonomous vehicle and context information defining a state of an environment surrounding the autonomous vehicle; assigning class(es) to a scenario specified by the context information and a first candidate vehicle trajectory; generating a first quality score for the first candidate vehicle trajectory using scoring function(s) selected based on the assigned class(es); select a candidate vehicle trajectory based on the first quality score associated with the first candidate vehicle trajectory and second quality score(s) associated with at least one second candidate vehicle trajectory; and causing the autonomous vehicle to perform autonomous driving operations using the selected candidate vehicle trajectory.
B60W 60/00 - Drive control systems specially adapted for autonomous road vehicles
B60W 40/02 - Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit related to ambient conditions
B60W 50/00 - Details of control systems for road vehicle drive control not related to the control of a particular sub-unit
Systems and methods are provided for navigating a vehicle to veer around a lane obstruction safely into a neighboring lane. The system may plan a trajectory around the obstructed lane. Over a temporal horizon, the system determines temporal margins by measuring an amount of time between a predicted state of a moving actor in the neighboring lane and a predicted state of the vehicle. The system identifies a minimum temporal margin of the temporal margins and determines whether the minimum temporal margin is equal to or larger than a required temporal buffer. If the minimum temporal margin is equal to or larger than the required temporal buffer, the system generates a motion control signal to cause the vehicle to follow the trajectory to veer around the obstruction into the neighboring lane. Otherwise, the system generates a motion control signal to cause the vehicle to reduce speed or stop.
A system receives a road network map that corresponds to a road network that is in an environment of an autonomous vehicle. For each of the one or more lane segments, the system identifies one or more conflicting lane segments from the plurality of lane segments, each of which conflicts with the lane segment, and adds conflict data pertaining to a conflict between the lane segment and the one or more conflicting lane segments to a set of conflict data. The system analyzes the conflict data to identify a conflict cluster that is representative of an intersection. The system groups predecessor lane segments and the successor lane segments as inlets or outlets of the intersection, generates an outer geometric boundary of the intersection, generates an inner geometric boundary of the intersection, creates a data representation of the intersection and adds the data representation to the road network map.
Systems and methods for on-board selection of data logs for training a machine learning model are disclosed. The system includes an autonomous vehicle having a plurality of sensors and a processor. The processor receives a plurality of unlabeled images from the plurality of sensors, a machine learning model, and a loss function corresponding to the machine learning model. For each of the plurality of images, the processor then determines one or more predictions using the machine learning model, compute an importance function based on the loss function and the one or more predictions, and transmit that image to a remote server for updating the machine learning model when a value of the importance function is greater than a threshold.
Systems and methods for generating operating an autonomous vehicle. The methods comprise: obtaining LiDAR point cloud data generated by a LiDAR system of the autonomous vehicle; inspecting the LiDAR point cloud data to infer a health of LiDAR beams; identifying bad quality point cloud data based on the inferred health of the LiDAR beams; removing the bad quality point cloud data from the LiDAR point cloud data to generate modified LiDAR point cloud data; and causing the autonomous vehicle to perform at least one autonomous driving operation or mode change based on the modified LiDAR point cloud data.
Systems and methods are disclosed for a fanless design of a rotating LIDAR system with integrated cleaning and cooling. An example system may include an enclosure including one or more electronics. The example system may also include a cooling element provided externally to the enclosure, the cooling element comprising one or more horizontal fins.
A system includes a computing device of an autonomous vehicle and a computer-readable storage medium that includes one or more programming instructions. The system identifies one or more lead objects located in front of the autonomous vehicle, and, for each of the one or more lead objects that are identified, determines an action type associated with the lead object which is used to generate a longitudinal plan for the autonomous vehicle.
B60W 30/09 - Taking automatic action to avoid collision, e.g. braking and steering
B60W 30/095 - Predicting travel path or likelihood of collision
G06V 20/58 - Recognition of moving objects or obstacles, e.g. vehicles or pedestriansRecognition of traffic objects, e.g. traffic signs, traffic lights or roads
G05D 1/02 - Control of position or course in two dimensions
98.
METHODS AND SYSTEM FOR PREDICTING TRAJECTORIES OF UNCERTAIN ROAD USERS BY SEMANTIC SEGMENTATION OF DRIVABLE AREA BOUNDARIES
Methods and systems for controlling navigation of an autonomous vehicle for traversing a drivable area are disclosed. The methods include receiving information relating to a drivable area that includes a plurality of polygons, identifying a plurality of logical edges that form a boundary of the drivable area, sequentially and repeatedly analyzing concavities of each the plurality of logical edges until identification of a first logical edge that has a concavity greater than a threshold, creating a first logical segment of the boundary of the drivable area. This segmentation may be repeated until each of the plurality of logical edges has been classified. The method may include creating and adding (to a map) a data representation of the drivable area that comprises an indication of the plurality of logical segments, and adding the data representation to a road network map comprising the drivable area.
Vehicle driver assistance and warning systems that alert a driver of a vehicle to wrong-way driving and/or imminent traffic control measures (TCMs) are disclosed. The system will identify a region of interest around the vehicle, access a vector map that includes the region of interest, and extract lane segment data associated with lane segments that are within the region of interest. The system will analyze the lane segment data and the vehicle's direction of travel to determine whether motion of the vehicle indicates that either: (a) the vehicle is traveling in a wrong-way direction for its lane; or (b) the vehicle is within a minimum stopping distance to an imminent TCM in its lane. When the system detects either condition, it will cause a driver warning system of the vehicle to output a driver alert.
Systems, methods, and computer-readable media are disclosed for a systems and methods for intra-shot dynamic LIDAR detector gain. One example method my include receiving first image data associated with a first image of an object illuminated at a first wavelength and captured by a camera at the first wavelength, the first image data including first pixel data for a first pixel of the first image and second pixel data for a second pixel of the first image. The example method may also include calculating a first reflectance value for the first pixel using the first pixel data. The example method may also include calculating a second reflectance value for the second pixel using the second pixel data. The example method may also include generating, using first reflectance value and the second reflectance value, a first reflectance distribution of the object.
