Abstract: Systems and methods for measuring autonomous vehicle (AV) capabilities in a simulation environment are provided. A method includes selecting, by a computer-implemented system, a first plurality of sampling points in an N-dimensional parameter space associated with a vehicle capability test, classifying, by the computer-implemented system, each sampling point of the first plurality of sampling points into a first class based on a vehicle passing a test scenario associated with the respective sampling point; or a second class based on the vehicle failing the test scenario associated with the respective sampling point; and determining, by the computer-implemented system based on the classifying, a capability of the vehicle. The classifying can include computing a first hyperplane in the N-dimensional parameter space to separate the first plurality of sampling points into the first class and the second class.

Abstract: Systems and methods for failover handling at a vehicle in response to a degraded state of operation are provided. For example, a method includes receiving, from a fallback vehicle path planner of a vehicle, data indicative of a fallback path; storing, at a memory of the vehicle, the data indicative of the fallback path; receiving, from a primary vehicle path planner of the vehicle, data indicative of a primary path; receiving an event trigger indicative of a degraded operating condition associated with the primary vehicle path planner; selecting, in response to the event trigger, the fallback path over the primary path; and sending, to a control system of the vehicle in response to the selecting, the stored data indicative of the fallback path.

Abstract: Systems and techniques are provided for rare scenario handling in autonomous vehicles. In some aspects, an AV management system can determine a target likelihood value range for identifying relevant rare scenarios. In some cases, the AV management system may use the target likelihood value range to generate new relevant rare scenarios that have a likelihood value that falls within the target likelihood value range. In some examples, the AV management system may initiate simulations of the generated relevant rare scenarios and capture synthetic AV scene data, which can be used to train machine learning models used in AVs. As a result, the performance of the AVs may be improved when faced with rare scenarios.

Abstract: The subject technology is related to autonomous vehicles (AV) and, in particular, to calibration of an sensors of an AV on open roads after calibrating the sensors in an undefined training area. An example method includes calibrating a plurality of sensors of the AV based on performing a plurality of training steps of increasing complexity within the undefined environment, wherein the plurality of sensors of the AV are uncalibrated with respect to each other, determining that the AV satisfies an open road requirement to navigate an open road based on completing the plurality of training steps in the undefined environment, and operating the AV on open roads subject to at least one constraint. The method of claim 1, wherein the at least one constraint comprises a list of prohibited maneuvers that limit operation of the AV on open roads. The constraints are configured to dynamically change.

Abstract: Platforms to support and manage an autonomous vehicle (AV) fleet can be implemented on and supported by cluster infrastructure. Cluster infrastructure may include different clusters, such as a cluster for an AV fleet with safety drivers, and a cluster for an AV fleet without safety drivers. Updates to the cluster infrastructure can be made to multiple clusters at once. Such updates may cause an outage that impacts multiple clusters and create a massive vehicle retrieval event for all AV fleets. To mitigate the risk and allow for prioritization of clusters, updates can be rolled out in a staged and ordered manner according to order values associated with different clusters. After applying an update to a cluster at a stage of the roll out, the cluster may be evaluated to confirm the success of the update, before the roll out can be moved to the next stage.

Abstract: Multi-sensor radar microDoppler holography is described. An example of a method includes performing a 2D Fourier transform calculation for multiple sets of raw Radar sensor data to generate Doppler spatial frequency map data, the raw sensor data including at least a first set of raw sensor data associated with a first Radar sensor at a first location and a second set of raw sensor data associated with a second Radar sensor at a second, different location; performing a DWT calculation of the Doppler spatial frequency map data; applying phase compensation to generate phase compensated data transforms; adding the phase compensated data transforms to generate a sum; performing an inverse 2D Fourier transform calculation to generate a transform result; and extracting microDoppler information and Doppler information extraction from the transform result.

Abstract: Systems and methods for a centrally designed vehicle HVAC system that cools vehicle components as well as the cabin and/or delivery containers. The HVAC system is designed with the ability to divert HVAC capacity from one vehicle system to another, allowing for more optimized HVAC usage. In some examples, the HVAC system disclosed herein allows for a more optimized HVAC system size, including decreased HVAC system weight and power consumption. In various implementations, the HVAC system uses back office prediction and remote control to make the determination of HVAC system bias based on current weather conditions as well as forecasted weather conditions. The HVAC system provides a comfortable vehicle cabin while ensuring the thermal condition of vehicle systems and components are managed to avoid interruptions to service.

Abstract: System, methods, and computer-readable media for an object path prediction model, and an associated training technique, to output a path that is considered an object collision path. The object path prediction model outputs a set of predicted paths for the object that are outputted to a trained planning algorithm, which includes paths that are most likely to occur and a path that is considered an object collision path. The predicted paths are sent to the trained planning algorithm and used for planning a trajectory for the autonomous vehicle that is associated with a low probability of colliding with or taking a sudden evasive action to avoid the object.

Abstract: Systems and techniques are provided for management of autonomous cargo by autonomous vehicles (AVs). An example method can include determining, based on data from one or more sensors, a location for deploying a ramp that enables robots to enter the AV, the location comprising an area free of obstacles having one or more dimensions above a threshold; generating an instruction configured to trigger the AV to stop at the location; based on a determination that the AV is at the stopping position, deploying the ramp; sending, to the robots, a message instructing the robots to enter a cabin of the AV via the ramp and guiding each robot to a respective location within the cabin; and based on a determination that the AV has reached a destination of one or more robots, deploying the ramp and guiding the one or more robots to exit the cabin via the ramp.

Abstract: Sensors coupled to a vehicle are calibrated, optionally using a dynamic scene with sensor targets around a motorized turntable that rotates the vehicle to different orientations. One vehicle sensor captures a representation of one feature of a sensor target, while another vehicle sensor captures a representation of a different feature of the sensor target, the two features of the sensor target having known relative positioning on the target. The vehicle generates a transformation that maps the captured representations of the two features to positions around the vehicle based on the known relative positioning of the two features on the target.

Abstract: For some embodiments of the present disclosure, systems and methods for using computer vision to guide processing of receive responses of RADAR sensors of a vehicle are described. A computer implemented method comprises receiving, with one or more receivers of RADAR sensors, environment receive RF responses, receiving region of interest (ROI) information including segments of a tentative set of ROIs with free space area boundaries from an image processor of an image processing chain for the computer vision, dynamically determining a number of polyphase filters based on a number of ROIs having dynamic scenes that are provided by the image processing chain, and adjusting parameters of the polyphase filters of a RADAR processing chain based on the ROI information.

Abstract: An AV may detect degraded states of other AVs. For instance, the AV may use its sensors to detect one or more other vehicles in the local area. The AV may determine whether any of these vehicles is a peer of the AV based on features of these vehicles captured by its sensors. Alternatively, the AV may determine if any vehicle is a peer based on encrypted communication with the vehicle. The AV may also determine whether any peer AV has a state that deviates from an expected or desirable state. The AV may communicate with an online system and request the online system to provide information for identifying the vehicle or detecting degraded states. The AV may also report degradations in peer AVs to the online system. The online system may recover the degraded AV or dispatch another AV to complete a task assigned to the degraded AV.

Abstract: A set of devices are coupled to a control area network (CAN) bus. At least some of the devices include switchable resistors that can apply a termination resistor to the CAN bus. Identification pins are used to identify devices on the CAN bus, and also to identify which device or devices are at the ends of the CAN bus. If a device is at an end of the CAN bus, the switch of the switchable resistor is set to couple the termination resistor to the CAN bus. Otherwise, the termination resistor is not coupled to the CAN bus.

Abstract: A unified electronic control unit (ECU) interface provides a bridge from ECU clients to the ECU. The ECU interface may be implemented on a vehicle's onboard computer, and it may be used by clients executing on the onboard computer and, in some cases, by clients outside the onboard computer. The ECU interface may receive a request from a client in a first messaging format, e.g., a local networking protocol used by processes running on the vehicle. The ECU interface translates the request into a second messaging format and transmits the request to the ECU. The ECU interface receives a response from the ECU and translates the response into the first messaging format for delivery to the client. The ECU interface may further perform authentication of the client and/or the ECU, packet serialization of the response from the ECU, packet diagnostics, and other functionalities associated with communicating with the ECU.

Abstract: Disclosed are embodiments for facilitating purposeful stress testing of autonomous vehicle response time with simulation. In some aspects, an embodiment includes receiving a request to launch a simulation scenario on an autonomous vehicle (AV) that is to operate on a real-world test course; initiating a simulation derived from the simulation scenario using a simulation driver that is executing on the AV; engaging operation of the AV on the real-world test course; coordinating a simulated AV position in the simulation with a physical AV position of the AV on the real-world test course; combining virtual entities from the simulation with physical entities on the real-world test course into a list of tracked objects for the AV; and causing the AV to respond to the list of tracked objects including the virtual entities and the physical entities during the operation of the AV on the real-world test course.

Abstract: Autonomous vehicles (AVs) utilize perception and understanding of objects on the road to predict behaviors of the objects, and to plan a trajectory for the vehicle. In some situations, an object may be occluded and undetected by an AV. However, a different AV viewing the same scene may detect the object. With information from multiple views of the same scene, it is possible to determine occlusion attributes for the object, such as relational occlusion information and extent of occlusion. For the AV that is driving on the road, having knowledge of the occluded object and the occlusion attributes can improve the performance of perception, understanding, tracking, prediction, and/or planning algorithms. For the algorithms, occlusion attributes can be generated from the multi-view data and included as part of labeled data for machine learning training. The models in the algorithms can learn to better handle occluded objects.

Abstract: Autonomous vehicles utilize perception to identify objects in a vehicle's surrounding environment and plan a trajectory. In perceiving an AV's surroundings, an object detection model uses sensor data from AV sensors to detect objects in the AV surroundings. An object detection model can be trained to detect objects using training datasets having sensor data and ground truth objects. In training, the object detection model uses the sensor data to identify objects in the locations of the ground truth objects. However, sometimes there is little or no sensor data corresponding to the ground truth objects, and the model is not able to learn patterns in sensor data to correctly detect the objects. Systems and methods are provided herein for removing ground truth objects that do not have sufficient corresponding sensor data from the training dataset, thereby preventing these objects from dominating the loss and interfering with the model learning useful patterns.

Abstract: An ultrasonic detection system provides enhanced object detection capabilities. The ultrasonic detection system can generate complex ultrasonic waveforms based on excitation voltage waveforms constructed using high frequency components. In certain embodiments, an ultrasonic detection system may be capable of producing multiple different waveforms, e.g., different waveforms output by different transmitters, or multiple time-multiplexed waveforms output by the same transmitter. The ultrasonic detection system may be included in an autonomous vehicle (AV) for object detection in the environment of the AV.

Abstract: Autonomous vehicles (AVs) utilize perception and understanding of objects on the road to predict behaviors of the objects, and to plan a trajectory for the vehicle. In some scenarios, an AV may benefit from having information about an object that is not within a perceivable area of the sensors of the AV. Another AV in the area that has the object within a perceivable area of the sensors of the other AV may share information with the AV. Rich information about the object determined by the other AV can be compressed using an encoder and transferred efficiently to the AV for inclusion in a temporal map that combines locally determined object information and transferred object information determined by other AV(s). The temporal map may be used in one or more parts of the software stack of the AV.

Abstract: Systems and methods for automatic removal for selected training data from a dataset are provided. Systems and methods are provided for identifying portions of radar data that contain information that is not present in camera and/or lidar data. The identified portions of the radar data can be processed by a neural network to provide the additional information. The identified parts of the radar data can then be processed while the remaining parts of the radar data remain unprocessed. In various examples, features can be extracted from identified regions of the radar data using a neural network and fused with camera and/or lidar features. In some examples, the fused features can be used for object detection.