Abstract: Disclosed are systems and methods for scintillation-based neural network for RADAR target classification. In some aspects, a method includes generating a point cloud from radio frequency (RF) scene responses received from a radio detection and ranging (RADAR) sensor for a scanned scene; populating a rolling buffer with frame data from the point cloud, the frame data including radar cross section (RCS) values, RCS scintillation measurements, and velocity values for objects in the scanned scene; inputting the RCS scintillation measurements and velocity values for an object of the objects to a convolutional neural network (CNN); and receiving a classification of the object from the CNN, wherein the CNN is to utilize a probability density function (PDF) estimate of the RCS scintillation measurements and the velocity values to determine fits with one or more reference PDFs based on a Neyman-Pearson evaluation, and wherein the fits are assessed to classify the object.

Abstract: Systems and methods for a selectively-activated magnetic strip under a vehicle chassis that is powered to pick up nails and other metal debris. The magnetic strip can be selectively activated using an electromagnet powered by the vehicle and controlled by an onboard computer. The magnetic strip can generally be powered on while the vehicle is driving and selectively deactivated based on mapping data to avoid interactions with metallic infrastructure. The magnetic strip can be selectively deactivated based on vehicle parameters, such as vehicle speed.

Abstract: Aspects of the disclosed technology encompass solutions for automatically requesting a backup vehicle for passengers of an autonomous vehicle provisioned ride-hailing service. In some aspects, a process of the disclosed technology includes steps for collecting diagnostic data relating to at least one AV operation, and analyzing the diagnostic data to determine if the AV needs maintenance. Moreover, in response to a determination that the AV needs maintenance, the process can include steps for automatically requesting a backup service for a passenger of the AV. Systems and machine-readable media are also provided.

Abstract: Disclosed are systems and methods for synthetic loading of configurable logic devices. In some aspects, a method includes determining computational elements that are available for configuration in a configurable logic hardware device; executing a compilation process to program the available computational elements with a conditionally-enabled configuration and to program one or more load enable trees to enable a load of the conditionally-enabled configuration at the computational elements; configuring a software interface to enable the load of the conditionally-enabled configuration on portions of the computational elements via the one or more load enable trees based on a percentage enablement parameter; and enabling iteration through different percentage enablement parameter values, via the software interface, to cause the load of the conditionally-enabled configuration to be applied to different portions of the computational elements without recompiling the configurable logic hardware device.

Abstract: Curvelet-based low level fusion of camera and RADAR sensor information is disclosed and includes processing RADAR data corresponding to a scene to generate a RADAR point cloud and processing camera image data corresponding to the scene using a curvelet transform to identify a target of interest in the scene and generate for the target of interest a target type, (x,y) coordinate values, and a curvelet magnitude per decomposition level. If discrepancies exist between (x,y) coordinate values of the RADAR point cloud and the target type, (x,y) coordinate values, and curvelet magnitude per composition level of the target of interest, a portion of the RADAR data processing is repeated to regenerate the RADAR point cloud; otherwise, the RADAR point cloud to a perception stack of a vehicle.

Abstract: Disclosed are systems and methods for detecting weather conditions at a LiDAR sensor level. In some aspects, a method includes calculating a reference probability mass function (PMF) of at least one field of a point cloud generated from reference scene responses received from a light detection and ranging (LiDAR) sensor; calculating a current PMF for the at least one field of the point cloud generated from a current scene response received from the LiDAR sensor; determining a statistical difference between the reference PMF and the current PMF using a Kullbeck-Leibler (KL) divergence calculation; and responsive to the statistical difference satisfying a threshold for the at least one field, flagging an environmental change in the current scene response.

Abstract: Disclosed are systems and methods for a sensor synchronization system. In some aspects, a method includes synchronizing sensors of an autonomous vehicle (AV) to cause sampling of a first sensor of the sensors to occur in alignment with sampling of a second sensor of the sensors; determining a sampling time point for the first sensor based on the synchronizing the sensors, the sampling time point comprising a time when the first sensor is in alignment with the second sensor; providing the sampling time point to the first sensor; determining, at a controller circuit of the first sensor, an offset of the first sensor to apply to a local system time of the first sensor to cause a data acquisition of the first sensor to occur at the sampling time point; and causing the data acquisition to be performed at the first sensor using the sampling time point and the offset.

Abstract: There is disclosed a method of operating an autonomous vehicle (AV), including: detecting an alert condition within the AV via data from an electronic sensor suite of the AV; based at least in part on detecting the alert condition, automatically initiating a call with another party; and communicatively coupling a passenger of the AV to the conference call, whereby the passenger can communicate with the other party via the conference call.

Abstract: There is disclosed a method of operating an autonomous vehicle (AV), including: detecting an alert condition within the AV via data from an electronic sensor suite of the AV; based at least in part on detecting the alert condition, automatically initiating a call with another party; and communicatively coupling a passenger of the AV to the conference call, whereby the passenger can communicate with the other party via the conference call.

Abstract: There is disclosed a method of operating an autonomous vehicle (AV), including: detecting an alert condition within the AV via data from an electronic sensor suite of the AV; based at least in part on detecting the alert condition, automatically initiating a call with another party; and communicatively coupling a passenger of the AV to the conference call, whereby the passenger can communicate with the other party via the conference call.

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: There is disclosed a method of operating an autonomous vehicle (AV), including: detecting an alert condition within the AV via data from an electronic sensor suite of the AV; based at least in part on detecting the alert condition, automatically initiating a call with another party; and communicatively coupling a passenger of the AV to the conference call, whereby the passenger can communicate with the other party via the conference call.

Abstract: There is disclosed a method of operating an autonomous vehicle (AV), including: detecting an alert condition within the AV via data from an electronic sensor suite of the AV; based at least in part on detecting the alert condition, automatically initiating a call with another party; and communicatively coupling a passenger of the AV to the call, whereby the passenger can communicate with the other party via the call.

Abstract: An equipment inspection system receives data captured by a sensor of an autonomous vehicle (AV). The captured data describes a current state of equipment for servicing the AV. The equipment inspection system compares the captured data to a model describing an expected state of the equipment. The equipment inspection system determines, based on the comparison, that the equipment differs from the expected state. The equipment inspection system may transmit data describing the current state of the equipment to an equipment manager. The equipment manager may schedule maintenance for the equipment based on the current state of the equipment.

Abstract: A computing system that analyzes the network effects of avoidance areas on autonomous vehicle routing is described herein. The computing system includes a data store that comprises a set of avoidance areas through which the autonomous vehicle is prohibited from being routed. A grouping system identifies groups of avoidance areas. A graph construction system constructs a graph representation of the avoidance area groups. A ranking algorithm is evaluated over the graph representation to generate a ranking of the avoidance area groups by relative impact on routing metrics for routes through an operational area of the autonomous vehicle. A mapping vehicle can be dispatched to resolve avoidance areas in avoidance area groups indicating in the ranking as having a greater impact on routing metrics than other avoidance area groups.

Abstract: By way of example, there is disclosed a method of a device communicating messages in a vehicle, such as an autonomous vehicle (AV), including: participating in mutual authentication with a key server located on the vehicle; receiving from the key server a cryptographic key; using the cryptographic key for symmetric cryptography, comprising signing messages sent to or verifying messages received from another device of the vehicle; and clearing the cryptographic key at reboot.

Abstract: The present technology can detect potential labeling conflicts made during different labeling tasks when those tasks are checked in to ensure that a map database is free from conflicts that might interrupt publishing of a map. The present technology can determine whether a first labeled version of map portion is based on a most recent version for the map portion that is stored in the map database, and when it is determined that it is not, and there is an intervening version, the present technology can identify differences between the intervening version of the map portion and the first version of the map portion and identify differences between the second version of the map portion and the first version of the map portion. Based on the identified differences, the present technology can determine whether any of those differences are conflicting.

Abstract: Systems and methods are disclosed for detecting crosswalk locations. Crosswalk locations can be detected by determining at least two painted lines on a road surface, and then combining the at least two painted lines on the road surface into a grouping of related elements. The grouping of related elements can be classified into a crosswalk (or in some embodiments a type of crosswalk) based on attributes of the grouping of related elements, where the attributes of the grouping of the elements includes a distance between the at least two painted lines, and an orientation of the grouping of related elements on the road surface.

Abstract: A method of providing an onboard assistant for a vehicle, comprising: receiving sensor data from sensors of the vehicle; transforming the sensor data using a trained machine learning model to provide transformed sensor data; inferring from the transformed sensor data that a special condition for the vehicle requires intervention; and contacting an operator of the vehicle to inform the operator of the special condition and receive instructions for handling the special condition.