Abstract: Systems and methods for servicing vehicle messages utilizing a common communications infrastructure are provided. A method includes obtaining, by a vehicle computing system onboard an autonomous vehicle, a message including a cryptographic signature and contextual information, a request, or a command. The method includes determining an originating sender associated with the message based on the cryptographic signature and determining a message privilege for the message based on the originating sender. The originating sender is a process that generated the message. The method includes determining a response for the contextual information, the request, or the command based on the message privilege. The response is indicative of an acceptance or rejection of contextual information, an assignment of computing resources to a request, or an acceptance or rejection of a command. The method includes performing a vehicle action based on the response.

Abstract: An example method includes receiving a request to initiate a computer-controlled operational state of the autonomous vehicle. The example method includes verifying, using a cryptographically signed identifier, an identity of the autonomous vehicle and an authorization status associated with the autonomous vehicle. The example method includes verifying that a control subsystem of the autonomous vehicle is configured to execute the software version and that a map subsystem of the autonomous vehicle is configured to execute the map version. The example method includes verifying that one or more environmental conditions associated with the route for execution by the autonomous vehicle satisfy criteria. The example method includes receiving, from a human-machine interface device, a launch signal input.

Abstract: A system for determining a pose of a vehicle and building maps from vehicle priors processes received ground intensity LIDAR data including intensity data for points believed to be on the ground and height information to form ground intensity LIDAR (GIL) images including pixels in 2D coordinates where each pixel contains an intensity value, a height value, and x- and y-gradients of intensity and height. The GIL images are formed by filtering aggregated ground intensity LIDAR data falling into a same spatial bin on the ground and using a registration algorithm to align two GIL images relative to one another by estimating a 6-degree-of-freedom pose with associated uncertainty that minimizes error between the two GIL images. The aligned GIL images are provided as a pose estimate to a localizer. The system may provide online localization and pose estimation, prior building, and prior to prior alignment pose estimation using image-based techniques.

Abstract: A light detection and ranging (LIDAR) system includes a light source to emit light and a scanner. The scanner includes a fixed first portion including one or more coils, a rotatable second portion including one or more magnets and flexure components which oscillate in response to the one or more coils being driven, a scan element to rotate via rotation of the rotatable second portion and to direct the light emitted by the light source to an environment of a vehicle, an encoder to output a first signal indicating position or direction information associated with rotation of the rotatable second portion when the one or more coils are driven, and one or more controllers to provide an input associated with driving the one or more coils and to adjust the input based on the first signal output by the encoder and a second signal associated with the input.

Abstract: Techniques are disclosed for evaluating manual driving data using an AV control system based on differences between data generated using the AV control system and the manual driving data. In many implementations, manual driving data captures action(s) of a vehicle controlled by a manual driver. Additionally or alternatively, an additional AV control system can be trained using the evaluated manual driving data.

Abstract: An example method includes obtaining a LIDAR scan including a plurality of LIDAR points. The LIDAR scan being descriptive of an environment of an autonomous vehicle. The method includes obtaining a surfel map descriptive of the environment. The surfel map includes a plurality of surfels. The method includes classifying each of the plurality of LIDAR points as an explained LIDAR point or an unexplained LIDAR point based on an alignment of the LIDAR scan to the surfel map, wherein an explained LIDAR point is a LIDAR point that matches a surfel in the surfel map. The method includes shifting the LIDAR scan along a longitudinal direction for a plurality of iterations. The method includes determining a longitudinal bias for each of the plurality of iterations. The method includes performing an operation for the autonomous vehicle based on the longitudinal bias.

Abstract: Systems and methods for predicting interactions between objects and predicting a trajectory of an object are presented herein. A system can obtain object data associated with a first object and a second object. The object data can have position data and velocity data for the first object and the second object. Additionally, the system can process the obtained object data to generate a hybrid graph using a graph generator. The hybrid graph can have a first node indicative of the first object and a second node indicative of the second object. Moreover, the system can process, using an interaction prediction model, the generated hybrid graph to predict an interaction type between the first node and the second node. Furthermore, the system can process, using a graph neural network model, the predicted interaction type between the first node and the second node to predict a trajectory of the first object.

Abstract: A vehicle radar sensor utilizes Frequency Modulated Continuous Wave (FMCW) radar signals that incorporate non-uniform FMCW chirps having chirp profiles that differ from one another to sense one or more parameters of one or more objects in a field of view of the radar sensor. The chirp profiles may differ from one another in various manners, e.g., based on starting frequency, repetition interval, duration and/or slope, and among other advantages, may be used to enhance sensing of various parameters such as range, Doppler/velocity and/or angle.

Abstract: A teleoperations system may be used to generate virtual paths of travel for an autonomous vehicle based upon teleoperations system-provided suggestions, and virtual path suggestion constraints, e.g., based upon physical constraints associated with an autonomous vehicle such as minimum turning radius, trailer sweep, and the like, may be used assist in guiding a teleoperations system operator during generation of virtual path suggestions.

Abstract: A method is provided, that includes: receiving camera data from a perception system of an autonomous vehicle; and providing the camera data to a visual language model, where the visual language model includes a mapping of a corpus of images and a corpus of text to a common parameter space. The method further includes: receiving from the visual language model an output corresponding to one or more text tokens; accessing a configuration file comprising a plurality of text tokens representing a plurality of objects or events of interest to the autonomous vehicle; and identifying a respective object or event of interest in an environment of the autonomous vehicle by determining that a text token of the output matches a respective one of the plurality of text tokens in the configuration file. The autonomous vehicle can then be controlled based at least in part on the respective object or event of interest.

Abstract: A unified boundary machine learning model is capable of processing perception data received from various types of perception sensors on an autonomous vehicle to generate perceived boundaries of various semantic boundary types. Such perceived boundaries may then be used, for example, to control the autonomous vehicle, e.g., by generating a trajectory therefor. In some instances, the various semantic boundary types detectable by a unified boundary machine learning model may include at least a virtual construction semantic boundary type associated with a virtual boundary formed by multiple spaced apart construction elements, as well as an additional semantic boundary type associated with one or more other types of boundaries such as boundaries defined by physical barriers, painted or taped lines, road edges, etc.

Abstract: An autonomous vehicle control system and method may utilize a dual mode map including sparse map data for some portions of an environment that lacks some of the data maintained in dense map data for other portions of the environment. Sparse map data may be used, for instance, to address a recently-established construction area on a roadway that is incompatible with dense map data that was previously used to operate on the roadway, enabling operation of an autonomous vehicle in the construction area to proceed even in the absence of dense map data for the construction area, e.g., by dynamically augmenting the sparse map data to incorporate additional data sensed by a perception system of the autonomous vehicle.

Abstract: A live map system may be used to propagate observations collected by autonomous vehicles operating in an environment to other autonomous vehicles and thereby supplement a digital map used in the control of the autonomous vehicles. In addition, a live map system in some instances may be used to propagate location-based teleassist triggers to autonomous vehicles operating within an environment. A location-based teleassist trigger may be generated, for example, in association with a teleassist session conducted between an autonomous vehicle and a remote teleassist system proximate a particular location, and may be used to automatically trigger a teleassist session for another autonomous vehicle proximate that location and/or to propagate a suggested action to that other autonomous vehicle.

Abstract: A teleassist system may be used to assist with verifying road signs encountered by an autonomous vehicle, particularly road signs that may be new and/or temporary in nature, e.g., within construction zones, and thus not maintained in a map database utilized by the autonomous vehicle. Detection of an unmapped road sign by an autonomous vehicle, for example, may be used to initiate a teleassist session with a remote teleassist operator to facilitate autonomous vehicle compliance with the unmapped road sign.

Abstract: Systems and methods for determining whether a vehicle inspection station present within an environment of an autonomous vehicle is active or inactive are provided, to appropriately control the autonomous vehicle and to timely respond to detection of an active vehicle inspection station. When the vehicle inspection station is determined to be active, the autonomous vehicle can be controlled to arrive at an appropriate inspection location/spot within the vehicle inspection station, where while being held for vehicle inspection, the autonomous vehicle can be in an inspection mode. Systems and methods for further determining when or whether the vehicle inspection completes are also provided, to timely and appropriately release the autonomous vehicle from the inspection mode and to exit the vehicle inspection station.

Abstract: An example method includes (a) obtaining an object detection from a perception system that describes an object in an environment of the autonomous vehicle; (b) obtaining, from a reference dataset, a label that describes a reference position of the object in the environment; (c) determining a plurality of component divergence values respectively for a plurality of divergence metrics, wherein a respective divergence value characterizes a respective difference between the object detection and the label; (d) providing the plurality of component divergence values to a machine-learned model to generate a score that indicates an aggregate divergence between the object detection and the label, wherein the machine-learned model includes a plurality of learned parameters defining an influence of the plurality of component divergence values on the score; (e) evaluating a quality of a match between the object detection and the label based on the score.

Abstract: Systems and methods for controlling the motion of an autonomous are provided. In one example embodiment, a computer-implemented method includes obtaining data associated with an object within a surrounding environment of an autonomous vehicle. The data associated with the object is indicative of a predicted motion trajectory of the object. The method includes determining a vehicle action sequence based at least in part on the predicted motion trajectory of the object. The vehicle action sequence is indicative of a plurality of vehicle actions for the autonomous vehicle at a plurality of respective time steps associated with the predicted motion trajectory. The method includes determining a motion plan for the autonomous vehicle based at least in part on the vehicle action sequence. The method includes causing the autonomous vehicle to initiate motion control in accordance with at least a portion of the motion plan.

Abstract: A light detection and ranging (LIDAR) system may include one or more processors configured to transmit an optical signal to an environment. The one or more processors may receive, from the environment, a returned optical signal in response to transmitting the optical signal. The one or more processors may generate, based on the returned optical signal, an electrical signal. The one or more processors may determine a Doppler frequency shift in the returned optical signal based on the electrical signal. The one or more processors may adjust the electrical signal using the Doppler frequency shift. The one or more processors may divide the adjusted electrical signal into a plurality of electrical signals. The one or more processors may determine a range of the returned optical signal by performing an operation on the plurality of electrical signals in parallel.

Abstract: Systems and methods for improved vehicle-to-vehicle communications are provided. A system can obtain sensor data depicting its surrounding environment and input the sensor data (or processed sensor data) to a machine-learned model to perceive its surrounding environment based on its location within the environment. The machine-learned model can generate an intermediate environmental representation that encodes features within the surrounding environment. The system can receive a number of different intermediate environmental representations and corresponding locations from various other systems, aggregate the representations based on the corresponding locations, and perceive its surrounding environment based on the aggregated representations. The system can determine relative poses between the each of the systems and an absolute pose for each system based on the representations.

Abstract: Various examples are directed to systems and methods for controlling an autonomous vehicle. For example, a navigator system at an autonomous vehicle may generate a plurality of local routes beginning at a vehicle location and extending to a plurality of local route end points. The navigator system may access general route cost data, the general route cost data describing general route costs from the plurality of local route end points to a trip end point. The navigator system may select the first local route of the plurality of routes based at least in part on the general route cost data. A vehicle autonomy system at the autonomous vehicle may begin to control the autonomous vehicle along the first local route.