Abstract: An autonomous platform can obtain sensor data descriptive of an actor in an environment of an autonomous vehicle and at least a portion of the environment of the autonomous vehicle that does not include the actor, the sensor data comprising at least one sweep of the environment of the autonomous vehicle; process the sensor data with a machine-learned perception model to generate a detection of the actor and one or more predicted future velocities; and determine a motion trajectory for the autonomous vehicle based at least in part on the detection and the one or more predicted future velocities.

Abstract: A light detection and ranging (LIDAR) system for a vehicle, includes a first scanner that receives a beam transmitted along an optical axis and projects the beam, a second scanner that is positioned along the optical axis, one or more motors that are coupled to the first scanner and the second scanner, and one or more processors. The one or more processors are configured to generate, based on one or more components of a particular waveform, a signal indicating data including a relative phase between the first scanner and the second scanner, and transmit the generated signal to the one or more motors, the signal causing the one or more motors to rotate the first scanner and the second scanner.

Abstract: A light detection and ranging (LIDAR) sensor assembly can comprise an optics assembly that includes a LIDAR sensor and a set of dovetail joint inserts. The LIDAR sensor assembly can further include a frame comprising a set of dovetail joint septums coupled to the set of dovetail joint inserts of the optics assembly.

Abstract: A light detection and ranging (LIDAR) sensor system includes a circuit module. The circuit module includes a silicon substrate having a first thermal feature. The circuit module includes a III-V semiconductor substrate coupled to the silicon substrate, the III-V semiconductor substrate having a second thermal feature. The circuit board includes an optical device coupled to the III-V semiconductor substrate, the optical device configured to output a transmit beam. The circuit module further includes a plurality of vias disposed in a particular portion of the silicon substrate, where the particular portion corresponds to the III-V semiconductor substrate, at least one of the plurality of vias having a third thermal feature. The LIDAR system further includes a scanner configured to direct the transmit beam to an environment of the vehicle.

Abstract: Systems and methods are disclosed for motion forecasting and planning for autonomous vehicles. For example, a plurality of future traffic scenarios are determined by modeling a joint distribution of actor trajectories for a plurality of actors, as opposed to an approach that models actors individually. As another example, a diversity objective is evaluated that rewards sampling of the future traffic scenarios that require distinct reactions from the autonomous vehicle. An estimated probability for the plurality of future traffic scenarios can be determined and used to generate a contingency plan for motion of the autonomous vehicle. The contingency plan can include at least one initial short-term trajectory intended for immediate action of the AV and a plurality of subsequent long-term trajectories associated with the plurality of future traffic scenarios.

Abstract: A light detection and ranging (LIDAR) system includes a transmitter, a first receiver, a second receiver, and one or more processors. The transmitter is configured to output a transmit beam. The first receiver is positioned on a first side of the transmitter and is configured to receive a first component of a return beam from reflection of the transmit beam by an object. The second receiver is positioned on a second side of the transmitter and is configured to receive a second component of the return beam. The one or more processors are configured to determine at least one of a range to the object or a velocity of the object and control operation of the autonomous vehicle based on the at least one of the range or the velocity.

Abstract: A light detection and ranging (LIDAR) transceiver includes optical antenna arrays and an optical switch. Some of the optical antenna arrays include a number of optical antennas and an optical splitter coupled to the optical antennas. The optical splitter may include a number of passive optical splitters. The optical splitter provides a portion of an input signal to the optical antennas. The optical switch is configured to selectively provide the input signal to at least one of the plurality of optical antenna arrays. The optical switch enables addressable field of view scanning by selectively providing the input signal to the plurality of antenna arrays, one array at a time.

Abstract: Example aspects of the present disclosure relate to an example computer-implemented method for data annotation for training machine perception models. The example method can include (a) receiving source sensor data descriptive of an object, the source sensor data having a source reference frame of at least three dimensions, wherein the source sensor data includes annotated data associated with the object; (b) receiving target sensor data descriptive of the object, the target sensor data having a target reference frame of at least two dimensions; (c) providing an input to a machine-learned boundary recognition model, wherein the input includes the target sensor data and a projection of the source sensor data into the target reference frame; and (d) determining, using the machine-learned boundary recognition model, a bounded portion of the target sensor data, wherein the bounded portion indicates a subset of the target sensor data descriptive of the object.

Abstract: A system and method for vehicle odometry using coherent range Doppler optical sensors. The system and method includes operating a Doppler light detection and ranging (LIDAR) system to collect raw point cloud data that indicates for a point a plurality of dimensions, wherein a dimension of the plurality of dimensions includes an inclination angle, an azimuthal angle, a range, or a relative speed between the point and the LIDAR system; determining a corrected velocity vector for the Doppler LIDAR system based on the raw point cloud data; and producing revised point cloud data that is corrected for the velocity of the Doppler LIDAR system.

Abstract: Systems and methods for controlling autonomous vehicle are provided. A method can include obtaining, by a computing system, data indicative of a plurality of objects in a surrounding environment of the autonomous vehicle. The method can further include determining, by the computing system, one or more clusters of the objects based at least in part on the data indicative of the plurality of objects. The method can further include determining, by the computing system, whether to enter an operation mode having one or more limited operational capabilities based at least in part on one or more properties of the one or more clusters. In response to determining that the operation mode is to be entered by the autonomous vehicle, the method can include controlling, by the computing system, the operation of the autonomous vehicle based at least in part on the one or more limited operational capabilities.

Abstract: Generally, the disclosed systems and methods utilize multi-task machine-learned models for object intention determination in autonomous driving applications. For example, a computing system can receive sensor data obtained relative to an autonomous vehicle and map data associated with a surrounding geographic environment of the autonomous vehicle. The sensor data and map data can be provided as input to a machine-learned intent model. The computing system can receive a jointly determined prediction from the machine-learned intent model for multiple outputs including at least one detection output indicative of one or more objects detected within the surrounding environment of the autonomous vehicle, a first corresponding forecasting output descriptive of a trajectory indicative of an expected path of the one or more objects towards a goal location, and/or a second corresponding forecasting output descriptive of a discrete behavior intention determined from a predefined group of possible behavior intentions.

Abstract: Systems and methods for providing a vehicle service are provided. In one example embodiment, a computer-implemented method includes receiving data indicative of a service request to provide a vehicle service for an entity with respect to one or more cargo items designated for autonomous transport. The method includes obtaining a first cargo item among the one or more cargo items, from a representative of the entity at a dedicated first transfer hub proximate to a first location associated with the first cargo item. The method includes controlling a first autonomous vehicle to transport the first cargo item from the first transfer hub to a dedicated second transfer hub proximate to a second location associated with the first cargo item. The method includes providing the first cargo item to a representative of the entity at the second transfer hub, to provide the vehicle service.

Abstract: Systems and methods for onboard vehicle certificate distribution are provided. A system can include a plurality of devices including a master device for authenticating processes and one or more requesting devices. The master device can include a master host security service configured to authenticate the one or more processes of the system. The master host security service can run a certificate authority to generate a root certificate and a private root key corresponding to the root certificate. A respective host security service can receive a request for a process manifest for a requesting process of a respective device from a respective orchestration service. The respective host security service can generate the process manifest for the requesting process and provide the process manifest to the requesting process. The requesting process can use the process manifest to communicate with the certificate authority to obtain an operational certificate based on the root certificate.

Abstract: A system and method for combining multiple functions of a light detection and ranging (LIDAR) system includes receiving a second optical beam generated by the laser source or a second laser source, wherein the second optical beam is associated with a second local oscillator (LO); splitting the second optical beam into a third split optical beam and a fourth split optical beam; transmitting, to the optical device, the third split optical beam and the fourth split optical beam; receiving, from the optical device, a third reflected beam that is associated with the third split optical beam and a fourth reflected beam that is associated with the fourth split optical beam; and pairing the third reflected beam with the second LO signal and the fourth reflected beam with the second LO signal.

Abstract: The present disclosure is directed to deviating from a planned path for an autonomous vehicle. In particular, a computing system comprising one or more computing devices physically located onboard an autonomous vehicle can identify one or more boundaries at least in part defining a lane in which the autonomous vehicle is traveling along a path of a planned route. Responsive to identifying one or more obstructions ahead of the autonomous vehicle along the path, the computing system can: determine one or more deviations from the path that would result in the autonomous vehicle avoiding the obstruction(s) and at least partially crossing at least one of the one or more boundaries; and generate, based at least in part on the deviation(s), a motion plan instructing the autonomous vehicle to deviate from the path such that it avoids the obstruction(s) and continues traveling along the planned route.

Abstract: A LIDAR sensor for an autonomous vehicle (AV) can include one or more lasers outputting one or more laser beams, one or more non-mechanical optical components to (i) receive the one or more laser beams, (ii) configure a field of view of the LIDAR sensor, and (iii) output modulated frequencies from the one or more laser beams, and one or more photodetectors to detect return signals based on the outputted modulated frequencies from the one or more laser beams.

Abstract: Systems and methods for generating attention masks are provided. In particular, a computing system can access sensor data and map data for an area around an autonomous vehicle. The computing system can generate a voxel grid representation of the sensor data and map data. The computing system can generate an attention mask based on the voxel grid representation. The computing system can generate, by using the voxel grid representation and the attention mask as input to a machine-learned model, an attention weighted feature map. The computing system can determine using the attention weighted feature map, a planning cost volume for an area around the autonomous vehicle. The computing system can select a trajectory for the autonomous vehicle based, at least in part, on the planning cost volume.

Abstract: A light detection and ranging (LIDAR) sensor system includes a dual-polarization optical antenna, a single-polarization optical antenna, a first receiver, and a second receiver. The dual-polarization optical antenna is configured to (i) emit a transmit beam with a first polarization orientation and (ii) and detect a return beam having a second polarization orientation. The single-polarization optical antenna is configured to detect the return beam having the second polarization orientation.