Abstract: An apparatus include a motor, a first scanner, and a second scanner. The first scanner is coupled to the motor, and the motor is configured to rotate the first scanner at a first angular velocity about a rotation axis to deflect a first beam incident in a third plane on the first scanner into a first plane different from the third plane. The second scanner is coupled to the motor, and the motor is configured to rotate the second scanner at a second angular velocity different from the first angular velocity about the rotation axis to deflect a second beam incident in the third plane on the second scanner into a second plane different from the third plane.

Abstract: Systems and methods for improved tracking of articulated vehicles can obtain, through one or more sensor systems onboard a vehicle, sensor data descriptive of an environment of the vehicle, the environment including an articulated vehicle having at least a first portion and a second portion; generate based on the sensor data, first state data for the first portion of the articulated vehicle and second state data for the second portion of the articulated vehicle; determine an articulated vehicle relationship between the first portion and the second portion based on the first state data for the first portion and the second state data for the second portion; generate, using an articulated vehicle motion model, synthetic motion data for the second portion based on the first state data for the first portion; and update the second state data of the second portion based on the synthetic motion data.

Abstract: Systems and methods are directed to generating behavioral predictions in reaction to autonomous vehicle movement. In one example, a computer-implemented method includes obtaining, by a computing system, local scene data associated with an environment external to an autonomous vehicle, the local scene data including actor data for an actor in the environment external to the autonomous vehicle. The method includes extracting, by the computing system and from the local scene data, one or more actor prediction parameters for the actor using a machine-learned parameter extraction model. The method includes determining, by the computing system, a candidate motion plan for the autonomous vehicle. The method includes generating, by the computing system and using a machine-learned prediction model, a reactive prediction for the actor based at least in part on the one or more actor prediction parameters and the candidate motion plan.

Abstract: A light detection and ranging (LIDAR) system includes a laser source and a polygon scanner. The laser source is configured to generate a first beam. The polygon scanner includes a frame and a plurality of mirrors coupled to the frame, each mirror comprising a glass material.

Abstract: Techniques for improving the performance of an autonomous vehicle (AV) by automatically annotating objects surrounding the AV are described herein. A system can obtain sensor data from a sensor coupled to the AV and generate an initial object trajectory for an object using the sensor data. Additionally, the system can determine a fixed value for the object size of the object based on the initial object trajectory. Moreover, the system can generate an updated initial object trajectory, wherein the object size corresponds to the fixed value. Furthermore, the system can determine, based on the sensor data and the updated initial object trajectory, a refined object trajectory. Subsequently, the system can generate a multi-dimensional label for the object based on the refined object trajectory. A motion plan for controlling the AV can be generated based on the multi-dimensional label.

Abstract: Systems and methods of the present disclosure are directed to a method for editing a machine-learned model to facilitate distributed processing. The method can include obtaining a machine-learned graph model comprising a plurality of connected nodes. The method can include determining a plurality of processing capabilities for a respective plurality of computation resources. The method can include determining a plurality of portions from the machine-learned graph model, wherein each of the plurality of portions comprises a respective subset of the plurality of nodes and a minimum processing capability. The method can include assigning each of the plurality of portions to a respective computation resource of the plurality of computation resources based at least in part on the minimum processing capability of a respective portion and the processing capability of the respective computation resource.

Abstract: An example method includes (a) generating a request to obtain log data descriptive of operation of an autonomous vehicle control system in a subject scenario, the log data indexed by an indexing parameter; (b) submitting the request to a log repository service, the log repository service configured to receive the request and serve, responsive to the request, log metadata; (c) loading, based on the log metadata and an index value of the indexing parameter, a log data sketch associated with the index value; and (d) loading, based on the log metadata and the index value, and responsive to an inspection indicator, detailed log data associated with the index value.

Abstract: Systems and methods for controlling an autonomous vehicle are provided. In one example embodiment, a computer-implemented method includes obtaining, from an autonomy system, data indicative of a planned trajectory of the autonomous vehicle through a surrounding environment. The method includes determining a region of interest in the surrounding environment based at least in part on the planned trajectory. The method includes controlling one or more first sensors to obtain data indicative of the region of interest. The method includes identifying one or more objects in the region of interest, based at least in part on the data obtained by the one or more first sensors. The method includes controlling the autonomous vehicle based at least in part on the one or more objects identified in the region of interest.

Abstract: A LIDAR device for a vehicle includes an integrated chip. The integrated chip includes a substrate layer, a cladding layer, a waveguide, a scattering array, and a reflector layer. The cladding layer is disposed on the substrate layer to form an interface with the substrate layer. The waveguide is disposed within the cladding layer and configured to route an infrared optical field. The scattering array is disposed within the cladding layer between the waveguide and the interface and perturbs the infrared optical field and scatters the infrared optical field into a first beam propagating toward a surface of the cladding layer and into a second beam propagating towards the interface. The reflector layer is disposed within the cladding layer between the waveguide and the surface of the cladding layer to reflect the first beam towards the interface.

Abstract: A method for coupling semiconductor optical components for a Light Detection and Ranging (LIDAR) system includes providing a first semiconductor optical component and a second semiconductor optical component; optically coupling a fiber array unit to the second semiconductor optical component; applying, by a vacuum component, a suction force to the second semiconductor optical component to couple the vacuum component to the second semiconductor optical component, wherein the fiber array unit is coupled to the vacuum component; and aligning the first semiconductor optical component with the second semiconductor optical component based on a measurement of light transmitted between the first semiconductor optical component and the fiber array unit via the second semiconductor optical component.

Abstract: A light detection and ranging (lidar) sensor system may include a laser source configured to generate a beam, an electronic module, and one or more processors. The electronic module may generate, based on the beam, an optical signal that is frequency-shifted by a frequency offset relative to a local oscillator (LO) signal. The electronic module may control a transmitter to transmit the optical signal to an environment. In response to transmitting the optical signal, the electronic module may receive a returned optical signal that is reflected from an object in the environment. The electronic module may generate a digital signal based on the received signal. The electronic module may digitally mix the digital signal based on the frequency offset to generate a sample signal. The one or more processors may determine, based on the sample signal, a range to the object.

Abstract: Systems and methods for generating synthetic testing data for autonomous vehicles are provided. A computing system can obtain map data descriptive of an environment and object data descriptive of a plurality of objects within the environment. The computing system can generate context data including deep or latent features extracted from the map and object data by one or more machine-learned models. The computing system can process the context data with a machine-learned model to generate synthetic motion prediction for the plurality of objects. The synthetic motion predictions for the objects can include one or more synthesized states for the objects at future times. The computing system can provide, as an output, synthetic testing data that includes the plurality of synthetic motion predictions for the objects. The synthetic testing data can be used to test an autonomous vehicle control system in a simulation.

Abstract: An example implementation includes generating a plurality of possible decisions with respect to one or more objects in an environment of the autonomous vehicle; generating an offline strategy search space, wherein: the offline strategy search space comprises a plurality of candidate strategies that respectively correspond to a plurality of cost functions, and a respective candidate strategy comprises one or more of the plurality of possible decisions; scoring the plurality of candidate strategies relative to a strategy that a human exemplar executed in the environment; and updating one or more parameters of the machine-learned model based on the scoring of the plurality of candidate strategies; and deploying the trained machine-learned model to the autonomous vehicle control system to control the autonomous vehicle, wherein: an online strategy search space generated using the deployed machine-learned model is configured to comprise a smaller number of candidate strategies than the offline strategy search spac

Abstract: Systems and methods related to controlling an autonomous vehicle (“AV”) are described herein. Implementations can obtain a plurality of instances that each include input and output. The input can include actor(s) from a given time instance of a past episode of locomotion of a vehicle, and stream(s) in an environment of the vehicle during the past episode. The actor(s) may be associated with an object in the environment of the vehicle at the given time instance, and the stream(s) may each represent candidate navigation paths in the environment of the vehicle. The output may include ground truth label(s) (or reference label(s)). Implementations can train a machine learning (“ML”) model based on the plurality of instances, and subsequently use the ML model in controlling the AV. In training the ML model, the actor(s) and stream(s) can be processed in parallel.

Abstract: The present disclosure is directed to a light detection and ranging (LIDAR) sensor system for a vehicle. The LIDAR sensor system includes a light source configured to output a beam. The LIDAR sensor system includes a semiconductor optical amplifier (SOA) array including a plurality of individualized SOA dies. A first individualized SOA die of the plurality of individualized SOA dies is spaced apart from a second individualized SOA die of the plurality of individualized SOA dies such that a spacing is defined between the first individualized SOA die and the second individualized SOA die. The SOA array is configured to receive the beam from the light source and amplify the beam.

Abstract: Systems and methods for generating motion plans for autonomous vehicles are provided. An autonomous vehicle can include a machine-learned motion planning system including one or more machine-learned models configured to generate target trajectories for the autonomous vehicle. The model(s) include a behavioral planning stage configured to receive situational data based at least in part on the one or more outputs of the set of sensors and to generate behavioral planning data based at least in part on the situational data and a unified cost function. The model(s) includes a trajectory planning stage configured to receive the behavioral planning data from the behavioral planning stage and to generate target trajectory data for the autonomous vehicle based at least in part on the behavioral planning data and the unified cost function.

Abstract: Example aspects of the present disclosure describe a scene generator for simulating scenes in an environment. For example, snapshots of simulated traffic scenes can be generated by sampling a joint probability distribution trained on real-world traffic scenes. In some implementations, samples of the joint probability distribution can be obtained by sampling a plurality of factorized probability distributions for a plurality of objects for sequential insertion into the scene.

Abstract: A system and method for scanning of coherent LIDAR. The system includes a motor, a laser source configured to generate an optical beam, and a deflector. A first facet of the plurality of facets has a facet normal direction. The deflector is coupled to the motor and is configured to rotate about a rotation axis to deflect the optical beam from the laser source. The laser source is configured to direct the optical beam such that the optical beam is incident on the deflector at a first incident angle in a first plane, wherein the first plane includes the rotation axis, wherein the first incident angle is spaced apart from the facet normal direction for the first facet. A second facet of the plurality of facets includes an optical element configured to deflect the optical beam at the first incident angle into a deflected angle.

Abstract: Systems and methods for controlling a failover response of an autonomous vehicle are provided. In one example embodiment, a method includes determining, by one or more computing devices on-board an autonomous vehicle, an operational mode of the autonomous vehicle. The autonomous vehicle is configured to operate in at least a first operational mode in which a human driver is present in the autonomous vehicle and a second operational mode in which the human driver is not present in the autonomous vehicle. The method includes detecting a triggering event associated with the autonomous vehicle. The method includes determining actions to be performed by the autonomous vehicle in response to the triggering event based on the operational mode. The method includes providing one or more control signals to one or more of the systems on-board the autonomous vehicle to perform the one or more actions in response to the triggering event.