Uatc, LLC

Aurora Operations, Inc.

Uber Technologies, Inc.

Brian C Becker

Carlos Vallespi-Gonzalez

Yang Xu

Shivam Gautam

Michael Lee Phillips

Eric Michael Perko

Narek Melik-Barkhudarov

Nemanja Djuric

Cole Christian Gulino

J Andrew Bagnell

Karthik Lakshmanan

Abhishek Sen

Abhishek Mohta

Ashton James Fagg

Nathan Nicolas Pilbrough

Arunprasad Venkatraman

James Andrew Bagnell

Gregory P Meyer

Davis Edward King

Fang-Chieh Chou

Sida Zhang

Xinyan Yan

Drew Edward Steedly

Skandavimal Shridhar

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.

Systems and methods for autonomous vehicle controls

Systems and methods are disclosed for detecting and predicting the motion of objects within the surrounding environment of a system such as an autonomous vehicle. For example, an autonomous vehicle can obtain sensor data from a plurality of sensors comprising at least two different sensor modalities (e.g., RADAR, LIDAR, camera) and fused together to create a fused sensor sample. The fused sensor sample can then be provided as input to a machine learning model (e.g., a machine learning model for object detection and/or motion prediction). The machine learning model can have been trained by independently applying sensor dropout to the at least two different sensor modalities. Outputs received from the machine learning model in response to receipt of the fused sensor samples are characterized by improved generalization performance over multiple sensor modalities, thus yielding improved performance in detecting objects and predicting their future locations, as well as improved navigation performance.

Systems and methods for sensor data processing and object detection and motion prediction for robotic platforms

An autonomous vehicle computing system can include a primary perception system configured to receive a plurality of sensor data points as input generate primary perception data representing a plurality of classifiable objects and a plurality of paths representing tracked motion of the plurality of classifiable objects. The autonomous vehicle computing system can include a secondary perception system configured to receive the plurality of sensor data points as input, cluster a subset of the plurality of sensor data points of the sensor data to generate one or more sensor data point clusters representing one or more unclassifiable objects that are not classifiable by the primary perception system, and generate secondary path data representing tracked motion of the one or more unclassifiable objects. The autonomous vehicle computing system can generate fused perception data based on the primary perception data and the one or more unclassifiable objects.

Systems and methods for detecting actors with respect to an autonomous vehicle

The present disclosure provides an example method for validating a trajectory generated by an autonomous vehicle control system (AV trajectory) in a driving scenario. The example method includes (a) obtaining the AV trajectory and a reference trajectory, wherein the reference trajectory describes a desired motion of a vehicle in the driving scenario; (b) determining a plurality of component divergence values for a plurality of divergence metrics, wherein a respective divergence value characterizes a respective difference between the AV trajectory and the reference trajectory; (c) providing the plurality of component divergence values to a machine-learned model to generate a score that indicates an aggregate divergence between the AV trajectory and the reference trajectory, wherein the machine-learned model comprises a plurality of learned parameters defining an influence of the plurality of component divergence values on the score; and (d) validating the AV trajectory based on the score.

Learned validation metric for evaluating autonomous vehicle motion planning performance

Systems, methods, tangible non-transitory computer-readable media, and devices associated with object association and tracking are provided. Input data can be obtained. The input data can be indicative of a detected object within a surrounding environment of an autonomous vehicle and an initial object classification of the detected object at an initial time interval and object tracks at time intervals preceding the initial time interval. Association data can be generated based on the input data and a machine-learned model. The association data can indicate whether the detected object is associated with at least one of the object tracks. An object classification probability distribution can be determined based on the association data. The object classification probability distribution can indicate a probability that the detected object is associated with each respective object classification. The association data and the object classification probability distribution for the detected object can be outputted.

Association and tracking for autonomous devices

Systems and methods for controlling an autonomous vehicle are provided. In one example embodiment, a computer-implemented method includes obtaining sensor data indicative of a surrounding environment of the autonomous vehicle, the surrounding environment including one or more occluded sensor zones. The method includes determining that a first occluded sensor zone of the occluded sensor zone(s) is occupied based at least in part on the sensor data. The method includes, in response to determining that the first occluded sensor zone is occupied, controlling the autonomous vehicle to travel clear of the first occluded sensor zone.

Systems and methods for controlling an autonomous vehicle with occluded sensor zones

Systems, device, and methods for trajectory association and tracking are provided. A method can include obtaining input data indicative of a respective trajectory for each of one or more first objects for a first time step and input data indicative of a respective trajectory for each of one or more second objects for a second time step subsequent to the first time step. The method can include generating, using a machine-learned model, a temporally-consistent trajectory for at least one of the one or more first objects or the one or more second objects based at least in part on the input data and determining a third predicted trajectory for the at least one of the one or more first objects or the one or more second objects for at least the second time step based at least in part on the temporally-consistent trajectory.

Object trajectory association and tracking

Systems, methods, tangible non-transitory computer-readable media, and devices for operating an autonomous vehicle are provided. For example, a vehicle computing system can receive sensor data including information based on sensor outputs associated with detection of objects in an environment by sensors of a vehicle. Inflection points can be determined based at least in part on the sensor data. The inflection points can correspond to portions of the objects that occlude detection of the environment beyond the portions of the objects. A set of polar coordinates can be determined for each of the one or more inflection points. The set of polar coordinates can include a distance from the sensors to a portion of the objects and an angle of the sensor with respect to the portion of the objects. Furthermore, sparse map data including the set of polar coordinates can be generated based on the set of polar coordinates.

Generation of polar occlusion maps for autonomous vehicles

The present disclosure provides systems and methods for tracking vehicles or other objects that are perceived by an autonomous vehicle. A vehicle filter can employ a motion model that models the location of the tracked vehicle using a vehicle bounding shape and an observation model that generates an observation bounding shape from sensor observations. A dominant vertex or side from each respective bounding shape can be identified and used to update or otherwise correct one or more predicted shape locations associated with the vehicle bounding shape based on a shape location associated with the observation bounding shape.

Systems and methods to track vehicles proximate perceived by an autonomous vehicle

Growing community of inventors

Pittsburgh, PA, United States of America

Brian C Becker