Uatc, LLC

Uber Technologies, Inc.

Aurora Operations, Inc.

Chenggang Liu

David McAllister Bradley

Daoyuan Jia

Moslem Kazemi

Michael Lee Phillips

William Payne Ross

Matthew Sweeney

Thomas E Pilarski

Tianyu Gu

Eric Michael Perko

Colin Jeffrey Green

John Evan Bares

Kalin Vasilev Gochev

Samuel Philip Marden

Thomas Pilarski

Jacob Panikulam

Charles R Hogg, Iii

Utku Eren

Nitish Thatte

Andy Lee

The present disclosure is directed to generating vehicle motion corridors for use in generating autonomous vehicle paths. In particular, a computing system can access map data for a geographic area and sensor data for the geographic area around an autonomous vehicle. The computing system can identify, based on the map data and the sensor data, object data describing a position and a size of one or more objects in the geographic area of the autonomous vehicle. The computing system can access path data describing a nominal path through the geographic area. The computing system can determine a plurality of corridor segments associated with the nominal path. The computing system can generate a vehicle motion corridor by aggregating the plurality of corridor segments, wherein the vehicle motion corridor defines an area in which the autonomous vehicle can travel without colliding with the one or more objects.

Systems and methods for generating vehicle corridors to improve path planning efficiency

The present disclosure is directed to altering vehicle paths. In particular, a computing system can access map data for a geographic area. The computing system can obtain target zone data describing a target zone within the geographic area. The computing system can determine an altered nominal path to traverse the target zone. The computing system can designate a portion of the altered nominal path as a designated action region associated with the target zone. The computing system can generate a longitudinal plan for an autonomous vehicle through the geographic area based on the altered nominal path. The computing system can generate a target velocity for one or more portions of the nominal path within the designated action region. The computing system can generate a trajectory for the autonomous vehicle based on the target velocity and the altered nominal path.

Systems and methods for autonomous vehicle motion control and motion path adjustments

Systems and methods for vehicle spatial path sampling are provided. The method includes obtaining an initial travel path for an autonomous vehicle from a first location to a second location and vehicle configuration data indicative of one or more physical constraints of the autonomous vehicle. The method includes determining one or more secondary travel paths for the autonomous vehicle from the first location to the second location based on the initial travel path and the vehicle configuration data. The method includes generating a spatial envelope based on the one or more secondary travel paths that indicates a plurality of lateral offsets from the initial travel path. And, the method includes generating a plurality of trajectories for the autonomous vehicle to travel from the first location to the second location such that each of the plurality of trajectories include one or more lateral offsets identified by the spatial envelope.

Systems and methods for vehicle spatial path sampling

Systems and methods for basis path generation are provided. In particular, a computing system can obtain a target nominal path. The computing system can determine a current pose for an autonomous vehicle. The computing system can determine, based at least in part on the current pose of the autonomous vehicle and the target nominal path, a lane change region. The computing system can determine one or more merge points on the target nominal path. The computing system can, for each respective merge point in the one or more merge points, generate a candidate basis path from the current pose of the autonomous vehicle to the respective merge point. The computing system can generate a suitability classification for each candidate basis path. The computing system can select one or more candidate basis paths based on the suitability classification for each respective candidate basis path in the plurality of candidate basis paths.

Systems and methods for generating basis paths for autonomous vehicle motion control

Generally, the present disclosure is directed to systems and methods that include or otherwise leverage an iterative solver as part of optimizing a motion plan for an autonomous vehicle (AV). In particular, a scenario generator within a motion planning system can include a warm start generator configured to determine an initial trajectory that respects the dynamics of the autonomous vehicle and that closely tracks a speed profile determined by a constraint solver and one or more nominal paths determined by a route selector. A decision validator can analyze speed profiles and nominal paths to identify potential inconsistencies and validate a decision before optimization and execution. An initial trajectory can be further optimized by an iterative solver to determine an optimized trajectory for execution as a motion plan for the autonomous vehicle.

Initial trajectory generator for motion planning system of autonomous vehicles

Systems, devices, and methods for validating vehicle trajectories are provided. A vehicle controller can obtain a motion plan indicative of a trajectory including one or more state variables and one or more control variables. The vehicle controller can determine a dynamics defect value for the motion plan based at least in part on the one or more state variables, the one or more control variables, and a continuous-time dynamics function comprising a function indicative of a change in the one or more state variables and the one or more control variables over time. The vehicle controller can further determine the motion plan is dynamically consistent based at least in part on the dynamics defect value, generate one or more vehicle system control signals, and control the autonomous vehicle based at least in part on the one or more vehicle system control signals.

Vehicle trajectory dynamics validation and interpolation

The present disclosure is directed generating candidate trajectories and selecting one of them to be implemented. In particular, a computing system can obtain an initial travel path for an autonomous vehicle. The computing system can obtain sensor data describing objects within an environment of the autonomous vehicle. The computing system can generate a plurality of trajectories for the autonomous vehicle based on the sensor data and the initial travel path. The computing system can determine whether the initial travel path, an offset profile, and a velocity profile meet flatness criteria. In response to determining that the initial travel path, the offset profile, and the velocity profile meet the flatness criteria, the computing system can combine the initial travel path, the offset profile, and the velocity profile into the respective trajectory. The computing system can determine a trajectory from the plurality of trajectories.

Method for using lateral motion to optimize trajectories for autonomous vehicles

The present disclosure provides systems and methods for automatic event detection and classification for autonomous vehicles. One example method includes obtaining, by one or more computing devices, vehicle data descriptive of vehicle conditions associated with an autonomous vehicle during an autonomous driving session. The method includes extracting, by the one or more computing devices, a plurality of features from the vehicle data. The method includes determining, by the one or more computing devices using a machine-learned classifier, a classification for each of one or more candidate events based at least in part on one or more of the plurality of features that are respectively associated with the one or more candidate events. The method includes associating, by the one or more computing devices, the classification determined for each of the one or more candidate events with the vehicle data.

Machine learning for event detection and classification in autonomous vehicles

The present disclosure provides systems and methods that enable an autonomous vehicle motion planning system to learn to generate motion plans that mimic human driving behavior. In particular, the present disclosure provides a framework that enables automatic tuning of cost function gains included in one or more cost functions employed by the autonomous vehicle motion planning system.

Automatic tuning of autonomous vehicle cost functions based on human driving data

A control system of a self-driving vehicle (SDV) can dynamically determine a set of autonomous driving actions to be performed by the SDV, and generate a set of intention outputs using a light output system of the SDV based on the set of autonomous driving actions, where the set of intention outputs indicating the set of autonomous driving actions prior to the SDV executing the set of autonomous driving actions. The control system can then execute the set of autonomous driving actions using acceleration, braking, and steering systems of the SDV. While executing the set of autonomous driving actions, the control system can generate a corresponding set of reactive outputs using the light output system to indicate the set of autonomous driving actions being executed, where the corresponding set of reactive outputs replacing the set of intention outputs.

Light output system for a self-driving vehicle

An intention signaling system for an autonomous vehicle (AV) can monitor sensor information indicating a situational environment of the AV, and detect an external entity based, at least in part, on the sensor data. The intention signaling system can generate an output to signal one of an intent of the AV or an acquiescence of the AV to the external entity.

Intention signaling for an autonomous vehicle

A control system of a self-driving vehicle (SDV) can process sensor data from a sensor system of the SDV to autonomously control acceleration, steering, and braking systems of the SDV along a current route. Based on the current route, the control system can dynamically determine a set of immediate actions to be performed by the SDV. Based on the set of immediate actions, the control system can generate a set of intention outputs on a lighting strip of the SDV, the set of intention outputs indicating the set of immediate actions prior to the SDV executing the set of immediate actions.

Growing community of inventors

Pittsburgh, PA, United States of America

Chenggang Liu