Gm Cruise Holdings LLC

Gm Global Technolgoy Operations, Inc.

Jeremy Allan

Daniel Chen

Lucio Otavio Marchioro Rech

Brian Donohue

Andrew Robinson

Robin Yang

Amin Ghafouri

Prasanth Palli

Kavya Sambana

Erin Antcliffe

Eric Lujan

Shiva Ghose

Peter Ming Gao

Yu-Cheng Lin

Sohrab Haghighat

Abhishek Jain

Wei Mou

Siddhartho Bhattacharya

Adrian Kit Malaran

Jonathan Uesato

There is disclosed herein examples of system and procedure for generating a model to be implemented within autonomous vehicles for identifying assertive vehicles at an intersection having stop indicators. The model can be generated via data-driven procedure where captures of the movement of vehicles through an intersection are analyzed and utilized for generating the model. The model may be provided to the autonomous vehicles and may be implemented by the autonomous vehicles for identifying assertive vehicles.

Assertive vehicle detection model generation

Approaches to managing navigation of autonomous vehicles through minor-major intersections are disclosed. A minor-major intersection is detected. Shadow tracks are generated for occlusions associated with the minor-major intersection. A maneuver evaluation is performed based on induced kinematic discomfort and post-encroachment time. Preliminary lateral and longitudinal planning is performed based on shadow tracks, induced kinematic discomfort and post-encroachment time to generate one or more proposed trajectories. Final trajectory generation is performed by refining at least one of the one or more proposed trajectories to generate the final trajectory. The autonomous vehicle performs a selected maneuver corresponding to the final trajectory within the minor-major intersection.

Navigating minor-major intersections with an autonomous vehicle

Described herein are technologies relating to controlling an autonomous vehicle based upon a computed lane boundary. The computed lane boundary defines a travel path for the autonomous vehicle when the autonomous vehicle turns across a lane of traffic at an intersection of two or more roadways. The autonomous vehicle navigates turn based upon the computed lane boundary, which allows the autonomous vehicle to enter the intersection without crossing into a lane of oncoming traffic.

Controlling an autonomous vehicle based upon computed lane boundaries

The subject disclosure relates to techniques for real-time lane validation. A process of the disclosed technologies can include steps for receiving a route from a remote computing system, the route indicating lanes on the route that an autonomous vehicle must traverse, traversing at least one lane of the lanes on the route, and sending sensor data to the remote computing system after traversing the at least one lane, the sensor data indicating whether the at least one lane is in accordance with a virtual lane of a virtual map, the virtual lane corresponding to the at least one lane.

System and method for real-time lane validation

Systems and method are provided for controlling a vehicle. In one embodiment, a method includes: receiving, by a processor, a lane plan; determining, by a processor, from the lane plan an upcoming turn; determining, by a processor, if the upcoming turn is at least one of an unprotected left turn, an inside right turn, and an inside left turn; when at least one of an unprotected left turn, an inside right turn, and an inside left turn is determined, modifying, by a processor, a lane boundary; and controlling the vehicle based on the modified lane boundary.

Relaxable turn boundaries for autonomous vehicles

Systems and method are provided for controlling a vehicle. In one embodiment, an obstacle management method includes receiving, via one or more sensing devices, sensor data relating to an environment associated with a vehicle, wherein the vehicle is substantially stationary and has an intended path corresponding to entering a traffic flow of a first lane. The method includes determining the presence of an obstacle that at least partially occludes a view of the first lane by a first sensing device of the one or more sensing devices, and positioning, with a processor, the vehicle with respect to the obstacle to improve the view of the first lane by the first sensing device without significantly obstructing the first lane. The first lane is then monitored via the first sensing device to determine when the intended path clear.

Systems and methods for entering traffic flow in autonomous vehicles

Systems and method are provided for controlling a vehicle. The systems and methods calculate lane plan data including a set of lane plans defining a route from a start location to a destination location, solve a motion planning algorithm to produce solved lane plan data defining a solved lane plan and a trajectory therefor, receive forthcoming distance data representing a forthcoming distance, determine a feasible lane based on the solved lane plan data within the forthcoming distance, remove a lane plan from the lane plan data to produce feasible lane plan data including a feasible lane plan defining a route from the start location to the destination location, and control motion of the vehicle based on the feasible lane plan data.

Feasible lane routing

Growing community of inventors

San Francisco, CA, United States of America

Jeremy Allan