Toyota Research Institute, Inc.

Toyota Jidosha Kabushiki Kaisha

University of California

Logan Michael Ellis

Avinash Balachandran

Huihua Zhao

Adrien David Gaidon

Sudeep Pillai

Kuan-Hui Lee

Sergey Levine

Kun-Hsin Chen

Chao Fang

Daniele Molinari

Blake Warren Wulfe

Jia-En M Pan

Constantin Franziskus Dominik Hubmann

T Wolfram Burgard

Rowan Thomas Mcallister

Jean Mercat

A method for controlling a vehicle includes controlling, at a first time period, the vehicle based on a first velocity profile constrained by an acceleration profile that includes a minimum acceleration, a maximum acceleration, and a maximum velocity. The method also includes generating an adjusted acceleration profile by adjusting one or more of the minimum acceleration, the maximum acceleration, or the maximum velocity associated with the acceleration profile based on determining an object is approaching the vehicle. The method further includes controlling, at a second time period, the vehicle based a second velocity profile constrained by the adjusted acceleration profile.

Driver-centric model predictive controller

A method of generating an output trajectory of an ego vehicle includes recording trajectory data of the ego vehicle and pedestrian agents from a scene of a training environment of the ego vehicle. The method includes identifying at least one pedestrian agent from the pedestrian agents within the scene of the training environment of the ego vehicle causing a prediction-discrepancy by the ego vehicle greater than the pedestrian agents within the scene. The method includes updating parameters of a motion prediction model of the ego vehicle based on a magnitude of the prediction-discrepancy caused by the at least one pedestrian agent on the ego vehicle to form a trained, control-aware prediction objective model. The method includes selecting a vehicle control action of the ego vehicle in response to a predicted motion from the trained, control-aware prediction objective model regarding detected pedestrian agents within a traffic environment of the ego vehicle.

Planning-aware prediction for control-aware autonomous driving modules

Described herein are systems and methods for determining if a vehicle is parked. In one example, a system includes a processor, a sensor system, and a memory. Both the sensor system and the memory are in communication with the processor. The memory includes a parking determination module having instructions that, when executed by the processor, cause the processor to determine, using a random forest model, when the vehicle is parked based on vehicle estimated features, vehicle learned features, and vehicle taillight features of the vehicle that are based on sensor data from the sensor system.

System and method for determining if a vehicle is parked

A method for controlling a vehicle based on a driver-centric model is presented. The method includes generating a trajectory for the vehicle and receiving an input from a driver. The method also includes generating a velocity profile and an acceleration profile based on a combination of the trajectory and the input. The method further includes controlling the vehicle based on the velocity profile and the acceleration profile.

Growing community of inventors

Pleasanton, CA, United States of America

Logan Michael Ellis