Torc Robotics, Inc.

Yexuan Hao

William Davis

Daniel Fernández

Garrett Madsen

Ajay Tulsyan

Paul Brown

Joshua Petrin

Savio Pereira

Adam Shoemaker

John Blankenhorn

Embodiments herein include systems and methods of generating lane selection cost values to control autonomous vehicles to accommodate merging vehicles in a tapering lane (or merge lane). An autonomy system can identify a tapering lane in map data and detect a merging vehicle situated in the tapering lane using perception sensor data. The autonomy system includes a lane-selection cost function that generates lane-selection cost values for the lanes available to the automated vehicle, which the autonomy system references to determine whether to continue traveling a current lane or change lanes into an adjacent lane. The lane-selection cost function may apply a courtesy weight when detecting the merging vehicle, such that the autonomy system causes the automated vehicle to change lanes as a courtesy to the merging vehicle, but without overriding other safety-related factors of the lane-selection cost function or trajectory planning functions.

Courtesy lane selection paradigm

Systems and methods of generating lane selection cost maps to control autonomous vehicles are disclosed. An autonomous vehicle system can receive a plurality of cost values from a plurality of components of an autonomous vehicle; generate a lane selection cost map based on the plurality of cost values; determining that the autonomous vehicle should change lanes based on the lane selection cost map; and transmit a command that causes the autonomous vehicle to change lanes responsive to determining that the autonomous vehicle should change lanes.

Cost map fusion for lane selection

Growing community of inventors

Blacksburg, VA, United States of America

Yexuan Hao