US 12,122,419 B2
Two-level path planning for autonomous vehicles
Junbo Jing, San Diego, CA (US); Arda Kurt, San Diego, CA (US); Yujia Wu, San Diego, CA (US); Tianqu Shao, San Diego, CA (US); Xing Sun, San Diego, CA (US); Zijie Xuan, San Diego, CA (US); Haoming Sun, San Diego, CA (US); and Chasen Sherman, San Diego, CA (US)
Assigned to TUSIMPLE, INC., San Diego, CA (US)
Filed by TUSIMPLE, INC., San Diego, CA (US)
Filed on Jun. 25, 2020, as Appl. No. 16/912,444.
Prior Publication US 2021/0403032 A1, Dec. 30, 2021
Int. Cl. B60W 60/00 (2020.01); G05D 1/00 (2024.01); H04W 4/40 (2018.01)
CPC B60W 60/0011 (2020.02) [G05D 1/0022 (2013.01); G05D 1/0274 (2013.01); H04W 4/40 (2018.02)] 17 Claims
OG exemplary drawing
 
1. A method of navigating an autonomous vehicle, comprising:
determining, by an online server, a current location and a current heading angle of the autonomous vehicle in a mapped driving area;
receiving, by the online server from an offline path library, a path for the autonomous vehicle through the mapped driving area from the current location and the current heading angle to a destination vehicle state, wherein the mapped driving area comprises a road topology;
receiving fixed and moving obstacle information from one or more sensors on the autonomous vehicle;
adjusting the path to generate an optimized path wherein the optimized path avoids fixed and moving obstacles according to the fixed and moving obstacle information and ends at a final vehicle state, wherein the optimized path is generated by separately solving the fixed obstacles in a spatial domain using a fixed distance step size and solving the moving obstacles with respect to vehicle speed in a time domain using a fixed time step size; and
navigating the autonomous vehicle based on the optimized path.