US 12,228,472 B2
Perception simulation for improved autonomous vehicle control
Xing Sun, San Diego, CA (US); Wutu Lin, San Diego, CA (US); Yufei Zhao, San Diego, CA (US); and Liu Liu, San Diego, CA (US)
Assigned to TUSIMPLE, INC., San Diego, CA (US)
Filed by TuSimple, Inc., San Diego, CA (US)
Filed on Jan. 26, 2024, as Appl. No. 18/424,318.
Application 16/660,244 is a division of application No. 15/598,693, filed on May 18, 2017, granted, now 10,481,044, issued on Nov. 19, 2019.
Application 18/424,318 is a continuation of application No. 17/093,172, filed on Nov. 9, 2020, granted, now 11,885,712.
Application 17/093,172 is a continuation of application No. 16/660,244, filed on Oct. 22, 2019, granted, now 10,830,669, issued on Nov. 10, 2020.
Prior Publication US 2024/0192089 A1, Jun. 13, 2024
Int. Cl. B60W 50/02 (2012.01); B60W 30/00 (2006.01); G01M 17/00 (2006.01)
CPC G01M 17/00 (2013.01) [B60W 30/00 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
a data processor; and
a perception simulation module, executable by the data processor, the perception simulation module being configured to:
configure a sensor noise modeling module to produce simulated sensor errors or noise data by comparing calibrated sensor data from one or more of a plurality of sensors with ground truth data;
use the simulated sensor errors or noise data to generate simulated perception data by simulating errors related to constraints of one or more of the plurality of sensors; and
provide the simulated perception data to a motion planning system for an autonomous vehicle.