US 12,361,726 B2
Systems and methods for detecting trailer angle
Yi Luo, San Diego, CA (US); Xiaoling Han, San Diego, CA (US); and Xue Mei, Ann Arbor, MI (US)
Assigned to TUSIMPLE, INC., San Diego, CA (US)
Filed by TuSimple, Inc., San Diego, CA (US)
Filed on Sep. 6, 2023, as Appl. No. 18/462,244.
Application 18/462,244 is a continuation of application No. 17/457,885, filed on Dec. 6, 2021, granted, now 11,783,598.
Application 17/457,885 is a continuation of application No. 16/181,020, filed on Nov. 5, 2018, granted, now 11,200,430, issued on Dec. 14, 2021.
Prior Publication US 2023/0410537 A1, Dec. 21, 2023
Int. Cl. G06V 20/56 (2022.01); G01S 17/42 (2006.01); G01S 17/931 (2020.01); G06T 7/73 (2017.01); G08G 1/16 (2006.01); B60R 1/00 (2022.01)
CPC G06V 20/588 (2022.01) [G01S 17/42 (2013.01); G01S 17/931 (2020.01); G06T 7/73 (2017.01); G08G 1/167 (2013.01); B60R 1/002 (2013.01); G06T 2207/30204 (2013.01); G06T 2207/30256 (2013.01)] 18 Claims
OG exemplary drawing
 
1. An in-vehicle control system for a vehicle including a tractor and trailer, comprising:
an optical sensor configured to be mounted on the tractor and generate optical data corresponding to a plurality of three-dimensional (3D) points representative of at least a portion of a surface of the trailer from a point of view of the optical sensor;
a processor; and
a computer-readable memory in communication with the processor and having stored thereon computer-executable instructions to cause the processor to:
receive the optical data corresponding to the plurality of 3D points,
obtain at least one optimal 3D plane that simulates the surface of the trailer by optimizing an objective function through a converging process based on at least a portion of the optical data corresponding to the plurality of 3D points until convergence of the objective function, and
determine an angle between the trailer and the tractor based at least in part on the at least one optimal 3D plane;
wherein the memory further has stored thereon computer-executable instructions to cause the processor to:
identify one or more 3D points each having a reflectance value lower than a threshold reflectance value from the plurality of 3D points;
group the one or more 3D points into one or more clusters based on distance between the one or more 3D points;
extract one or more shape features from the one or more clusters; and
assign a marker identifier for each of the one or more clusters based on the extracted one or more shape features.