US 12,079,004 B2
Verification of iterative closest point alignments for autonomous vehicles
Mingcheng Chen, Sunnyvale, CA (US); and Christian Lauterbach, Campbell, CA (US)
Assigned to Waymo LLC, Mountain View, CA (US)
Filed by Waymo LLC, Mountain View, CA (US)
Filed on Aug. 18, 2021, as Appl. No. 17/405,715.
Application 17/405,715 is a continuation of application No. 16/194,837, filed on Nov. 19, 2018, granted, now 11,126,197.
Prior Publication US 2022/0004197 A1, Jan. 6, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G05D 1/00 (2006.01); G01S 13/86 (2006.01); G01S 17/89 (2020.01)
CPC G05D 1/0248 (2013.01) [G01S 13/865 (2013.01); G01S 17/89 (2013.01); G05D 1/0088 (2013.01); G05D 1/0221 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for controlling a vehicle having an autonomous driving mode, the method comprising:
receiving, by one or more computing devices of the vehicle, a plurality of LIDAR sensor data frames including an object;
using, by the one or more computing devices, the plurality of LIDAR sensor data frames and an iterative closest point (ICP) algorithm to determine alignment data for the object;
determining, by the one or more computing devices, whether the alignment data for the object should be trusted using a model, the model configured to take features of the ICP algorithm as input for the determination, wherein the alignment data is trusted when a velocity determined from the alignment data is within a tolerance value of a ground truth velocity expected from the plurality of LIDAR sensor data frames; and
controlling, by the one or more computing devices, the vehicle to maneuver in the autonomous driving mode based on the determination of whether the alignment data for the object should be trusted.