US 11,703,862 B2
Online machine learning for autonomous earth moving vehicle control
Gaurav Jitendra Kikani, San Francisco, CA (US); Noah Austen Ready-Campbell, San Francisco, CA (US); Andrew Xiao Liang, San Francisco, CA (US); and Joonhyun Kim, San Francisco, CA (US)
Assigned to Built Robotics Inc., San Francisco, CA (US)
Filed by Built Robotics Inc., San Francisco, CA (US)
Filed on Dec. 22, 2021, as Appl. No. 17/558,845.
Application 17/558,845 is a continuation of application No. 17/359,425, filed on Jun. 25, 2021, granted, now 11,237,558.
Prior Publication US 2022/0413495 A1, Dec. 29, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. E01C 19/00 (2006.01); E01C 23/00 (2006.01); E01C 21/00 (2006.01); E02F 3/00 (2006.01); E02F 5/00 (2006.01); E21C 49/02 (2006.01); G05D 1/00 (2006.01); G06N 20/00 (2019.01); G05D 1/02 (2020.01)
CPC G05D 1/0088 (2013.01) [G05D 1/0212 (2013.01); G06N 20/00 (2019.01); G05D 2201/0202 (2013.01)] 21 Claims
OG exemplary drawing
 
1. A method comprising:
determining, by an earth moving vehicle (EMV), a desired state for a portion of the EMV;
determining, by the EMV, a current state of the portion of the EMV;
selecting, by the EMV, a set of control inputs for moving the portion of the EMV from the current state to the desired state using a machine learning model trained to predict control inputs for moving the portion of the EMV to the desired state based on the current state, the set of control inputs comprising a first control input for actuating a portion of the EMV from the current state and a second control input for dynamically adjusting the actuation of the portion of the EMV to achieve the desired state;
executing, by the EMV, the selected set of control inputs;
determining an updated current state of the portion of the EMV; and
updating the machine learning model based on the updated current state of the portion of the EMV.