Online machine learning for calibration of autonomous earth moving vehicles

Patent metadata

Field	Value
Publication number	US-12565762-B2
Application number	US-202418787332-A
Country	US
Kind code	B2
Filing date	Jul 29, 2024
Priority date	Jun 25, 2021
Publication date	Mar 3, 2026
Grant date	Mar 3, 2026

Abstract

In some implementations, the EMV uses a calibration to inform autonomous control over the EMV. To calibrate an EMV, the system first selects a calibration action comprising a control signal for actuating a control surface of the EMV. Then, using a calibration model comprising a machine learning model trained based on one or more previous calibration actions taken by the EMV, the system predicts a response of the control surface to the control signal of the calibration action. After the EMV executes the control signal to perform the calibration action, the EMV system monitors the actual response of the control signal and uses that to update the calibration model based on a comparison between the predicted and monitored states of the control surface.

First claim

What is claimed is:

1 . A method comprising:
training, by a training system, a machine-learning model configured to predict an autonomous vehicle (“AV”) movement resulting from a movement instruction; generating a control signal for actuating a portion of the AV based on the AV movement predicted by the machine-learning model; actuating the portion of the AV to perform an actual AV movement based on the control signal; and updating, by the training system, the machine-learning model such that a difference between the actual AV movement based on the control signal and the AV movement predicted by the machine-learning model meets a threshold.

2 . The method of claim 1 , wherein the actual AV movement is measured based on a state of the portion of the AV at a time when the control signal is executed.

3 . The method of claim 1 , wherein the training system is configured to periodically compare actual AV movements to corresponding predicted AV movements.

4 . The method of claim 1 , wherein the machine-learning model is further trained based on baseline training data gathered from a set of additional AVs similar to the AV.

5 . The method of claim 1 , wherein the AV movement predicted by the machine-learning model comprises a predicted movement of a tool of the AV.

6 . The method of claim 1 , wherein updating the machine-learned model comprises:
updating, by online learning techniques, the machine-learning model based on the actual AV movement based on the control signal.

7 . The method of claim 1 , wherein the actual AV movement is compared to the predicted AV movement responsive to the AV switching between an autonomous operation mode and a manual operation mode.

8 . The method of claim 1 , wherein the actual AV movement based on the control signal is determined by measuring a set of action conditions based on collected sensor data.

9 . A non-transitory computer-readable storage medium storing executable instructions that, when executed by a processor, cause the processor to:
train, by a training system, a machine-learning model configured to predict an autonomous vehicle (“AV”) movement resulting from a movement instruction; generate a control signal for actuating a portion of the AV based on the AV movement predicted by the machine-learning model; actuate the portion of the AV to perform an actual AV movement based on the control signal; and update, by the training system, the machine-learning model such that a difference between the actual AV movement based on the control signal and the AV movement predicted by the machine-learning model meets a threshold.

10 . The non-transitory computer-readable storage medium of claim 9 , wherein the actual AV movement is measured based on a state of the portion of the AV at a time when the control signal is executed.

11 . The non-transitory computer-readable storage medium of claim 9 , wherein the training system is configured to periodically compare actual AV movements to corresponding predicted AV movements.

12 . The non-transitory computer-readable storage medium of claim 9 , wherein the machine-learned model is further trained based on baseline training data gathered from a set of additional AV similar to the AV.

13 . The non-transitory computer-readable storage medium of claim 9 , wherein the machine-learning model is further trained based on baseline training data gathered from a set of additional AVs similar to the AV.

14 . The non-transitory computer-readable storage medium of claim 9 , wherein the AV movement predicted by the machine-learning model comprises a predicted movement of a tool of the AV.

15 . The non-transitory computer-readable storage medium of claim 9 , wherein instructions for updating the machine-learned model further cause the processor to:
update, by online learning techniques, the machine-learning model based on the actual AV movement based on the control signal.

16 . The non-transitory computer-readable storage medium of claim 9 , wherein the actual AV movement is compared to the predicted AV movement responsive to the AV switching between an autonomous operation mode and a manual operation mode.

17 . The non-transitory computer-readable storage medium of claim 9 , wherein the actual AV movement based on the control signal is determined by measuring a set of action conditions based on collected sensor data.

18 . A model training system, comprising:
a hardware processor; and a non-transitory computer-readable storage medium storing executable instructions that, when executed by the hardware processor, cause the model training system to perform steps comprising:
training a machine-learning model configured to predict an autonomous vehicle (“AV”) movement resulting from a movement instruction;
generating a control signal for actuating a portion of the AV based on the AV movement predicted by the machine-learning model;
actuating the portion of the AV to perform an actual AV movement based on the control signal; and
updating, by the training system, the machine-learning model such that a difference between the actual AV movement based on the control signal and the AV movement predicted by the machine-learning model meets a threshold.

19 . The model training system of claim 18 , wherein the model training system is configured to periodically compare actual AV movements to corresponding predicted AV movements.

20 . The model training system of claim 18 , wherein instructions for updating the machine-learned model further cause the processor to:
update, by online learning techniques, the machine-learning model based on the actual AV movement based on the control signal.

Assignees

• Built Robotics Inc

Inventors

• Kikani Gaurav Jitendra
• Ready-Campbell Noah Austen
• Liang Andrew Xiao
• Kim Joonhyun

Classifications

• G05D1/81

  Handing over between on-board automatic and on-board manual control · CPC title

• G06N3/08

  Learning methods · CPC title

• E02F9/262

  with follow-up actions to control the work tool, e.g. controller · CPC title

• G05D1/0061

  for transition from automatic pilot to manual pilot and vice versa · CPC title

• G06N3/09

  Supervised learning · CPC title