System and method for autonomous work machine exception handling

Patent metadata

Field	Value
Publication number	US-12140964-B2
Application number	US-202117179893-A
Country	US
Kind code	B2
Filing date	Feb 19, 2021
Priority date	Feb 19, 2021
Publication date	Nov 12, 2024
Grant date	Nov 12, 2024

Abstract

A control system for an autonomous work machine includes a robotic controller, a position detection system coupled to the robotic controller, and a sensor coupled to the robotic controller and configured to provide a sensor signal. A controlled system is coupled to the robotic controller to receive control signals from the robotic controller. The robotic controller is configured to generate an event relative to an object in an environment around the autonomous work machine or a machine health/job quality issue, document the event, and store the documented event. The robotic controller is further configured to selectively generate a communication containing at least some information relative to the documented event to a supervisor and to receive user input from the supervisor and take responsive action based on the user input.

First claim

What is claimed is:

1. A computer-implemented method of handling object detection in an autonomous work machine, the method comprising:
detecting an object while performing an agricultural mission with the autonomous work machine, the autonomous work machine including a tractor and a towed implement, the towed implement having a width greater than a width of the tractor;
determining, with a robotic controller of the autonomous work machine, whether the object requires the work machine to take action to avoid the object based on a detected position of the object, a current path of the work machine, and a width of the towed implement;
selectively obtaining information relative to object detection and storing the information, based on the determination of whether the object requires the autonomous work machine to take action to avoid the object;
determining, with the robotic controller of the autonomous work machine, whether the obstacle is in a category and in a location that requires the autonomous work machine to stop;
based the determination of whether the work machine is required to stop, selectively halting motion of the work machine;
generating a communication to a supervisor indicating that motion has been halted and requesting user input; and
based on the user input selectively continuing the mission or shutting down the autonomous work machine.

2. The computer-implemented method of claim 1 , wherein obtaining information relative to object detection include obtaining, from a camera mounted to the autonomous work machine, an image of the object.

3. The computer-implemented method of claim 1 , wherein obtaining information relative to object detection include obtaining position information relative to the object.

4. The computer-implemented method of claim 1 , wherein obtaining information relative to object detection include obtaining time information regarding when the object was detected.

5. The computer-implemented method of claim 1 , wherein obtaining information relative to object detection include a categorization of the object generated by the robotic controller.

6. The computer-implemented method of claim 1 , wherein the communication to the supervisor includes an image of the object.

7. The computer-implemented method of claim 1 , and further comprising storing the information relative to object detection.

8. The computer-implemented method of claim 1 , wherein determining with the robotic controller of the autonomous work machine, whether the obstacle is in a category and in a location that requires the autonomous work machine to stop generates a confidence metric and wherein halting motion of the work machine is performed when the robotic controller has determined that the work machine must stop and the confidence metric for such decision is above a selected threshold.

9. The computer-implemented method of claim 1 , wherein determining with the robotic controller of the autonomous work machine, whether the obstacle is in a category and in a location that requires the autonomous work machine to stop generates a confidence metric and wherein halting motion of the work machine is not performed when the robotic controller has determined that the work machine must stop and the confidence metric for such decision is below a selected threshold.

10. The computer-implemented method of claim 9 , wherein the robotic controller is configured to adjust at least one machine parameter for proceeding while the confidence metric is below the selected threshold.

11. The computer-implemented method of claim 1 , wherein generating the communication to the supervisor includes selecting, with the robotic controller, a supervisor among a plurality of supervisors based on a categorization of the object by the robotic controller.

12. The computer-implemented method of claim 1 , and further comprising monitoring a perimeter of the autonomous work machine while motion is halted.

13. The computer-implemented method of claim 1 , wherein the agricultural mission is an agricultural mission relative to a crop.

14. The computer-implemented method of claim 13 , wherein the agricultural mission includes applying nutrients to the crop.

15. The computer-implemented method of claim 13 , wherein the agricultural mission includes harvesting the crop.

16. The computer-implemented method of claim 13 , wherein the agricultural mission includes transporting logs.

Assignees

• Deere & Co

Inventors

• Ascherl Margaux M
• Runde Jeffrey E
• Maeder Curtis A
• Johnson David A

Classifications

• B60W60/0015

  specially adapted for safety · CPC title

• B60W50/14 Primary

  Means for informing the driver, warning the driver or prompting a driver intervention · CPC title

• G05D1/222

  operated by humans · CPC title

• G05D1/2437

  Extracting relative motion information · CPC title

• G05D1/247

  using signals provided by artificial sources external to the vehicle, e.g. navigation beacons · CPC title