Systems, devices, articles, and methods for using trained robots

Patent metadata

Field	Value
Publication number	US-11772266-B2
Application number	US-202217678847-A
Country	US
Kind code	B2
Filing date	Feb 23, 2022
Priority date	May 6, 2016
Publication date	Oct 3, 2023
Grant date	Oct 3, 2023

Abstract

Robotic systems, methods of operation of robotic systems, and storage media including processor-executable instructions are disclosed herein. The system may include a robot, at least one processor in communication with the robot, and an operator interface in communication with the robot and the at least one processor. The method may include executing a first set of autonomous robot control instructions which causes a robot to autonomously perform the at least one task in an autonomous mode, and generating a second set of autonomous robot control instructions from the first set of autonomous robot control instructions and a first set of environmental sensor data received from a senor. Execution of the second set of autonomous robot control instructions causes the robot to autonomously perform the at least one task. The method may include producing at least one signal that represents the second set of autonomous robot control instructions.

First claim

The invention claimed is:

1. A method of operation in a robotic system including a robot and at least one processor in communication with the robot, the method comprising:
receiving, by the at least one processor, sensor data for an environment associated with the robot;
receiving, by the at least one processor, a set of piloted robot control instructions, wherein the set of piloted robot control instructions, as a result of execution, causes the robot to perform at least one task;
generating, by the at least one processor, as a result of the robot performing the at least one task, a first set of autonomous robot control instructions from the set of piloted robot control instructions and the sensor data, wherein the first set of autonomous robot control instructions when executed causes the robot to autonomously perform a modified version of the at least one task;
recording on a data structure, by the at least one processor, at least one trace of information; and
generating, by the at least one processor, using the at least one trace of information, a second set of autonomous robot control instructions, wherein the second set of autonomous robot control instructions when executed causes the robot to autonomously perform a second modified version of the at least one task.

2. The method of claim 1 , wherein the sensor data for the environment comprises location information, feature proximity information, force feedback information, chemical information, temperature information, kinematic information, or orientation information.

3. The method of claim 1 , wherein the at least one trace of information comprises:
a success or failure of the at least one task,
a success or failure of the modified version of the at least one task,
the first set of autonomous robot control instructions,
the set of piloted robot control instructions, or
the sensor data.

4. The method of claim 1 , further comprising, utilizing, by the at least one processor, a machine learning system communicatively coupled to the at least one processor to generate additional sets of autonomous robot control instructions using the at least one trace of information.

5. The method of claim 1 , wherein the at least one trace of information is recorded as a Boolean value.

6. The method of claim 1 , wherein the data structure stores a unique identifier for the at least one trace of information.

7. The method of claim 6 , further comprising labelling, by the processor, the second set of autonomous robot control instructions with the unique identifier.

8. The method of claim 6 , wherein the data structure stores a task identifier associated with the second set of autonomous robot control instructions, wherein the task identifier is further associated with the unique identifier.

9. A method of operation in a robotic system including a robot and at least one processor in communication with the robot, the method comprising:
receiving, by the at least one processor, sensor data for an environment associated with the robot;
receiving, by the at least one processor, a set of piloted robot control instructions, wherein the set of piloted robot control instructions, as a result of execution, causes the robot to perform at least one task;
generating, by the at least one processor, as a result of the robot performing the at least one task, a first set of autonomous robot control instructions from the set of piloted robot control instructions and the sensor data, wherein the first set of autonomous robot control instructions when executed causes the robot to autonomously perform a modified version of the at least one task;
recording on a data structure, by the at least one processor, at least one trace of information comprising a success or failure of the at least one task, a success or failure of the modified version of the at least one task, the first set of autonomous robot control instructions, the set of piloted robot control instructions, or the sensor data; and
generating, by the at least one processor, using the at least one trace of information, a second set of autonomous robot control instructions, wherein the second set of autonomous robot control instructions when executed causes the robot to autonomously perform a second modified version of the at least one task; and
utilizing, by the processor, a machine learning system communicatively coupled to the at least one processor, to generate additional sets of autonomous robot control instructions using the at least one trace of information.

10. The method of claim 9 , wherein the sensor data for the environment comprises location information, feature proximity information, force feedback information, chemical information, temperature information, kinematic information, or orientation information.

11. The method of claim 9 , wherein the at least one trace of information is recorded as a Boolean value.

12. The method of claim 9 , wherein the data structure stores a unique identifier for the at least one trace of information.

13. The method of claim 12 , further comprising labelling, by the processor, the second set of autonomous robot control instructions with the unique identifier.

14. The method of claim 12 , wherein the data structure stores a task identifier associated with the second set of autonomous robot control instructions, wherein the task identifier is further associated with the unique identifier.

15. A system, comprising:
a robot including a motion subsystem and a manipulation subsystem;
at least one processor communicatively coupled to the motion subsystem and the manipulation subsystem;
a machine learning system communicatively coupled to the at least one processor; and
at least one non-transitory processor-readable storage device communicatively coupled to the at least one processor and which stores processor-executable instructions which, as a result of execution by the at least one processor, cause the at least one processor to:
receive sensor data for an environment associated with the robot;
receive a set of piloted robot control instructions, wherein the set of piloted robot control instructions, as a result of execution, causes the robot to perform at least one task;
generate, as a result of the robot performing the at least one task, a first set of autonomous robot control instructions from the set of piloted robot control instructions and the sensor data, wherein the first set of autonomous robot control instructions when executed causes the robot to autonomously perform a modified version of the at least one task;
record at least one trace of information on a data structure, wherein the at least one trace of information includes information associated with a success or failure of the at least one task and a success or failure of the modified version of the at least one task; and
generate, using the at least one trace of information, a second set of autonomous robot control instructions, wherein the second set of autonomous robot control instructions when executed causes the robot to autonomously perform a second modified version of the at least one task.

16. The system of claim 15 , wherein the sensor data for the environment comprises location information, feature proximity information, force feedback information, chemical information, temperature information, kinematic information, or orientation information.

17. The system of claim 15 , wherein processor utilizes the machine learning system to additional sets of autonomous robot control instructions using the at least one trace of information.

18. The system

Assignees

• Ocado Innovation Ltd

Inventors

• Ding Weiguang
• Rudy Jan Stanislaw
• Norton Olivia S
• Rose George Samuel
• Bergstra James Sterling
• Rodrigues Oswin

Classifications

• B25J9/1664 Primary

  characterised by motion, path, trajectory planning · CPC title

• B25J9/161

  Hardware, e.g. neural networks, fuzzy logic, interfaces, processor · CPC title

• B25J9/163 Primary

  learning, adaptive, model based, rule based expert control · CPC title

• B25J9/1656

  characterised by programming, planning systems for manipulators · CPC title

• B25J9/1661

  characterised by task planning, object-oriented languages · CPC title