Reliable real-time deployment of robot safety updates

Patent metadata

Field	Value
Publication number	US-12515320-B2
Application number	US-202117556788-A
Country	US
Kind code	B2
Filing date	Dec 20, 2021
Priority date	Dec 20, 2021
Publication date	Jan 6, 2026
Grant date	Jan 6, 2026

Abstract

Systems and techniques for reliable real-time deployment of robot safety updates are described herein. Condition data may be collected for an environment in which a robot is operating. The robot may be classified with a condition type. Condition type data selected from the condition data may be analyzed based on the condition type to calculate a safety risk level for the robot. A microservice may be identified to provide a robot safety rule for the robot based on the safety risk level. The microservice may be identified using a safety prediction model generated from the condition type data.

First claim

What is claimed is:

1. An apparatus for reliable real-time deployment of robot safety updates, comprising:
at least one processor; and
memory including instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to:
collect condition data for an environment in which a robot is operating;
classify the robot with a condition type;
analyze condition type data selected from the condition data based on the condition type to calculate a safety risk level for the robot;
identify a microservice to provide a robot safety rule for the robot based on the safety risk level, wherein the microservice is identified using a safety prediction model generated from the condition type data;
establish a relationship between an on premise edge compute node and the robot, wherein the robot safety rule is encapsulated for execution by the on premise edge compute node;
generate a microservice repository for the robot based on the relationship; and
add the microservice to the microservice repository for deployment to the robot using the microservice repository.

2. The apparatus of claim 1 , the memory further comprising instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to:
validate the robot safety rule based on a comparison between outputs of the robot safety rule and expected outputs; and
upon validation of the robot safety rule, deploy the identified microservice to the robot.

3. The apparatus of claim 1 , wherein the instructions to calculate the safety risk level further comprises instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to:
identify a current robot safety rule for the robot;
determine risk factors for the current robot safety rule using the condition type data;
apply weights to the risk factors to generate weighted risk factor values; and
sum the weighted risk factor values to create a risk factor sum, wherein the safety risk level is calculated by determining placement of the risk factor sum in a set of safety risk level thresholds.

4. The apparatus of claim 1 , the memory further comprising instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to:
determine that a current microservice is unable to reduce the safety risk level; and
remove the current microservice from the microservice repository.

5. The apparatus of claim 1 , the memory further comprising instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to:
access a cloud repository of safety services;
identify a safety service from the cloud repository that will reduce the safety risk level; and
generate the microservice for the identified safety service.

6. The apparatus of claim 1 , the memory further comprising instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to:
obtain a test case description for validation of the robot safety rule;
transmit instructions to a robot fleet control to initiate control of the robot according to the test case description; and
determine expected outputs of the robot safety rule based on the test case description.

7. The apparatus of claim 1 , wherein the instructions to encapsulate the robot safety rule further comprises instructions to generate an encapsulation container for the robot safety rule.

8. The apparatus of claim 7 , the memory further comprising instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to:
identify a robot type for the robot; and
generate the encapsulation container using hardware virtualization or operating system virtualization based on the robot type.

9. The apparatus of claim 2 , the memory further comprising instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to obtain validation inputs from other robots, wherein the instructions to validate the robot safety rule includes instructions to evaluate the validation inputs to determine that the robot is operating correctly using the robot safety rule.

10. The apparatus of claim 2 , the memory further comprising instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to:
transmit a message to a human operator to request an environmental change to facilitate a testing scenario;
upon receipt of a response to the message indicating that the environmental change has been made, transmit control instructions to the robot to complete the testing scenario; and
receive output from sensors of the robot, wherein the instructions to validate the robot safety rule includes instructions to evaluate the received output to determine if the received output is within a range of values of the expected outputs.

11. The apparatus of claim 2 , the memory further comprising instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to:
calculate a testing variation time value based on a current workload of the robot;
determine that completion time for a test scenario is lower than the testing time variation value;
transmit a robot control message to the robot to use robot safety rule to execute the test scenario; and
receive output from the robot upon completion of the test scenario, wherein the instructions to validate the robot safety rule includes instruction to evaluate the received output to determine if the received output is within a range of values of the expected outputs.

12. The apparatus of claim 1 , wherein the condition data is collected from a public condition data source that includes outdoor environmental conditions, wherein the outdoor environmental conditions include a weather condition or a road condition.

13. The apparatus of claim 1 , wherein the condition data is collected from a public condition data source that includes indoor environmental conditions, wherein the indoor environmental conditions include building configuration data or building operating conditions.

14. The apparatus of claim 1 , wherein the condition data is collected from a private condition data source that includes profile data for at least one human-robot interaction.

15. The apparatus of claim 1 , wherein the condition data is collected from a sensor of the robot that includes robot environmental conditions, wherein the robot environmental conditions include camera data or light detection and ranging data.

16. At least one non-transitory machine-readable medium including instructions for reliable real-time deployment of robot safety updates that, when executed by at least one processor, cause the at least one processor to perform operations to:
collect condition data for an environment in which a robot is operating;
classify the robot with a condition type;
analyze condition type data selected from the condition data based on the condition type to calculate a safety risk level for the robot;
identify a microservice to provide a robot safety rule for the robot based on the safety risk level, wherein the microservice is identified using a safety prediction model generated from the condition type data;
establish a relationship between an on premise edge compute node and the robot, wherein the robot safety rule is encapsulated for execution by the on premise edge compute node;
generate

Assignees

• Intel Corp

Inventors

• Yeap Wei Seng
• Yew Chien Chern
• Liew Ying Wei
• Tan Say Chuan
• Hau Tze Ming
• Pasch Frederik
• Oboril Fabian
• Scholl Kay-Ulrich
• Buerkle Cornelius

Classifications

• G05D1/617

  Safety or protection, e.g. defining protection zones around obstacles or avoiding hazards (arrangements for controlling the position or course of two or more vehicles for avoiding collisions therebetween G05D1/693; arrangements for reacting to or preventing system or operator failure G05D1/80) · CPC title

• B25J9/1674

  characterised by safety, monitoring, diagnostic · CPC title

• G06F8/65

  Updates (security arrangements therefor G06F21/57) · CPC title

• G05D1/0291

  Fleet control (monitoring fleets in traffic control systems for road vehicles G08G1/127, G08G1/127) · CPC title

• B25J9/163 Primary

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