Situation-aware safety assessment of robot-human activities

Patent metadata

Field	Value
Publication number	US-12420422-B2
Application number	US-202117553854-A
Country	US
Kind code	B2
Filing date	Dec 17, 2021
Priority date	Dec 17, 2021
Publication date	Sep 23, 2025
Grant date	Sep 23, 2025

Abstract

Disclosed herein are systems, devices, and methods of a safety system for analyzing and improving the safety of collaborative environments in which a robot may interact a human. The safety system may determine a monitored attribute of a person within an operating environment of a robot, where the monitored attribute may be based on received sensor information about the person in the operating environment. In addition, the safety system may determine a risk score for the person based on the monitored attribute. The risk score may be defined by (1) a collision probability that the person will cause an interference during a planned operation of the robot and (2) a severity level associated with the interference. The safety system may also generate a mitigating instruction for the robot if the risk score exceeds a threshold level.

First claim

The invention claimed is:

1. A device comprising:
a processor configured to:
determine a monitored attribute of a person within an operating environment of a robot, wherein the monitored attribute is based on received sensor information about the person in the operating environment;
determine a risk score for the person based on the monitored attribute, wherein the risk score is defined by
a collision probability that the person will cause an interference during a planned operation of the robot;
a severity level associated with the interference; and
control, based on whether the risk score exceeds a threshold level, the robot to stop operating or to operate according to a modified instruction, wherein the modified instruction comprises a change to the planned operation of the robot and is associated with a modified instruction risk level that is lower than the risk score;
select the modified instruction from among a plurality of possible modified instructions, wherein each possible modified instruction of the plurality of possible modified instructions is associated with a corresponding risk level of the each possible modified instruction, wherein the modified instruction is selected based on the corresponding risk level; and
determine, for each possible modified instruction of the plurality of possible modified instructions, the corresponding risk level based on a corresponding collision probability and a corresponding severity level of the possible modified instruction.

2. The device of claim 1 , wherein the processor configured to determine the monitored attribute comprises the processor configured to determine at least one of the following based on the received sensor information: equipment information about safety equipment worn by the person; an identification profile for the person; training information about a training level of the person with respect to the planned operation; a sound within the operating environment; a distraction level of the person; a response time of the person; and a monitored behavior of the person.

3. The device of claim 1 , wherein the processor is configured to determine the risk score based on a behavior-matching score indicative of a difference between an expected behavior of the person and the monitored attribute.

4. The device of claim 3 , wherein the processor is configured to determine the expected behavior based on an estimated trajectory of the person and an associated confidence level of the estimated trajectory.

5. The device of claim 1 , wherein the processor is configured to determine the collision probability based on at least one of a robot trajectory of the robot associated with the planned operation or an expected behavior of the person during the planned operation.

6. The device of claim 1 , further comprising a memory configured to store at least one of the monitored attribute, received sensor information, the risk score, the collision probability, the severity level, or the modified instruction.

7. The device of claim 1 , wherein the processor is configured to determine the severity level based on at least one of the following: equipment information about safety equipment worn by the person; training information about a training level of the person with respect to the planned operation; and robot movements of the robot associated with the planned operation of the robot.

8. The device of claim 7 , wherein the processor is configured to determine the severity level from a severity lookup table that associates severity levels with at least one of the following: the equipment information; the training information; and the robot movements.

9. The device of claim 1 , wherein the processor is further configured to select the possible-modified instruction based on a progress level associated with the each possible modified instruction, wherein the progress level is defined by progress toward completing the planned operation provided from the each possible modified instruction.

10. The device of claim 1 , the device further comprising a receiver configured to receive the received sensor information from a sensor, wherein the sensor comprises a depth sensor, a camera, a radar, a light ranging and detection sensor, a microphone, a health-monitoring sensor, a heart-rate monitor, a motion sensor, a gyroscopic sensor, an accelerometer, and/or an ultrasonic sensor.

11. The device of claim 1 , wherein the risk score comprises a plurality of risk scores, wherein the operating environment is subdivided into a plurality of subregions, wherein each risk score of the plurality of risk scores comprises a regional risk score for a corresponding subregion of the plurality of subregions, wherein the processor is configured to determine the regional risk score based on a corresponding collision probability for the corresponding subregion and a corresponding severity level for the corresponding subregion.

12. The device of claim 11 , wherein the threshold level comprises a plurality of subregion threshold levels, wherein each corresponding subregion of the plurality of subregions has an associated subregion threshold level from the plurality of subregion threshold levels, wherein the modified instruction is configured to avoid corresponding subregions where the regional risk score for the each corresponding region exceeds the subregion threshold level for the corresponding region.

13. A non-transitory computer readable medium, including instructions which, if executed, cause a processor to:
determine a monitored attribute of a person within an operating environment of a robot, wherein the monitored attribute is based on received sensor information about the person in the operating environment;
determine a risk score for the person based on the monitored attribute, wherein the risk score is defined by a collision probability that the person will cause an interference during a planned operation of the robot; and
a severity level associated with the interference; and
control, based on whether the risk score exceeds a threshold level, the robot to stop operating or to operate according to a modified instruction, wherein the modified instruction comprises a change to the planned operation of the robot and is associated with a modified instruction risk level that is lower than the risk score;
select the modified instruction from among a plurality of possible modified instructions, wherein each possible modified instruction of the plurality of possible modified instructions is associated with a corresponding risk level of the each possible modified instruction, wherein the modified instruction is selected based on the corresponding risk level; and
determine, for each possible modified instruction of the plurality of possible modified instructions, the corresponding risk level based on a corresponding collision probability and a corresponding severity level of the possible modified instruction.

14. The non-transitory computer readable medium of claim 13 , wherein the monitored attribute of the person comprises at least one of the following: a facial expression of the person; an emotional reaction of the person; a spoken word from the person; a movement of the person; a posture of the person; equipment information about safety equipment worn by the person; an identification profile for the person; training information about a training level of the person with respect to the planned operation; a sound within the operating environment; a distraction level of the person; a response time of the person; a monitored behavior of the person; and a heart rate of the person.

15. The non-transitory computer reada

Assignees

• Intel Corp

Inventors

• Oboril Fabian
• Buerkle Cornelius
• Pasch Frederik
• Gassmann Bernd
• Yew Chien Chern
• Hau Tze Ming
• Liew Ying Wei
• Tan Say Chuan
• Yeap Wei Seng

Classifications

• B25J9/1666

  Avoiding collision or forbidden zones · CPC title

• B25J9/163

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

• G09B19/16

  Control of vehicles or other craft (simulators G09B9/02) · CPC title

• G09B19/24

  Use of tools · CPC title

• G05B2219/40202

  Human robot coexistence · CPC title