Repetitive task and contextual risk analytics for human-robot collaboration

Patent metadata

Field	Value
Publication number	US-12479101-B2
Application number	US-202117553860-A
Country	US
Kind code	B2
Filing date	Dec 17, 2021
Priority date	Dec 17, 2021
Publication date	Nov 25, 2025
Grant date	Nov 25, 2025

Abstract

Disclosed herein are systems, devices, and methods of a robot safety system for improving the safety of human-robot collaborations. The robot safety system may include a processor that receives a collaboration policy for task collaboration between a robot and a collaborator. The task collaboration may include a movement plan of the robot to move a manipulator to a collaboration position. The robot safety system may also determine a new collaboration position based on the collaboration policy. The robot safety system may also update the collaboration position of the movement plan to the new collaboration position.

First claim

The invention claimed is:

1 . A device comprising:
a processor configured to:
receive a collaboration policy for task collaboration between a robot and a collaborator, wherein the task collaboration comprises a movement plan of the robot to move a manipulator to a collaboration position;
determine a new collaboration position based on the collaboration policy, wherein the collaboration policy comprises a randomization policy, wherein the processor is configured to select the new collaboration position from predetermined collaboration positions within a collaboration region defined by a spatial dimension corresponding to a degree of freedom of the manipulator, wherein the processor is configured to select the new collaboration position based on a random distribution of the predetermined collaboration positions within the collaboration region;
update the collaboration position of the movement plan to the new collaboration position; and
control movements of the manipulator to the new collaboration position based on the movement plan.

2 . The device of claim 1 , wherein the random distribution comprises at least one of:
an equal distribution of the predetermined collaboration positions along the spatial dimension from a maximum value of the spatial dimension to a minimum value of the spatial dimension; a gaussian distribution of the predetermined collaboration positions along the spatial dimension from the maximum value to the minimum value; or a multimodal distribution of the predetermined collaboration positions along the spatial dimension, centered at two different center positions along the spatial dimension.

3 . The device of claim 1 , wherein the collaboration policy comprises a monitoring policy, wherein the processor is configured to determine the new collaboration position based on a received observation of the collaborator during task collaboration.

4 . The device of claim 3 , wherein the processor configured to determine the new collaboration position based on the received observation of the collaborator comprises the processor further configured to determine a risk score based on the received observation, wherein the risk score is indicative of an occupational safety of the collaborator with respect to the task collaboration, wherein the processor is configured to select the new collaboration position based on the risk score.

5 . The device of claim 3 , wherein the received observation comprises at least one of an identity of the collaborator, a movement of the collaborator, a posture of the collaborator, or a determined level of attention of the collaborator to the task collaboration.

6 . The device of claim 5 , wherein the processor is configured to determine the determined level of attention based on at least one of an eye movement of the collaborator, a facial expression of the collaborator, a hand position of the collaborator, a head position of the collaborator, the movement of the collaborator, the posture of the collaborator, or a gaze direction of the collaborator.

7 . The device of claim 3 , wherein the received observation comprises sensor data indicative of the received observation, wherein the processor is configured to receive the sensor data from a sensor comprising at least one of a camera, a depth sensor, a light detection and ranging sensor, an infrared sensor, or an ultrasonic sensor.

8 . The device of claim 1 , wherein the movement plan further comprises a speed for the robot to move the manipulator to the collaboration position, wherein the processor is configured to determine the speed based on a received observation of the collaborator.

9 . The device of claim 1 , wherein the movement plan further comprises a trajectory for the robot to move the manipulator to the collaboration position, wherein the processor is configured to determine the trajectory based on a received observation of the collaborator.

10 . The device of claim 1 , wherein the collaboration policy comprises a heuristic policy, wherein the processor is configured to select the new collaboration position based on a predefined sequence of predetermined collaboration positions.

11 . The device of claim 10 , wherein the processor is configured to select the predefined sequence of predetermined collaboration positions based on a received observation of the collaborator.

12 . The device of claim 11 , wherein the received observation is indicative of at least one of a height of the collaborator or an arm length of the collaborator.

13 . The device of claim 1 , wherein the processor is further configured to determine a set of exercise instructions for the collaborator, wherein the processor is configured to suspend the movement plan until the collaborator has completed the exercise instructions.

14 . A non-transitory computer readable medium, comprising instructions which, if executed, cause a processor to:
receive a collaboration policy for task collaboration between a robot and a collaborator, wherein the task collaboration comprises a movement plan of the robot to move a manipulator to a collaboration position, wherein the task collaboration further comprises a plurality of work tasks to be distributed between the robot and the collaborator; determine a new collaboration position based on the collaboration policy, wherein the collaboration policy comprises a randomization policy, wherein the processor is configured to select the new collaboration position from predetermined collaboration positions within a collaboration region defined by a spatial dimension corresponding to a degree of freedom of the manipulator, wherein the processor is configured to select the new collaboration position based on a random distribution of the predetermined collaboration positions within the collaboration region; update the collaboration position of the movement plan to the new collaboration position; and assign each work task of the plurality of work tasks to either the robot or the collaborator based on a confidence score of completing a work goal associated with the plurality of work tasks; and control movements of the manipulator to the new collaboration position based on the movement plan.

15 . The non-transitory computer readable medium of claim 14 , wherein the processor is configured to determine the confidence score based on sensor data indicative of at least one of visual images of a work area of the task collaboration, an environmental status of the work area, a collaborator activity status of the collaborator during the task collaboration, or a robot activity status of the robot during the task collaboration.

16 . The non-transitory computer readable medium of claim 14 , wherein the processor is configured to determine the confidence score based on a performance rating of the collaborator with respect to each work task and a performance rating of the robot with respect to each work task.

17 . The non-transitory computer readable medium of claim 14 , wherein the processor is configured to determine the confidence score based on an expected time to complete the work goal compared to an actual time to complete the work goal.

18 . The non-transitory computer readable medium of claim 14 , wherein the processor is configured to determine the confidence score based on a learning model of attributes of at least one of the robot, the collaborator, the work task, or the work goal.

19 . An apparatus comprising:
a means for receiving a collaboration policy for task collaboration between a robot and a collaborator, wherein the

Assignees

• Intel Corp

Inventors

• Chin Siew Wen
• Graefe Ralf
• Kose Cihangir Neslihan
• Manepalli Sangeeta
• Moustafa Hassnaa
• Peng Yang
• Rosales Rafael
• Wouhaybi Rita H

Classifications

• B25J9/1651

  acceleration, rate control · CPC title

• G06Q10/06398 Primary

  Performance of employee with respect to a job function · CPC title

• G06Q10/06316

  Sequencing of tasks or work · CPC title

• G06Q10/063114

  Status monitoring or status determination for a person or group · CPC title

• B25J9/163

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