ANTICIPATORY ROBOT NAVIGATION

• US 20160075026A1
• Filed: 09/12/2014
• Published: 03/17/2016
• Est. Priority Date: 09/12/2014
• Status: Active Grant

• Current Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Original Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Inventors: Sisbot, Emrah Akin, Cosgun, Akansel
• Granted Patent: US 9,475,195 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: B25J 9/1676 Avoiding collision or forbidden zones
• CPC Class Codes: G05B 2219/39082 Collision, real time collision avoidance
• CPC Class Codes: G05B 2219/40202 Human robot coexistence
• CPC Class Codes: G05D 1/0217 in accordance with energy consumption, time reduction or distance reduction criteria
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G05D 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30

Abstract

The disclosure includes a system and method for using a robot to simulate user motions by detecting a user, estimating a first position and orientation of the user, determining a current position of the robot, generating an initial path from the current position of the robot to a goal position based on whether the robot affects the user while travelling on the initial path, determining whether the user will traverse in response to the robot when the robot travels on the initial path, responsive to the user traversing in response to the robot, estimating a second position where the user will move when the robot is near, and generating a new path from the current position of the robot to the goal position.

Claims

1. A method comprising:

detecting a user with a processor-based computing device programmed to perform the detecting;

estimating a first position and orientation of the user;

determining a current position of a robot;

generating an initial path from the current position of the robot to a goal position based on whether the robot affects the user while travelling on the initial path;

determining whether the user will traverse in response to the robot when the robot travels on the initial path;

responsive to the user traversing in response to the robot, estimating a second position where the user will move when the robot is near; and

generating a new path from the current position of the robot to the goal position.

2. The method of claim 1, further comprising:

generating velocity constraints for the robot to follow the new path; and

instructing the robot to move to the goal position based on the new path and the velocity constraints.

3. The method of claim 1, wherein responsive to determining that the user will not traverse, instructing the robot to move based on the initial path.

4. The method of claim 1, wherein generating the initial path further comprises:

assigning a Gaussian cost to the user with a maximum range;

receiving the goal position, an environment map, and the current position for the robot;

generating a two-dimensional grid with the first position of the user, the current position of the robot, and the goal position;

generating the initial path;

determining whether the initial path will disturb the user; and

responsive to the initial path failing to disturb the user, outputting the initial path.

5. The method of claim 1, wherein generating the initial path further comprises:

assigning a Gaussian cost to the user with a maximum range;

receiving the goal position, an environment map, and the current position for the robot;

generating a two-dimensional grid with the first position of the user, the current position of the robot, and the goal position;

generating the initial path;

determining whether the initial path will disturb the user;

responsive to the initial path disturbing the user, revising the initial path to include a longer route that avoids disturbing the user; and

outputting the initial path.

6. The method of claim 5, wherein the Gaussian cost is increased as a number of users increases.

7. The method of claim 6, wherein the Gaussian cost is increased when at least two of the users are facing each other.

8. The method of claim 1, wherein the initial path includes users and wherein generating the new path from the current position of the robot to the goal position further comprises:

detecting the users in the environment;

clustering the users into user groups;

computing a portion of the initial path that intersects with the user groups; and

applying a social forces model to the robot and the user groups.

9. The method of claim 8, wherein the social forces model includes a goal force, a social force, an obstacle force, and a group force.

10. The method of claim 1, wherein generating the initial path is also based on avoiding obstacles.

11. A computer program product comprising a tangible, non-transitory computer-usable medium including a computer-readable program, wherein the computer-readable program when executed on a computer causes the computer to:

detect a user;

estimate a first position and orientation of the user;

determine a current position of a robot;

generate an initial path from the current position of the robot to a goal position based on whether the robot affects the user while travelling on the initial path;

determine whether the user will traverse in response to the robot when the robot travels on the initial path;

responsive to the user traversing in response to the robot, estimate a second position where the user will move when the robot is near; and

generate a new path from the current position of the robot to the goal position.

12. The computer program product of claim 11, wherein the computer-readable program is further configured to:

generate velocity constraints for the robot to follow the new path; and

instruct the robot to move to the goal position based on the new path and the velocity constraints.

13. The computer program product of claim 11, wherein responsive to determining that the user will not traverse, instructing the robot to move based on the initial path.

14. The computer program product of claim 11, wherein generating the initial path further comprises:

assigning a Gaussian cost to the user with a maximum range;

receiving the goal position, an environment map, and the current position for the robot;

generating a two-dimensional grid with the first position of the user, the current position of the robot, and the goal position;

generating the initial path;

determining whether the initial path will disturb the user; and

responsive to the initial path failing to disturb the user, outputting the initial path.

15. The computer program product of claim 11, wherein generating the initial path further comprises:

assigning a Gaussian cost to the user with a maximum range;

receiving the goal position, an environment map, and the current position for the robot;

generating a two-dimensional grid with the first position of the user, the current position of the robot, and the goal position;

generating the initial path;

determining whether the initial path will disturb the user;

responsive to the initial path disturbing the user, revising the initial path to include a longer route that avoids disturbing the user; and

outputting the initial path.

16. A system comprising:

a processor; and

a tangible, non-transitory memory storing instructions that, when executed, cause the system to;

detect a user;

estimate a first position and orientation of the user;

determine a current position of a robot;

generate an initial path from the current position of the robot to a goal position based on whether the robot affects the user while travelling on the initial path;

determine whether the user will traverse in response to the robot when the robot travels on the initial path;

responsive to the user traversing in response to the robot, estimate a second position where the user will move when the robot is near; and

generate a new path from the current position of the robot to the goal position.

17. The system of claim 16, wherein the memory is further configured to:

generate velocity constraints for the robot to follow the new path; and

instruct the robot to move to the goal position based on the new path and the velocity constraints.

18. The system of claim 16, wherein responsive to determining that the user will not traverse, instructing the robot to move based on the initial path.

19. The system of claim 16, wherein generating the initial path further comprises:

assigning a Gaussian cost to the user with a maximum range;

receiving the goal position, an environment map, and the current position for the robot;

generating a two-dimensional grid with the first position of the user, the current position of the robot, and the goal position;

generating the initial path;

determining whether the initial path will disturb the user; and

responsive to the initial path failing to disturb the user, outputting the initial path.

20. The system of claim 16, wherein generating the initial path further comprises:

assigning a Gaussian cost to the user with a maximum range;

receiving the goal position, an environment map, and the current position for the robot;

generating a two-dimensional grid with the first position of the user, the current position of the robot, and the goal position;

generating the initial path;

determining whether the initial path will disturb the user;

responsive to the initial path disturbing the user, revising the initial path to include a longer route that avoids disturbing the user; and

outputting the initial path.