Robot control system and method for planning driving path of robot

• US 10,124,488 B2
• Filed: 10/24/2016
• Issued: 11/13/2018
• Est. Priority Date: 10/29/2015
• Status: Active Grant

• Current Assignee: Korea Advanced Institute of Science and Technology
• Original Assignee: Korea Advanced Institute of Science and Technology
• Inventors: Lee, Junghwan, Park, Jung Min, Oh, Sang Rok
• Primary Examiner(s): RINK, RYAN J
• Application Number:
  US15/332,312
• Publication Number:
  US 20170120448A1
• Time in Patent Office: 750 Days
• Field of Search: None
• CPC Class Codes: B25J 9/1666 Avoiding collision or forbidden zones
• CPC Class Codes: G05D 1/0214 in accordance with safety or protection criteria, e.g. avoiding hazardous areas monitoring the location of vehicles within a certain area, e.g. forbidden or allowed areas, in traffic control systems for road vehicles G08G1/13

Abstract

A robot control system includes a detecting device configured to detect an obstacle, and a control device configured to control a robot by planning a driving path of the robot. The control device generates a road map space including nodes containing information about a state of the robot and edges connecting the nodes. Also, the control device checks whether the obstacle detected by the detecting device overlaps with the nodes, removes an overlapped node, generates a driving path by sampling remaining nodes and edges, and checks whether the edges of the driving path overlap with the obstacle. When there is no overlapped edge, the control device determines the driving path on the road map space to plan a path along which the robot drives without colliding with the obstacle.

Claims

1. A method for planning a driving path for a robot, the method comprising:

detecting an obstacle;

checking, prior to generation of a driving path, whether nodes overlap with the obstacle;

removing one of the nodes overlapping with the obstacle;

generating the driving path by sampling edges and remaining nodes excluding the removed one of the nodes;

checking whether edges of the generated driving path overlap with the obstacle; and

determining the driving path on a road map space in response to no edge overlaps overlapping with the obstacle,

wherein the road map space defines a driving state of the robot.

2. The method of claim 1, further comprising:

removing one of the edges of the generated driving path in response to the one of the edges overlapping with the obstacle; and

generating a new driving path by sampling the remaining nodes and remaining edges excluding the removed one of the edges.

3. The method of claim 1,

wherein the robot is a manipulator robot having one or more joints.

4. The method of claim 3,

wherein the nodes define a location of the robot and a posture of a joint of the one or more joints.

5. The method of claim 1,

wherein the driving path is planned in a robot state tree including a part of nodes and edges extracted from the road map space.

6. The method of claim 5,

wherein an interval between the nodes included in the robot state tree is adjusted to be smaller than a minimal size of the detected obstacle.

7. The method of claim 3,

wherein the road map space is interconvertible with a working space in which the robot actually drives, by means of an inverse kinematics calculation method, and

wherein the driving path is generated by directly connecting a start point and a target point of an end-effector of the robot on the working space.

8. The method of claim 2, further comprising:

before removing one of the edges, generating edges of the driving path connecting a present node corresponding to a present state of the robot to nodes adjacent to the present node on the road map space.

9. The method of claim 2, further comprising:

before generating a new driving path, detecting movement of the obstacle and generating a new node and a new edge in an area where the obstacle is no longer located.

10. The method of claim 2, further comprising:

before generating a new driving path, removing a node and an edge that are neither directly nor indirectly connected to a present node corresponding to a present state of the robot, among the remaining nodes and the remaining edges.

11. A control system for a robot, comprising:

a detector configured to detect an obstacle; and

a controller configured to;

control a robot by planning a driving path of the robot,

generate a road map space including nodes containing information about a state of the robot and edges connecting the nodes,

check, prior to generation of a driving path, whether the nodes overlap with the obstacle detected by the detecting device,

remove an overlapped node of the nodes,

generate the driving path by sampling edges and remaining nodes excluding the removed overlapped node,

check whether the edges of the generated driving path overlap with the obstacle, and

determine, in response to there being no overlapped edge, the driving path on the road map space to plan a path along which the robot is to drive without colliding with the obstacle.

12. The robot control system according to claim 11, further comprising:

a driver controlled by the controller to drive the robot along the determined driving path.

13. The robot control system according to claim 12,

wherein the controller is configured to indirectly detect an obstacle based on changes of a driving state of the driver.

14. The robot control system according to claim 11,

wherein the detector is configured to periodically detect the obstacle while the robot is driving, and

wherein the controller is configured to:

control the driver to drive the robot along the determined driving path, and

periodically check whether the nodes and edges of the determined driving path overlap with the obstacle.