Semi-autonomous multi-use robot system and method of operation

• US 10,011,012 B2
• Filed: 05/05/2017
• Issued: 07/03/2018
• Est. Priority Date: 10/27/2009
• Status: Active Grant

• Current Assignee: Battelle Memorial Institute
• Original Assignee: Battelle Memorial Institute
• Inventors: Krasny, Darren P., Shoaf, Richard L., Keip, Jeffrey D., Newhouse, Scott A., Lastrapes, Timothy J.
• Primary Examiner(s): Oh, Harry Y
• Application Number:
  US15/587,615
• Publication Number:
  US 20170305015A1
• Time in Patent Office: 424 Days
• Field of Search: 700255
• CPC Class Codes: B25J 9/1666 Avoiding collision or forbidden zones
• CPC Class Codes: G05B 2219/40183 Tele-machining
• CPC Class Codes: G05B 2219/40418 Presurgical planning, on screen indicate regions to be operated on
• CPC Class Codes: G05B 2219/40424 Online motion planning, in real time, use vision to detect workspace changes

Abstract

A semi-autonomous robot system (10) that includes scanning and scanned data manipulation that is utilized for controlling remote operation of a robot system within an operating environment.

Claims

1. A robot system comprising:

a robot that includes an arm having multiple degrees of freedom of movement;

environmental data regarding an operating environment surrounding the robot; and

an operator station located remotely from the robot, the operator station including an operator input device, a computer and associated software that is configured to employ a motion planning algorithm in combination with the environmental data and commands received from the operator input device to;

voxelize the environmental data;

utilize the voxelized environmental data to define surfaces within the operating environment;

utilize the voxelized environmental data to define a path for the robot within the operating environment along a series of target waypoints, several time steps into the future, that avoids any collisions between the robot and the surfaces; and

control movement of the robot along the path, wherein the motion planning algorithm is further configured to employ the voxelized environmental data to define a path for the arm of the robot within the operating environment that avoid collisions between the arm of the robot and the surfaces defined within the operating environment; and

control movement of the arm of the robot along the path for the arm of the robot.

2. The robot system according to claim 1, wherein the computer and associated software is further configured to:

define the path for the robot by predicting, with a look-ahead feature, a potential collision of the robot with the surfaces when the robot is at each waypoint and modifying the path for the robot until no potential collisions are predicted based on commands received by the input device; and

movement of the robot before a collision.

3. The robot system according to claim 1, wherein the motion planning algorithm is a Rapidly-exploring Random Tree (RRT) motion planning algorithm.

4. The robot system according to claim 3, wherein the computer and associated software is further configured to:

acquire geometrical data regarding the operating environment; and

utilize the geometrical data to perform operations within the operating environment with virtual tooling.

5. The robot system according to claim 1, wherein the computer and associated software is further configured to define the path for the robot within an enclosed space for moving the arm of the robot to a selected point within the enclosed space while also avoiding collision with any of the surfaces defined within the operating environment.

6. The robot system according to claim 1, wherein the computer and associated software is further configured to produce continuous trajectories for contour following by first finding a plurality of collision-free candidate solutions and then using pseudo-inverse Jacobian control methodology to compute required joint angles and rates to achieve a desired path for the arm of the robot while also maintaining a proper orientation and path speed.

7. The robot system according to claim 1, further comprising a digital camera mounted upon the arm of the robot and a display device, the digital camera and display device being configured to provide a pictorial view of the operating environment to an operator as an aid to guiding movement of the robot.

8. The robot system according to claim 1, wherein the arm of the robot is configured to carry at least one tool.

9. The robot system according to claim 1, further including multiple computing nodes connected by Ethernet, the nodes spawning multiple threads to determine potential paths for movement of the robot.

10. The robot system according to claim 1, wherein the operating environment defines an enclosed space.

11. A method for operating a robot system including a robot having an arm with multiple degrees of freedom of movement and an operator station located remotely from the robot, the arm of the robot carrying a tool and the operator station being configured to control movement of the robot, said method comprising:

(a) collecting data regarding an operating environment surrounding the robot;

(b) defining surfaces within the operating environment;

(c) selecting, with an operator input device, a desired position for the robot in Cartesian space within the operating environment;

(d) determining a path for moving the robot to the desired position selected in step (c) along a series of target waypoints, several time steps into the future, so that the path avoids any collisions between the robot and the surfaces defined in step (b) while an operator is employing Cartesian control of the tool with the input device; and

(e) moving the robot to the position selected in step (c) via the path determined in step (d).

12. The method according to claim 11, wherein the operator station includes a display screen, with the display screen displaying a cursor controlled by the input device, and further wherein step (c) includes using the input device to position the cursor upon the display screen at the desired position for the tool.

13. The method according to claim 11, wherein determining the path for moving the robot includes determining the path within the operating environment by predicting, with a look-ahead feature, a potential collision of the robot with the surfaces defined in step (b) when the robot is at each waypoint and modifying the path until no potential collisions are predicted based on commands received by the input device and further comprises stopping movement of the robot along the path before a collision.

14. The method according to claim 11, wherein step (c) includes selecting a desired position of the tool and the robot performs a desired operation once the tool has moved to the position selected in step (c).

15. The method according to claim 14, wherein the data collected in step (a) is voxelized to generate voxelized data that defines the surfaces within the operating environment in step (b), and further wherein the voxelized data is utilized to determine the path in step (d).

16. The method according to claim 15, wherein the voxelized data is utilized to perform real-time collision checking between the robot and the operating environment.

17. The method according to claim 11, wherein the operator station includes a computer and associated software that is configured to use a Rapidly-exploring Random Tree (RRT) motion planning algorithm in combination with the data collected in step (a) to determine the path in step (d).

18. A method for operating a robot system including a robot having an arm with multiple degrees of freedom of movement and an operator station located remotely from the robot, the arm of the robot carrying a tool and the operator station being configured to control movement of the robot, said method comprising:

(a) collecting data regarding an operating environment surrounding the robot;

(b) defining surfaces within the operating environment;

(c) selecting, with an operator input device, a desired position for the tool in Cartesian space within the operating environment using the input device to click and drag across virtual geometry to define a trajectory;

(d) determining a path for moving the tool to the desired position selected in step (c) that avoids any collisions between the robot and the surfaces defined in step (b), whereby the tool follows the trajectory while maintaining a prescribed stand-off from the surfaces in the operating environment; and

(e) moving the tool to the position selected in step (c) via the path determined in step (d).

19. The method according to claim 18, wherein the data collected in step (a) is voxelized to generate voxelized data that defines the surfaces within the operating environment in step (b), and further wherein the voxelized data is utilized to determine the path in step (d).