Robotic system control method and controller
The present disclosure provides a control method of a robotic system. The control method includes: deriving an approach location at which the end effector grips an operation object; deriving a scan location for scanning an identifier of the operation object; and based on the approach location and the scan location, creating or deriving a control sequence to instruct the robot to execute the control sequence. The control sequence includes (1) gripping the operation object from a start location; (2) scanning an identifier of the operation object with a scanner located between the start location and a task location; (3) temporarily releasing the operation object from the end effector and regripping the operation object by the end effector to be shifted, at a shift location, when a predetermined condition is satisfied; and (4) moving the operation object to the task location.
1. A non-transitory computer-readable medium storing processor instructions, the processor instructions, when executed by one or more processors, causing a robotic system to:
compute one or more control sequences that, when executed by a robot, transfers an operation object from a starting location to a task location, wherein the computed one or more control sequences cause the robot to:
transfer the operation object from the starting location based on gripping the operation object at a first grip location of the operation object;
regrip the operation object at a second grip location of the operation object at a location between the starting location and the task location; and
transfer the operation object from the location to the task location based on gripping the operation object at the second grip location of the operation object.
2. The non-transitory computer-readable medium of claim 1 , wherein the system is further caused to, prior to regripping the operation object, perform a scan of the operation object at a location between the starting location and the task location.
3. The non-transitory computer-readable medium of claim 2 , wherein the first grip location is computed to facilitate one or more scanning poses of the operation object while the operation object is transferred between the starting location and the task location.
4. The non-transitory computer-readable medium of claim 2 , wherein the regrip is based on the scan of the operation object at the location between the starting location and the task location.
5. The non-transitory computer-readable medium of claim 1 , wherein the system is further caused to, prior to regripping the operation object and subsequent to initially displacing the operation object from the starting location, obtain a measurement descriptive of the operation object.
6. The non-transitory computer-readable medium of claim 5 , wherein the measurement includes a dimension of the operation object.
7. The non-transitory computer-readable medium of claim 5 , wherein the regrip is based on the measurement descriptive of the operation object.
8. The non-transitory computer-readable medium of claim 1 , wherein the second grip location is derived subsequent to displacing the operation object from the starting location.
9. The non-transitory computer-readable medium of claim 8 , wherein the second grip location is derived dynamically based on information obtained while the operation object is in motion between the starting location and the task location.
10. The non-transitory computer-readable medium of claim 9 , wherein the information includes a physical measurement of the operation object.
11. The non-transitory computer-readable medium of claim 1 , wherein the robotic system is further caused to detect the operation object with a confidence measure, wherein the confidence measure is associated with an initial pose of the operation object at the starting location.
12. The non-transitory computer-readable medium of claim 11 , wherein the robotic system is further caused to determine, based on the confidence measure, one or more scanning poses for the operation object.
13. The non-transitory computer-readable medium of claim 12 , wherein the first grip location is identified based on the initial pose and the one or more scanning poses.
14. The non-transitory computer-readable medium of claim 11 , wherein the robotic system is further caused to determine a placement pose based on the confidence measure, wherein the placement pose is the pose the operation object has at the task location.
15. The non-transitory computer-readable medium of claim 14 , wherein the second grip location is identified based on the placement pose so that the second grip location is compatible with the placement pose.
16. The non-transitory computer-readable medium of claim 14 , wherein the robotic system is further caused to:
determine whether the first grip location is compatible with the placement pose; and
in response to a determination that the first grip location is not compatible with the placement pose, identify the second grip location.
17. A method for controlling a robotic system, the method comprising:
computing one or more control sequences that, when executed by a robot, transfers an operation object from a starting location to a task location, wherein the computed one or more control sequences cause the robot to:
transfer the operation object from the starting location based on gripping the operation object at a first grip location of the operation object;
regrip the operation object at a second grip location of the operation object at a location between the starting location and the task location; and
transfer the operation object from the location to the task location based on gripping the operation object at the second grip location of the operation object.
18. The method of claim 17 , further comprising detecting the operation object with a confidence measure, wherein the confidence measure is associated with an initial pose of the operation object at the starting location.
19. A system, comprising:
a communication circuit configured to communicate with at least a robot; and
one or more processors coupled to the communication circuit, wherein the one or more processors are configured to execute a control method, the control method including computing one or more control sequences that, when executed by the robot, transfers an operation object from a starting location to a task location, wherein the computed one or more control sequences cause the robot to:
transfer the operation object from the starting location based on gripping the operation object at a first grip location of the operation object;
regrip the operation object at a second grip location of the operation object at a location between the starting location and the task location; and
transfer the operation object from the location to the task location based on gripping the operation object at the second grip location of the operation object.
20. The system of claim 19 , wherein the control method further comprises detecting the operation object with a confidence measure, wherein the confidence measure is associated with an initial pose of the operation object at the starting location.