Granted Patent B2

US 12,440,974 · App. 18/648,116 · Granted Oct 14, 2025

Inventors: David N. Walsh (Brooklyn, NY); Eric A. Litman (Brooklyn, NY); Charles Paul Pace (Manchester Center, VT); Matthew DiCicco (Brooklyn, NY)

Assignee: Aescape, Inc.

B25J9/1633B25J9/106B25J9/1664

Abstract

Claims (36)

1. A system, comprising:

a robotic manipulator including an end effector; and

one or more processors configured to:

cause the end effector to contact a deformable surface of an object at a first location on the deformable surface and apply a predefined amount of force to the deformable surface;

sense force data based at least in part on interaction of the end effector and the object; and

generate a manipulation plan based at least in part on the sensed force data to manage progression of the end effector from the first location on the deformable surface to a second location on the deformable surface while maintaining contact with the deformable surface.

2. The system recited in claim 1 , wherein the one or more processors are further configured to:

detect, while the end effector progresses from the first location on the deformable surface to the second location on the deformable surface, that a generated torque command would exceed a joint torque limit associated with a joint; and

in response to detecting that the generated torque command would exceed the joint torque limit, modify a stored representation of the generated torque command to be at or below the joint torque limit while maintaining a desired trajectory.

3. The system recited in claim 1 , wherein at least one of the first location or the second location is defined based on a contact frame that is different from a reference frame of the end effector.

4. The system recited in claim 3 , wherein the one or more processors are further configured to:

dynamically modify the contact frame in response to the sensed force data.

5. The system recited in claim 1 , wherein the predefined amount of force applied to the deformable surface comprises a predefined goal from a plurality of manipulation goals, and wherein the one or more processors are further configured to modify a gain parameter associated with a controller of the robotic manipulator based at least in part on the plurality of manipulation goals.

6. The system recited in claim 1 , wherein the one or more processors are further configured to:

modify a gain parameter associated with a controller of the robotic manipulator based at least in part on an orientation of the deformable surface.

7. A method, comprising:

causing an end effector associated with a robotic manipulator to contact a deformable surface of an object at a first location on the deformable surface and apply a predefined amount of force to the deformable surface;

sensing force data based at least in part on interaction of the end effector and the object; and

generating a manipulation plan based at least in part on the sensed force data to manage progression of the end effector from the first location on the deformable surface to a second location on the deformable surface while maintaining contact with the deformable surface.

8. The method of claim 7 , further comprising:

detecting, while the end effector progresses from the first location on the deformable surface to the second location on the deformable surface, that a generated torque command would exceed a joint torque limit associated with a joint; and

in response to detecting that the generated torque command would exceed the joint torque limit, modifying a stored representation of the generated torque command to be at or below the joint torque limit while maintaining a desired trajectory.

9. The method of claim 7 , wherein at least one of the first location or the second location is defined based on a contact frame that is different from a reference frame of the end effector.

10. The method of claim 9 , further comprising:

dynamically modifying the contact frame in response to the sensed force data.

11. The method of claim 7 , wherein the predefined amount of force applied to the deformable surface comprises a predefined goal from a plurality of manipulation goals, and further comprising modifying a gain parameter associated with a controller of the robotic manipulator based at least in part on the plurality of manipulation goals.

12. The method of claim 7 , further comprising:

modifying a gain parameter associated with a controller of the robotic manipulator based at least in part on an orientation of the deformable surface.

13. The system of claim 1 , wherein the one or more processors are further configured to determine at least one of a structure or a state of the object based at least in part on the sensed force data.

14. The system of claim 13 , wherein the one or more processors are configured to generate the manipulation plan based at least in part on the state of the object that is determined based at least in part on the sensed force data.

15. The system of claim 1 , wherein the one or more processors are further configured to attribute the sensed force data to at least one of structural constituency or changes in the object.

16. The system of claim 1 , wherein the one or more processors are further configured to determine a friction component.

17. The system of claim 16 , wherein the one or more processors are further configured to manage progression based at least in the determined friction component.

18. The system of claim 1 , wherein the one or more processors are further configured to determine a contact patch based at least in part on the interaction of the end effector and the object.

19. The system of claim 18 , wherein the contact patch comprises a region of surface to surface contact of the end effector and the object.

20. The system of claim 1 , wherein the processors are configured to determine a contact pressure between a surface of the end effector and the deformable surface of the object.

Assignments (3)

Continuity (3)

References Cited (109)