Force-and-Motion Constrained Planning for Tool Use

Abstract

The use of hand tools presents a challenge for robot manipulation in part because it calls for motions requiring continuous force application over a whole trajectory, usually involving large joint-angle excursions. The feasible application of a tool, such as pulling a nail with a hammer claw, requires careful coordination of the choice of grasp and joint trajectories to ensure kinematic and force limits are not exceededin the grasp as well as the robot mechanism. In this thesis, we formulate this type of problem as choosing the values of decision variables in the presence of various constraints. We evaluate the impact of the various constraints in some representative instances of tool use. To aid others in further investigating this class of problems, we have released materials such as printable tool models and experimental data. We hope that these can serve as the basis of a benchmark problem for investigating tasks that involve many kinematic, actuation, friction, and environment constraints.

kPAM 2.0: Feedback Control for Category-Level Robotic Manipulation

“…We can think of a robot as a programmable force/motion generator [7]. We propose to represent the task-specific motion profile as the motion of a set of oriented keypoints, and the force profile as the force/torque w.r.t some keypoints.…”

SEED: Series Elastic End Effectors in 6D for Visuotactile Tool Use

“…Tool-use has long been one of the hallmarks of intelligence [27], as well as a practical problem to solve for robotic applications. As such, many existing works [31,14] center around how to give robots the ability to use tools. However, only a few works attempt to perform explicit force control with a tool that has not been rigidly attached to the robot, but rather, must be grabbed before it can be used.…”

“…Most existing works in this setting focus on planning, where the grabbed tool must be used to manipulate the pose of another object [31,14,10]. Such plans can be very useful in reaching confined spaces [10] or beyond the workspace of the manipulator [31].…”

“…Even when sensing is given via finger attachments [9], the hardware often relies on friction to handle the forces that arise in hand-tool interaction, and may lack the ability to resist spatial forces in some of the axes. For example, torques applied perpendicular to the finger surface are hard to resist, but arise in many tool-use scenarios [14]. Multi-fingered hands are much more versatile, but existing solutions (e.g.…”

Planning for Multi-stage Forceful Manipulation

“…Approaches that attempt to explicitly encode solutions in the form of a policy, e.g. via a finite state machine or a fixed action sequence, will generally fail to capture the full range of feasible strategies [2], [3]. Methods that attempt to learn such a policy will need a very large number of interactions to explore this rich and highly-constrained solution space.…”