Maximally manipulable vision-based motion planning for robotic rough-cutting on arbitrarily shaped surfaces
This addresses industrial rough-cutting tasks, such as demolition of legacy nuclear plants, where precise cuts are not required but manipulability is crucial for avoiding singularities and responding to forces, though it is incremental as it extends existing sampling-based methods.
The paper tackles the problem of constrained motion planning for robotic rough-cutting on unknown surfaces by maximizing manipulability and minimizing surface-distance traveled, showing that their planner successfully completes tasks while avoiding singularities and ensuring significantly greater manipulability compared to a conventional RRT* planner.
This paper presents a method for constrained motion planning from vision, which enables a robot to move its end-effector over an observed surface, given start and destination points. The robot has no prior knowledge of the surface shape, but observes it from a noisy point-cloud camera. We consider the multi-objective optimisation problem of finding robot trajectories which maximise the robot's manipulability throughout the motion, while also minimising surface-distance travelled between the two points. This work has application in industrial problems of \textit{rough} robotic cutting, \textit{e.g.} demolition of legacy nuclear plant, where the cut path need not be precise as long as it achieves dismantling. We show how detours in the cut path can be leveraged, to increase the manipulability of the robot at all points along the path. This helps avoid singularities, while maximising the robot's capability to make small deviations during task execution, \textit{e.g.} compliantly responding to cutting forces via impedance control. We show how a sampling-based planner can be projected onto the Riemannian manifold of a curved surface, and extended to include a term which maximises manipulability. We present the results of empirical experiments, with both simulated and real robots, which are tasked with moving over a variety of different surface shapes. Our planner enables successful task completion, while avoiding singularities and ensuring significantly greater manipulability when compared against a conventional RRT* planner.