A neural signed configuration distance function for path planning of picking manipulators

TL;DR

This paper introduces a neural signed configuration distance function (nSCDF) for efficient path planning of picking manipulators, enabling collision-free corridor generation and optimized paths with reduced computation time.

Contribution

The paper presents a novel neural implicit obstacle representation (nSCDF) that reformulates multi-query path planning using balls in the configuration space, improving efficiency.

Findings

Paths are close to those from asymptotically optimal planners.

Significantly reduced planning time compared to traditional methods.

Effective collision avoidance with neural implicit obstacle representation.

Abstract

Picking manipulators are task specific robots, with fewer degrees of freedom compared to general-purpose manipulators, and are heavily used in industry. The efficiency of the picking robots is highly dependent on the path planning solution, which is commonly done using sampling-based multi-query methods. The planner is robustly able to solve the problem, but its heavy use of collision-detection limits the planning capabilities for online use. We approach this problem by presenting a novel implicit obstacle representation for path planning, a neural signed configuration distance function (nSCDF), which allows us to form collision-free balls in the configuration space. We use the ball representation to re-formulate a state of the art multi-query path planner, i.e., instead of points, we use balls in the graph. Our planner returns a collision-free corridor, which allows us to use convex programming to produce optimized paths. From our numerical experiments, we observe that our planner produces paths that are close to those from an asymptotically optimal path planner, in significantly less time.