Enhancing Dexterity in Confined Spaces: Real-Time Motion Planning for Multi-Fingered In-Hand Manipulation

TL;DR

This paper presents a real-time motion planning method for multi-fingered robotic hands, combining neural network-based collision modeling with sampling-based planning to enable dynamic, collision-free in-hand manipulation.

Contribution

It introduces a novel real-time approach that models collision-free space with neural networks and integrates it with sampling-based planning for improved dexterity.

Findings

Achieved real-time collision-free path planning for multi-fingered hands.

Enhanced in-hand manipulation capabilities with dynamic obstacle avoidance.

Demonstrated improved efficiency over traditional methods.

Abstract

Dexterous in-hand manipulation in robotics, particularly with multi-fingered robotic hands, poses significant challenges due to the intricate avoidance of collisions among fingers and the object being manipulated. Collision-free paths for all fingers must be generated in real-time, as the rapid changes in hand and finger positions necessitate instantaneous recalculations to prevent collisions and ensure undisturbed movement. This study introduces a real-time approach to motion planning in high-dimensional spaces. We first explicitly model the collision-free space using neural networks that are retrievable in real time. Then, we combined the C-space representation with closed-loop control via dynamical system and sampling-based planning approaches. This integration enhances the efficiency and feasibility of path-finding, enabling dynamic obstacle avoidance, thereby advancing the capabilities of multi-fingered robotic hands for in-hand manipulation tasks.