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

Dexterous in-hand manipulation in robotics, particularly with multifingered 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 (NNs) that are retrievable in real time. Then, we combined the configuration space (C-space) representation with closed-loop control via dynamical system (DS) and sampling-based planning approaches. This integration enhances the efficiency and feasibility of pathfinding, enabling dynamic obstacle avoidance, thereby advancing the capabilities of multifingered robotic hands for in-hand manipulation tasks.