A Reactive Grasping Framework for Multi-DoF Grippers via Task Space Velocity Fields and Joint Space QP

2025-08-31

AI Summary

To address the combinatorial explosion in high-dimensional state spaces arising from real-time, collision-free grasping of high-DOF multi-fingered robotic hands in dynamic environments, this paper proposes a hierarchical planning framework that synergistically integrates task-space and joint-space control. Specifically, a low-dimensional task-space velocity field—incorporating collision-avoidance constraints—is constructed to provide global path guidance, while full joint-space tracking and real-time optimization are achieved via weighted multi-priority quadratic programming (QP). Robust pose estimation is enabled by integrating FoundationPose. The key innovation lies in decoupling global motion planning into coarse-grained task-space guidance and fine-grained joint-space regulation, thereby significantly mitigating the curse of dimensionality. Both simulation and physical experiments demonstrate that the system achieves stable, real-time, collision-free reaching and grasping with millisecond-level responsiveness to target motion and external disturbances.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

We present a fast and reactive grasping framework for multi-DoF grippers that combines task-space velocity fields with a joint-space Quadratic Program (QP) in a hierarchical structure. Reactive, collision-free global motion planning is particularly challenging for high-DoF systems, since simultaneous increases in state dimensionality and planning horizon trigger a combinatorial explosion of the search space, making real-time planning intractable. To address this, we plan globally in a lower-dimensional task space, such as fingertip positions, and track locally in the full joint space while enforcing all constraints. This approach is realized by constructing velocity fields in multiple task-space coordinates (or in some cases a subset of joint coordinates) and solving a weighted joint-space QP to compute joint velocities that track these fields with appropriately assigned priorities. Through simulation experiments with privileged knowledge and real-world tests using the recent pose-tracking algorithm FoundationPose, we verify that our method enables high-DoF arm-hand systems to perform real-time, collision-free reaching motions while adapting to dynamic environments and external disturbances.

Problem

• Reactive collision-free motion planning for high-DoF grippers
• Real-time planning under combinatorial explosion challenges
• Dynamic adaptation to environmental changes and disturbances

Innovation

• Task-space velocity fields for global planning
• Joint-space QP for local constraint tracking
• Hierarchical structure combining task and joint spaces