Imitation-Guided Bimanual Planning for Stable Manipulation under Changing External Forces

2025-09-23

AI Summary

To address the challenge of inefficient and unstable bimanual grasping transitions under time-varying external forces in dynamic environments—where stability and real-time performance are difficult to reconcile—this paper proposes an imitation-guided bimanual coordination planning framework. Methodologically: (1) a stable intersection region is defined on the grasping manifold, coupled with an efficient sampling strategy enabling smooth transitions between unimanual and bimanual grasps; (2) a hierarchical two-stage motion architecture is introduced, wherein global trajectories are generated via imitation learning and locally refined by a quadratic programming (QP)-based optimizer to jointly ensure real-time obstacle avoidance, kinematic feasibility, and dexterous manipulability. Experiments demonstrate that the framework significantly reduces regrasping cost and computational overhead, improving grasping transition efficiency by 23% and trajectory tracking accuracy by 19% under high-force tasks, thereby achieving adaptive bimanual coordination with both high stability and dexterity.

Technology Category

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

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Robotic manipulation in dynamic environments often requires seamless transitions between different grasp types to maintain stability and efficiency. However, achieving smooth and adaptive grasp transitions remains a challenge, particularly when dealing with external forces and complex motion constraints. Existing grasp transition strategies often fail to account for varying external forces and do not optimize motion performance effectively. In this work, we propose an Imitation-Guided Bimanual Planning Framework that integrates efficient grasp transition strategies and motion performance optimization to enhance stability and dexterity in robotic manipulation. Our approach introduces Strategies for Sampling Stable Intersections in Grasp Manifolds for seamless transitions between uni-manual and bi-manual grasps, reducing computational costs and regrasping inefficiencies. Additionally, a Hierarchical Dual-Stage Motion Architecture combines an Imitation Learning-based Global Path Generator with a Quadratic Programming-driven Local Planner to ensure real-time motion feasibility, obstacle avoidance, and superior manipulability. The proposed method is evaluated through a series of force-intensive tasks, demonstrating significant improvements in grasp transition efficiency and motion performance. A video demonstrating our simulation results can be viewed at href{https://youtu.be/3DhbUsv4eDo}{ extcolor{blue}{https://youtu.be/3DhbUsv4eDo}}.

Problem

• Achieving smooth grasp transitions under changing external forces
• Optimizing motion performance with complex motion constraints
• Reducing computational costs and regrasping inefficiencies

Innovation

• Sampling stable intersections in grasp manifolds
• Hierarchical dual-stage motion architecture
• Imitation learning and quadratic programming integration