Adaptive Manipulation Potential and Haptic Estimation for Tool-Mediated Interaction

2026-03-11

AI Summary

This work addresses the lack of human-like dexterity in tool-mediated manipulation caused by visual occlusion and underconstrained tactile perception. The authors propose a unified framework based on a parameterized equilibrium manifold (EM), integrating a differentiable contact model, tactile SLAM, and adaptive stiffness control. By establishing a physics-geometry duality, tactile state estimation is reformulated as manifold parameter inference. The study pioneers the use of tactile SLAM for joint discrete shape classification and continuous pose estimation in tool manipulation. Coupled with online trajectory replanning and uncertainty-aware impedance modulation, the system demonstrates robust performance in both simulation and over 260 real-world screw loosening trials, achieving success rates meeting standard operational requirements. Ablation studies confirm that tactile SLAM and adaptive stiffness significantly outperform fixed-impedance baselines, effectively preventing jamming during high-precision assembly tasks.

Technology Category

• Intelligent Robots: Manipulation
• Computer Vision: Low Level & Physics-based Vision
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: The sharing economy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Achieving human-level dexterity in contact-rich, tool-mediated manipulation remains a significant challenge due to visual occlusion and the underdetermined nature of haptic sensing. This paper introduces a parameterized Equilibrium Manifold (EM) as a unified representation for tool-mediated interaction, and develops a closed-loop framework that integrates haptic estimation, online planning, and adaptive stiffness control. We establish a physical-geometric duality using an adaptive manipulation potential incorporating a differentiable contact model, which induces the manifold's geometric structure and ensures that complex physical interactions are encapsulated as continuous operations on the EM. Within this framework, we reformulate haptic estimation as a manifold parameter estimation problem. Specifically, a hybrid inference strategy (haptic SLAM) is employed in which discrete object shapes are classified via particle filtering, while the continuous object pose is estimated using analytical gradients for efficient optimization. By continuously updating the parameters of the manipulation potential, the framework dynamically reshapes the induced EM to guide online trajectory replanning and implement uncertainty-aware impedance control, thereby closing the perception-action loop. The system is validated through simulation and over 260 real-world screw-loosening trials. Experimental results demonstrate robust identification and manipulation success in standard scenarios while maintaining accurate tracking. Furthermore, ablation studies confirm that haptic SLAM and uncertainty-aware stiffness modulation outperform fixed impedance baselines, effectively preventing jamming during tight tolerance interactions.

Problem

• tool-mediated manipulation
• visual occlusion
• haptic sensing
• contact-rich interaction
• dexterity

Innovation

• Equilibrium Manifold
• haptic SLAM
• adaptive stiffness control
• differentiable contact model
• tool-mediated manipulation