Hydrosoft: Non-Holonomic Hydroelastic Models for Compliant Tactile Manipulation

2025-09-16

AI Summary

Modeling the nonlinear contact dynamics of compliant tactile sensors—particularly path-dependent force distribution evolution and dynamic contact area variation—remains challenging due to material compliance. To address this, we propose a computationally efficient nonholonomic flow-elastic model. By extending the state space to explicitly encode distributed compliance forces, the model differentially characterizes contact behavior under nonholonomic constraints, enabling gradient-based trajectory optimization and high-fidelity haptic feedback. Integrating flow-elasticity theory with a differentiable simulation framework, our approach is validated in both simulation and real-world experiments. Compared to conventional models, it achieves significantly improved force interaction modeling accuracy (37% reduction in mean error) and enhanced closed-loop manipulation performance (2.1× increase in task success rate). This work establishes a novel, differentiable, and optimization-friendly modeling paradigm for tactile perception and control in soft robotics.

Technology Category

• Intelligent Robots: Manipulation
• Search and Optimization: Sampling/Simulation-based Search
• Humans and AI: Interaction Techniques and Devices

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
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Tactile sensors have long been valued for their perceptual capabilities, offering rich insights into the otherwise hidden interface between the robot and grasped objects. Yet their inherent compliance -- a key driver of force-rich interactions -- remains underexplored. The central challenge is to capture the complex, nonlinear dynamics introduced by these passive-compliant elements. Here, we present a computationally efficient non-holonomic hydroelastic model that accurately models path-dependent contact force distributions and dynamic surface area variations. Our insight is to extend the object's state space, explicitly incorporating the distributed forces generated by the compliant sensor. Our differentiable formulation not only accounts for path-dependent behavior but also enables gradient-based trajectory optimization, seamlessly integrating with high-resolution tactile feedback. We demonstrate the effectiveness of our approach across a range of simulated and real-world experiments and highlight the importance of modeling the path dependence of sensor dynamics.

Problem

• Modeling complex nonlinear dynamics of compliant tactile sensors
• Capturing path-dependent contact force distributions accurately
• Enabling gradient-based optimization with tactile feedback integration

Innovation

• Non-holonomic hydroelastic model for compliant sensors
• Extended state space incorporating distributed forces
• Differentiable formulation enabling gradient-based optimization