Wearing A Coat: Dual-Arm Robot-Assisted Dressing with Differentiable Clothing Simulation

2026-07-12

AI Summary

This work addresses the control challenges in dual-arm robot-assisted dressing, particularly those arising from complex garment–body interactions and the difficulty of modeling and manipulating garments under constraints during partial dressing states. To tackle these issues, the authors propose a control algorithm integrating real-time differentiable cloth simulation. By incorporating an explicit iterative simulation scheme with high-order perturbations and a local constraint model, the method achieves efficient and stable physical simulation. A multi-stage policy further coordinates global motion planning with high-frequency local adjustments. The approach is validated on both simulated and real dual-arm robotic platforms for jacket-assisted dressing, demonstrating significantly improved task success rates and real-time performance.

Abstract

The development of assistive robots for dressing tasks serves to augment human convenience and improve the quality of life for individuals with physical impairments. However, due to the intricate contact interactions between garments and the human limbs during dressing, most robot-assisted dressing algorithms treat clothing as an assembly of discrete segments, thereby struggling to manage the partial worn garments under contact constraints. To overcome this challenge, we propose a novel robotic dressing control algorithm that integrates realtime differentiable clothing simulation. The simulation algorithm employs explicit iterative scheme with intentionally introduced higher-order perturbations to enhance computational efficiency while maintaining stability under large time-step conditions. Through simulation, we resolve the garment state under contact constraints, which then enables a multi-phase control strategy for successful coat dressing assistance. To further improve real-time performance, we introduce a constrained local model along with its corresponding optimization solver, permitting high-frequency local compensation for the differentiable simulation based global controller. Finally, we experimentally validate our approach through both simulated and physical dressing scenarios, conclusively demonstrating its feasibility and efficacy

Problem

• robot-assisted dressing
• clothing simulation
• contact constraints
• partial worn garments
• dual-arm robot

Innovation

• differentiable simulation
• robot-assisted dressing
• contact constraints
• real-time control
• clothing manipulation