Robustness without Wrinkles: Parallel Simulation and Robust MPC for Certified Deformable Manipulation

2026-06-12

AI Summary

This work addresses the challenge of safe, real-time manipulation of deformable objects—such as ropes and fabrics—under model and perception uncertainties. The authors propose a framework integrating GPU-accelerated differentiable simulation, contact-smoothed modeling, and output-feedback robust model predictive control (MPC). By employing conformal prediction to calibrate visual feedback errors, the method constructs high-probability safe reachable tubes, enabling millisecond-scale robust planning and accelerating model-based reinforcement learning policy training. Evaluated on complex deformable object manipulation tasks, the approach significantly outperforms existing methods, achieving notable improvements in safety, planning speed, and task success rate.

Abstract

We present CORD-SLS, a real-time control method for safe deformable object manipulation, with a focus on ropes and cloth. At its core is a GPU-parallel differentiable simulator with contact smoothing which enables efficient gradient-based planning through intermittent contact. To robustly satisfy constraints under model and sensing uncertainty, we develop a real-time, GPU-parallel output-feedback robust model predictive control (MPC) algorithm that plans with this simulator. We further show that the simulator accelerates model-based RL for training neural manipulation policies. To improve real-world robustness, we use conformal prediction to calibrate visual-feedback and perception-error bounds for MPC, producing reachable tubes that enable high-probability safe control. We evaluate CORD-SLS on high-dimensional, contact-rich rope and cloth manipulation tasks in simulation and hardware, including obstacle avoidance, routing, folding, and smoothing. Across settings, CORD-SLS achieves millisecond-speed planning, exceeding baselines in safety, speed, and task success.

Problem

• deformable manipulation
• robust control
• model predictive control
• uncertainty
• real-time planning

Innovation

• differentiable simulation
• robust MPC
• GPU-parallel
• conformal prediction
• deformable manipulation