Dynamic Manipulation of Deformable Objects in 3D: Simulation, Benchmark and Learning Strategy

TL;DR

This paper presents a comprehensive framework for 3D deformable object manipulation, combining a novel simulation benchmark, a diffusion policy with physics-informed adaptation, and extensive experiments demonstrating improved accuracy and robustness.

Contribution

It introduces a new simulation environment and benchmark for 3D deformable object manipulation, and proposes the Dynamics Informed Diffusion Policy with physics-based test-time adaptation.

Findings

Effective policy learning in 3D rope manipulation

Enhanced robustness through physics-informed adaptation

Superior performance over baseline methods

Abstract

Goal-conditioned dynamic manipulation is inherently challenging due to complex system dynamics and stringent task constraints, particularly in deformable object scenarios characterized by high degrees of freedom and underactuation. Prior methods often simplify the problem to low-speed or 2D settings, limiting their applicability to real-world 3D tasks. In this work, we explore 3D goal-conditioned rope manipulation as a representative challenge. To mitigate data scarcity, we introduce a novel simulation framework and benchmark grounded in reduced-order dynamics, which enables compact state representation and facilitates efficient policy learning. Building on this, we propose Dynamics Informed Diffusion Policy (DIDP), a framework that integrates imitation pretraining with physics-informed test-time adaptation. First, we design a diffusion policy that learns inverse dynamics within the reduced-order space, enabling imitation learning to move beyond na\"ive data fitting and capture the underlying physical structure. Second, we propose a physics-informed test-time adaptation scheme that imposes kinematic boundary conditions and structured dynamics priors on the diffusion process, ensuring consistency and reliability in manipulation execution. Extensive experiments validate the proposed approach, demonstrating strong performance in terms of accuracy and robustness in the learned policy.