DeformX: A Versatile Co-Simulation Framework for Deformable Linear Objects

2026-06-20

AI Summary

Existing methods struggle to simultaneously achieve physical accuracy and visual realism in simulating deformable linear objects such as cables and ropes, hindering sim-to-real transfer for robotic manipulation tasks. This work proposes DeformX, the first framework to integrate high-fidelity physics modeling based on Cosserat rod theory—which supports self-collision and arbitrary surface contact—into NVIDIA Isaac Sim, coupled with mesh skinning for photorealistic visualization. The resulting co-simulation framework seamlessly integrates into robotic learning pipelines and demonstrates significant performance gains in real-world experiments: fine-tuning SAM3 with DeformX-generated data improves cable segmentation mAP@75 by 10.2%, and a rope-swinging policy trained entirely in simulation achieves an average target-hitting error of 6.6 cm on a UR5e robot.

Abstract

Deformable linear objects (DLOs) such as wires, cables, and ropes are common in robotic manipulation tasks, yet simulating them with both visual realism and physical accuracy remains challenging. Existing visual simulation methods typically rely on procedural geometric primitives that lack physically grounded deformation behavior, while physics-based approaches with robot learning support often approximate DLOs as rigid-link chains or generic soft bodies, failing to accurately capture the bending, twisting, and shear mechanics of slender elastic structures. In this work, we introduce DeformX, a co-simulation framework that integrates a dedicated Cosserat rod physics engine with NVIDIA Isaac Sim, enabling DLO simulations that are both physically faithful and visually realistic. Our Cosserat rod engine simulates the dynamics and self-collisions of DLOs, and contact interactions with arbitrary free-form meshes. To achieve high-fidelity visualization, we employ mesh skinning to map discrete rod deformations onto imported CAD models. To the best of our knowledge, DeformX is the one of the first frameworks for DLO simulation that unifies realistic visualization, principled physics, and compatibility with robot learning pipelines. We demonstrate its versatility across synthetic data generation and policy learning for DLO manipulation, and validate visual and physical fidelity through comparisons against real-world experiments. Notably, fine-tuning Segment Anything Model 3 (SAM3) on DeformX-generated data yields a 10.2% mAP@75 improvement in real-image wire segmentation, and a rope-swinging policy trained entirely in DeformX achieves a mean target-hitting error of 6.6 cm on a UR5e manipulator in real-world trials, highlighting its strong sim-to-real transfer capability.

Problem

• Deformable Linear Objects
• Physical Simulation
• Visual Realism
• Cosserat Rod
• Robot Manipulation

Innovation

• Cosserat rod
• co-simulation
• deformable linear objects
• sim-to-real transfer
• mesh skinning