WireCraft: A Simulation Benchmark for Industrial DLO Manipulation

arXiv:2606.18097 · cs.RO · Submitted 2026-06-16 · Read on arXiv

cs.RO

Submitted: 2026-06-16

Updated: 2026-10-13

Comments: Accepted at CoRL 2026 (Spotlight). Camera-ready version with additional simulation and real-robot experiments. 29 pages including references and appendices

Code: https://github.com/isaac-sim/IsaacSim

Project page: https://isaac-sim.github.io/IsaacLab/main/source

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 7× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Imitation Learning (IL) — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes

Sources

• ManipulationNet: An Infrastructure for Benchmarking Real-World Robot Manipulation with Physical Skill Challenges and Embodied Multimodal Reasoning
• DEFT: Differentiable Branched Discrete Elastic Rods for Modeling Furcated DLOs in Real-Time
• Proximal Policy Optimization Algorithms
• Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards
• Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies