SILO: Simulation-in-the-Loop Sim-to-Real Transfer for Multi-Stage Cable Routing

2026-07-05

AI Summary

This work addresses the challenge of manipulating linear deformable objects, such as cables, in multi-stage routing tasks, where complex deformations hinder reliable control. To tackle this, the authors propose a reinforcement learning–based sim-to-real transfer framework that integrates GPU-accelerated parallel simulation for training, a local policy network, and a robust cable state estimator. Notably, they introduce a simulation-in-the-loop (SILO) deployment architecture to enable efficient policy transfer from simulation to the real world. Experimental results demonstrate that the proposed approach significantly outperforms existing learning-based methods on real-world cable routing tasks, achieving higher task success rates, nearly halving cycle times, and substantially improving policy generalization and deployment efficiency.

Abstract

Linear-deformable manipulation remains challenging due to the complex deformations of objects such as cables and ropes. Prior data-driven approaches, particularly imitation learning, have shown some promise in narrowly defined settings but typically require thousands of demonstrations for specific tasks and cable types, limiting scalability and generalization. We introduce a sim-to-real reinforcement learning (RL) framework for multi-stage cable routing that leverages GPU-parallelized simulation to approximate linear deformable behaviors. Training across thousands of parallel simulations enables the learned policies to generalize across diverse cable geometries and deformation patterns. To bridge the sim-to-real gap, we propose a novel deployment strategy that combines a Simulation In the LOop (SILO) execution framework, localized RL policies, and robust cable state estimation. On real-world cable routing tasks, our approach achieves higher success rates and 2x reduction in cycle times compared to prior state-of-the-art learning methods. To our knowledge, this is the first successful sim-to-real transfer of RL policies for multi-stage cable routing. Videos and additional visualizations are available at https://silo-cable-routing.github.io/

Problem

• linear-deformable manipulation
• cable routing
• sim-to-real transfer
• scalability
• generalization

Innovation

• sim-to-real transfer
• reinforcement learning
• deformable object manipulation
• GPU-parallelized simulation
• cable routing