SILO: Simulation-in-the-Loop Sim-to-Real Transfer for Multi-Stage Cable Routing
2026-07-06 • Robotics
RoboticsArtificial Intelligence
AI summaryⓘ
The authors address the challenge of manipulating cables and ropes, which bend and twist in complex ways, by using reinforcement learning (RL) trained in computer simulations. Instead of needing many real demonstrations, they run thousands of simulations in parallel to teach the robot how to handle different cable shapes and movements. They also develop a special strategy to make sure the robot can apply what it learned in simulations to real-life tasks. Their method works better and faster on real cable routing tasks compared to previous learning approaches. This work is the first to successfully transfer RL policies for multi-step cable routing from simulation to the real world.
linear deformable manipulationreinforcement learningsim-to-real transferimitation learningcable routingGPU-parallelized simulationSimulation In the Loop (SILO)policy generalizationrobotic manipulationstate estimation
Authors
Stone Tao, Jie Xu, Hesam Rabeti, Yashraj Narang, Yijie Guo, Iretiayo Akinola
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/