用强化学习实现软机械臂零样本仿真到现实的视觉伺服控制。
Zero-shot Sim-to-Real Transfer for Reinforcement Learning-based Visual Servoing of Soft Continuum Arms
- 分层控制：用RL规划运动，局部控制器优化执行，仅需视觉反馈。
- 仿真训练成功率99.8%，硬件部署零样本迁移成功率达67%。
- 适合软体机械臂、无需实机调参的视觉伺服场景。
软连续体机械臂（SCAs）因其无限自由度和非线性特性，在建模与控制上面临挑战。本文提出一种基于强化学习（RL）的视觉伺服框架，具备零样本仿真到现实的迁移能力，实验在单节气动驱动可弯曲扭转的机械臂上验证。该框架通过将运动学与力学特性解耦，采用RL运动规划控制器与局部执行控制器协同工作，仅依赖少量传感与视觉反馈。模型完全在仿真中训练，达到99.8%的成功率；部署至真实硬件后，零样本迁移成功率仍达67%，展现出良好的鲁棒性与适应性。该方法为3D视觉伺服中的软体机械臂提供了可扩展的解决方案，具备进一步优化与应用拓展潜力。
原文摘要 · Abstract (English)
Soft continuum arms (SCAs) soft and deformable nature presents challenges in modeling and control due to their infinite degrees of freedom and non-linear behavior. This work introduces a reinforcement learning (RL)-based framework for visual servoing tasks on SCAs with zero-shot sim-to-real transfer capabilities, demonstrated on a single section pneumatic manipulator capable of bending and twisting. The framework decouples kinematics from mechanical properties using an RL kinematic controller for motion planning and a local controller for actuation refinement, leveraging minimal sensing with visual feedback. Trained entirely in simulation, the RL controller achieved a 99.8% success rate. When deployed on hardware, it achieved a 67% success rate in zero-shot sim-to-real transfer, demonstrating robustness and adaptability. This approach offers a scalable solution for SCAs in 3D visual servoing, with potential for further refinement and expanded applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。