将软体机器人嵌入物理引擎，实现接触丰富的模拟与真实部署。
Do Rigid-Body Simulators Dream of Soft Robots? Learning Contact-Rich Manipulation for Tendon-Driven Continuum Robots
- 用连续力学启发的离散化方法，把腱驱动软体机器人接入MuJoCo物理引擎。
- 在3段式软体机器人上实现零样本迁移到真实机械臂的接触操作任务。
- 首个完成软体机器人接触操作的仿真到真实迁移，适合机器人控制研究者。
学习软体连续机器人在高接触场景下的全身操控，受限于缺乏加速刚体机器人操控的仿真基础设施。现有软体机器人仿真器虽具物理真实性，但缺少接触处理、驱动支持或学习集成能力；而刚体近似虽具备这些功能，却牺牲了物理真实性。本文通过推导基于连续力学的离散化方法，将腱驱动连续机器人（TDCR）原生嵌入MuJoCo，统一腱力、接触和动力学于单一物理管道。仿真结果与柯瑟拉杆参考模型（静态与动态）及真实硬件一致。随后，在仿真中通过遥操作训练状态基模仿学习策略，并零样本部署至7自由度Franka机械臂上的3段式真实TDCR，在两个高接触任务中成功执行。据我们所知，这是首个实现连续机器人接触丰富操作的仿真到真实迁移。
原文摘要 · Abstract (English)
Learning contact-rich, whole-body manipulation for soft continuum robots is held back by the lack of simulation infrastructure that has accelerated rigid-robot manipulation. Existing soft robot simulators are physically grounded but lack the contact handling, actuation support, or learning integration needed for contact-rich manipulation; rigid-body approximations offer these capabilities but sacrifice physical grounding. We bridge this gap for tendon-driven continuum robots (TDCRs) by deriving a continuum-mechanics-informed discretization that places the soft robot natively inside MuJoCo, unifying tendon forces, body contact, and dynamics in a single physics pipeline. We validate the simulator against a Cosserat rod reference (static and dynamic) and real TDCR hardware. We then train state-based imitation learning policies via teleoperation in simulation and deploy them zero-shot to a physical 3-segment TDCR on a 7-DoF Franka arm across two contact-rich manipulation tasks. To our knowledge, this is the first demonstration of sim-to-real transfer for contact-rich manipulation with continuum robots.
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。