Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2509.23556 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908562960154624 |
|---|---|
| author | Johnson, Curtis C. Alessi, Carlo Falotico, Egidio Killpack, Marc D. |
| author_facet | Johnson, Curtis C. Alessi, Carlo Falotico, Egidio Killpack, Marc D. |
| contents | Whole-body manipulation is a powerful yet underexplored approach that enables robots to interact with large, heavy, or awkward objects using more than just their end-effectors. Soft robots, with their inherent passive compliance, are particularly well-suited for such contact-rich manipulation tasks, but their uncertainties in kinematics and dynamics pose significant challenges for simulation and control. In this work, we address this challenge with a simulation that can run up to 350x real time on a single thread in MuJoCo and provide a detailed analysis of the critical tradeoffs between speed and accuracy for this simulation. Using this framework, we demonstrate a successful zero-shot sim-to-real transfer of a learned whole-body manipulation policy, achieving an 88% success rate on the Baloo hardware platform. We show that guiding RL with a simple motion primitive is critical to this success where standard reward shaping methods struggled to produce a stable and successful policy for whole-body manipulation. Furthermore, our analysis reveals that the learned policy does not simply mimic the motion primitive. It exhibits beneficial reactive behavior, such as re-grasping and perturbation recovery. We analyze and contrast this learned policy against an open-loop baseline to show that the policy can also exhibit aggressive over-corrections under perturbation. To our knowledge, this is the first demonstration of forceful, six-DoF whole-body manipulation using two continuum soft arms on a large-scale platform (10 kg payloads), with zero-shot policy transfer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_23556 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Zero-shot Whole-Body Manipulation with a Large-Scale Soft Robotic Torso via Guided Reinforcement Learning Johnson, Curtis C. Alessi, Carlo Falotico, Egidio Killpack, Marc D. Robotics Whole-body manipulation is a powerful yet underexplored approach that enables robots to interact with large, heavy, or awkward objects using more than just their end-effectors. Soft robots, with their inherent passive compliance, are particularly well-suited for such contact-rich manipulation tasks, but their uncertainties in kinematics and dynamics pose significant challenges for simulation and control. In this work, we address this challenge with a simulation that can run up to 350x real time on a single thread in MuJoCo and provide a detailed analysis of the critical tradeoffs between speed and accuracy for this simulation. Using this framework, we demonstrate a successful zero-shot sim-to-real transfer of a learned whole-body manipulation policy, achieving an 88% success rate on the Baloo hardware platform. We show that guiding RL with a simple motion primitive is critical to this success where standard reward shaping methods struggled to produce a stable and successful policy for whole-body manipulation. Furthermore, our analysis reveals that the learned policy does not simply mimic the motion primitive. It exhibits beneficial reactive behavior, such as re-grasping and perturbation recovery. We analyze and contrast this learned policy against an open-loop baseline to show that the policy can also exhibit aggressive over-corrections under perturbation. To our knowledge, this is the first demonstration of forceful, six-DoF whole-body manipulation using two continuum soft arms on a large-scale platform (10 kg payloads), with zero-shot policy transfer. |
| title | Zero-shot Whole-Body Manipulation with a Large-Scale Soft Robotic Torso via Guided Reinforcement Learning |
| topic | Robotics |
| url | https://arxiv.org/abs/2509.23556 |