Paper Overview
Research Area: Computer Vision / Robotics Authors: Zhao-Heng Yin, Guanya Shi, Pieter Abbeel Published: 2025-06-13 arXiv: 2506.10668
Summary
Articulated tool manipulation remains a major challenge in dexterous robotics due to the need to coordinate internal degrees of freedom and contact-rich interactions. While prior work has largely focused on rigid objects, articulated tool use remains underexplored because of its physical complexity and the difficulty of learning functional grasping and manipulation policies.
The authors present Mana (Manipulation Animator), a general sim-to-real framework that reinterprets dexterous manipulation as an animation problem. Inspired by computer animation, Mana employs a coarse-to-fine pipeline that transforms procedurally-generated grasp keyframes into manipulation trajectories through motion planning and reinforcement learning.
Key Highlights
- Animation-inspired pipeline: Procedurally generated grasp keyframes are converted into full manipulation trajectories via motion planning plus reinforcement learning.
- Largely automatic data generation: Specifying functional affordances takes only a few mouse clicks (under 1 minute per tool).
- Zero-shot sim-to-real transfer: Evaluated on four articulated tools spanning diverse scales and joint types, Mana succeeds at both grasping and in-hand manipulation without real-world fine-tuning.
- Scalable approach: The framework offers a scalable path toward dexterous use of articulated tools.
Original Abstract (excerpt)
> Articulated tool manipulation remains a major challenge in dexterous robotics due to the need to coordinate internal degrees of freedom and contact-rich interactions. While prior work has largely focused on rigid objects, articulated tool use remains underexplored because of its physical complexity and the difficulty of learning functional grasping and manipulation policies. We present Mana (Manipulation Animator), a general sim-to-real framework that reinterprets dexterous manipulation as an animation problem. Inspired by computer animation, Mana employs a coarse-to-fine pipeline that transforms procedurally-generated grasp keyframes into manipulation trajectories through motion planning and reinforcement learning. The data generation process is largely automatic, requiring only a few mou...
Read the full paper: https://arxiv.org/abs/2506.10668
--- *Auto-collected on 2026-06-14*