Li, Z., Liu, J., Li, D., Teng, T., Li, M., Calinon, S., Caldwell, D.G. and Chen, F. (2025)
ManiDP: Manipulability-Aware Diffusion Policy for Posture-Dependent Bimanual Manipulation
In Proc. IEEE/RSJ Intl Conf. on Intelligent Robots and Systems (IROS), pp. 9956-9962.
Abstract
Recent work has demonstrated the potential of diffusion models in robot bimanual skill learning. However, existing methods ignore the learning of posture-dependent task features, which are crucial for adapting dual-arm configurations to meet specific force and velocity requirements in dexterous bimanual manipulation. To address this limitation, we propose Manipulability-Aware Diffusion Policy (ManiDP), a novel imitation learning method that not only generates plausible bimanual trajectories, but also optimizes dual-arm configurations to better satisfy posture-dependent task requirements. ManiDP achieves this by extracting bimanual manipulability from expert demonstrations and encoding the encapsulated posture features using Riemannian-based probabilistic models. These encoded posture features are then incorporated into a conditional diffusion process to guide the generation of task-compatible bimanual motion sequences. We evaluate ManiDP on six real-world bimanual tasks, where the experimental results demonstrate a 39.33% increase in average manipulation success rate and a 0.45 improvement in task compatibility compared to baseline methods. This work highlights the importance of integrating posture-relevant robotic priors into bimanual skill diffusion to enable human-like adaptability and dexterity.
Bibtex reference
@inproceedings{ZLi25IROS,
author={Li, Z. and Liu, J. and Li, D. and Teng, T. and Li, M. and Calinon, S. and Caldwell, D. G. and Chen, F.},
title={{ManiDP}: Manipulability-Aware Diffusion Policy for Posture-Dependent Bimanual Manipulation},
booktitle={Proc.\ {IEEE/RSJ} Intl Conf.\ on Intelligent Robots and Systems ({IROS})},
pages={9956--9962},
year={2025}
}