Generative Skill Chaining: Long-Horizon Skill Planning with Diffusion Models

Utkarsh Aashu Mishra, Shangjie Xue, Yongxin Chen, Danfei Xu
Proceedings of The 7th Conference on Robot Learning, PMLR 229:2905-2925, 2023.

Abstract

Long-horizon tasks, usually characterized by complex subtask dependencies, present a significant challenge in manipulation planning. Skill chaining is a practical approach to solving unseen tasks by combining learned skill priors. However, such methods are myopic if sequenced greedily and face scalability issues with search-based planning strategy. To address these challenges, we introduce Generative Skill Chaining (GSC), a probabilistic framework that learns skill-centric diffusion models and composes their learned distributions to generate long-horizon plans during inference. GSC samples from all skill models in parallel to efficiently solve unseen tasks while enforcing geometric constraints. We evaluate the method on various long-horizon tasks and demonstrate its capability in reasoning about action dependencies, constraint handling, and generalization, along with its ability to replan in the face of perturbations. We show results in simulation and on real robot to validate the efficiency and scalability of GSC, highlighting its potential for advancing long-horizon task planning. More details are available at: https://generative-skill-chaining.github.io/

Cite this Paper

BibTeX
@InProceedings{pmlr-v229-mishra23a, title = {Generative Skill Chaining: Long-Horizon Skill Planning with Diffusion Models}, author = {Mishra, Utkarsh Aashu and Xue, Shangjie and Chen, Yongxin and Xu, Danfei}, booktitle = {Proceedings of The 7th Conference on Robot Learning}, pages = {2905--2925}, year = {2023}, editor = {Tan, Jie and Toussaint, Marc and Darvish, Kourosh}, volume = {229}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v229/mishra23a/mishra23a.pdf}, url = {https://proceedings.mlr.press/v229/mishra23a.html}, abstract = {Long-horizon tasks, usually characterized by complex subtask dependencies, present a significant challenge in manipulation planning. Skill chaining is a practical approach to solving unseen tasks by combining learned skill priors. However, such methods are myopic if sequenced greedily and face scalability issues with search-based planning strategy. To address these challenges, we introduce Generative Skill Chaining (GSC), a probabilistic framework that learns skill-centric diffusion models and composes their learned distributions to generate long-horizon plans during inference. GSC samples from all skill models in parallel to efficiently solve unseen tasks while enforcing geometric constraints. We evaluate the method on various long-horizon tasks and demonstrate its capability in reasoning about action dependencies, constraint handling, and generalization, along with its ability to replan in the face of perturbations. We show results in simulation and on real robot to validate the efficiency and scalability of GSC, highlighting its potential for advancing long-horizon task planning. More details are available at: https://generative-skill-chaining.github.io/} }
Endnote
%0 Conference Paper %T Generative Skill Chaining: Long-Horizon Skill Planning with Diffusion Models %A Utkarsh Aashu Mishra %A Shangjie Xue %A Yongxin Chen %A Danfei Xu %B Proceedings of The 7th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2023 %E Jie Tan %E Marc Toussaint %E Kourosh Darvish %F pmlr-v229-mishra23a %I PMLR %P 2905--2925 %U https://proceedings.mlr.press/v229/mishra23a.html %V 229 %X Long-horizon tasks, usually characterized by complex subtask dependencies, present a significant challenge in manipulation planning. Skill chaining is a practical approach to solving unseen tasks by combining learned skill priors. However, such methods are myopic if sequenced greedily and face scalability issues with search-based planning strategy. To address these challenges, we introduce Generative Skill Chaining (GSC), a probabilistic framework that learns skill-centric diffusion models and composes their learned distributions to generate long-horizon plans during inference. GSC samples from all skill models in parallel to efficiently solve unseen tasks while enforcing geometric constraints. We evaluate the method on various long-horizon tasks and demonstrate its capability in reasoning about action dependencies, constraint handling, and generalization, along with its ability to replan in the face of perturbations. We show results in simulation and on real robot to validate the efficiency and scalability of GSC, highlighting its potential for advancing long-horizon task planning. More details are available at: https://generative-skill-chaining.github.io/
APA
Mishra, U.A., Xue, S., Chen, Y. & Xu, D.. (2023). Generative Skill Chaining: Long-Horizon Skill Planning with Diffusion Models. Proceedings of The 7th Conference on Robot Learning, in Proceedings of Machine Learning Research 229:2905-2925 Available from https://proceedings.mlr.press/v229/mishra23a.html.

Related Material