Learning to Plan & Schedule with Reinforcement-Learned Bimanual Robot Skills

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wan, Weikang, Ramos, Fabio, Yang, Xuning, Garrett, Caelan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910012591308800
author Wan, Weikang
Ramos, Fabio
Yang, Xuning
Garrett, Caelan
author_facet Wan, Weikang
Ramos, Fabio
Yang, Xuning
Garrett, Caelan
contents Long-horizon contact-rich bimanual manipulation presents a significant challenge, requiring complex coordination involving a mixture of parallel execution and sequential collaboration between arms. In this paper, we introduce a hierarchical framework that frames this challenge as an integrated skill planning & scheduling problem, going beyond purely sequential decision-making to support simultaneous skill invocation. Our approach is built upon a library of single-arm and bimanual primitive skills, each trained using Reinforcement Learning (RL) in GPU-accelerated simulation. We then train a Transformer-based planner on a dataset of skill compositions to act as a high-level scheduler, simultaneously predicting the discrete schedule of skills as well as their continuous parameters. We demonstrate that our method achieves higher success rates on complex, contact-rich tasks than end-to-end RL approaches and produces more efficient, coordinated behaviors than traditional sequential-only planners.
format Preprint
id arxiv_https___arxiv_org_abs_2510_25634
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning to Plan & Schedule with Reinforcement-Learned Bimanual Robot Skills
Wan, Weikang
Ramos, Fabio
Yang, Xuning
Garrett, Caelan
Robotics
Artificial Intelligence
Long-horizon contact-rich bimanual manipulation presents a significant challenge, requiring complex coordination involving a mixture of parallel execution and sequential collaboration between arms. In this paper, we introduce a hierarchical framework that frames this challenge as an integrated skill planning & scheduling problem, going beyond purely sequential decision-making to support simultaneous skill invocation. Our approach is built upon a library of single-arm and bimanual primitive skills, each trained using Reinforcement Learning (RL) in GPU-accelerated simulation. We then train a Transformer-based planner on a dataset of skill compositions to act as a high-level scheduler, simultaneously predicting the discrete schedule of skills as well as their continuous parameters. We demonstrate that our method achieves higher success rates on complex, contact-rich tasks than end-to-end RL approaches and produces more efficient, coordinated behaviors than traditional sequential-only planners.
title Learning to Plan & Schedule with Reinforcement-Learned Bimanual Robot Skills
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2510.25634