Salvato in:
Dettagli Bibliografici
Autori principali: Peng, Weikun, Lv, Jun, Zeng, Yuwei, Chen, Haonan, Zhao, Siheng, Sun, Jichen, Lu, Cewu, Shao, Lin
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2407.03245
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929551022489600
author Peng, Weikun
Lv, Jun
Zeng, Yuwei
Chen, Haonan
Zhao, Siheng
Sun, Jichen
Lu, Cewu
Shao, Lin
author_facet Peng, Weikun
Lv, Jun
Zeng, Yuwei
Chen, Haonan
Zhao, Siheng
Sun, Jichen
Lu, Cewu
Shao, Lin
contents The tie-knotting task is highly challenging due to the tie's high deformation and long-horizon manipulation actions. This work presents TieBot, a Real-to-Sim-to-Real learning from visual demonstration system for the robots to learn to knot a tie. We introduce the Hierarchical Feature Matching approach to estimate a sequence of tie's meshes from the demonstration video. With these estimated meshes used as subgoals, we first learn a teacher policy using privileged information. Then, we learn a student policy with point cloud observation by imitating teacher policy. Lastly, our pipeline applies learned policy to real-world execution. We demonstrate the effectiveness of TieBot in simulation and the real world. In the real-world experiment, a dual-arm robot successfully knots a tie, achieving 50% success rate among 10 trials. Videos can be found https://tiebots.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2407_03245
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TieBot: Learning to Knot a Tie from Visual Demonstration through a Real-to-Sim-to-Real Approach
Peng, Weikun
Lv, Jun
Zeng, Yuwei
Chen, Haonan
Zhao, Siheng
Sun, Jichen
Lu, Cewu
Shao, Lin
Robotics
Artificial Intelligence
Systems and Control
The tie-knotting task is highly challenging due to the tie's high deformation and long-horizon manipulation actions. This work presents TieBot, a Real-to-Sim-to-Real learning from visual demonstration system for the robots to learn to knot a tie. We introduce the Hierarchical Feature Matching approach to estimate a sequence of tie's meshes from the demonstration video. With these estimated meshes used as subgoals, we first learn a teacher policy using privileged information. Then, we learn a student policy with point cloud observation by imitating teacher policy. Lastly, our pipeline applies learned policy to real-world execution. We demonstrate the effectiveness of TieBot in simulation and the real world. In the real-world experiment, a dual-arm robot successfully knots a tie, achieving 50% success rate among 10 trials. Videos can be found https://tiebots.github.io/.
title TieBot: Learning to Knot a Tie from Visual Demonstration through a Real-to-Sim-to-Real Approach
topic Robotics
Artificial Intelligence
Systems and Control
url https://arxiv.org/abs/2407.03245