Twisting Lids Off with Two Hands

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lin, Toru, Yin, Zhao-Heng, Qi, Haozhi, Abbeel, Pieter, Malik, Jitendra
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917801581608960
author Lin, Toru
Yin, Zhao-Heng
Qi, Haozhi
Abbeel, Pieter
Malik, Jitendra
author_facet Lin, Toru
Yin, Zhao-Heng
Qi, Haozhi
Abbeel, Pieter
Malik, Jitendra
contents Manipulating objects with two multi-fingered hands has been a long-standing challenge in robotics, due to the contact-rich nature of many manipulation tasks and the complexity inherent in coordinating a high-dimensional bimanual system. In this work, we share novel insights into physical modeling, real-time perception, and reward design that enable policies trained in simulation using deep reinforcement learning (RL) to be effectively and efficiently transferred to the real world. Specifically, we consider the problem of twisting lids of various bottle-like objects with two hands, demonstrating policies with generalization capabilities across a diverse set of unseen objects as well as dynamic and dexterous behaviors. To the best of our knowledge, this is the first sim-to-real RL system that enables such capabilities on bimanual multi-fingered hands.
format Preprint
id arxiv_https___arxiv_org_abs_2403_02338
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Twisting Lids Off with Two Hands
Lin, Toru
Yin, Zhao-Heng
Qi, Haozhi
Abbeel, Pieter
Malik, Jitendra
Robotics
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Manipulating objects with two multi-fingered hands has been a long-standing challenge in robotics, due to the contact-rich nature of many manipulation tasks and the complexity inherent in coordinating a high-dimensional bimanual system. In this work, we share novel insights into physical modeling, real-time perception, and reward design that enable policies trained in simulation using deep reinforcement learning (RL) to be effectively and efficiently transferred to the real world. Specifically, we consider the problem of twisting lids of various bottle-like objects with two hands, demonstrating policies with generalization capabilities across a diverse set of unseen objects as well as dynamic and dexterous behaviors. To the best of our knowledge, this is the first sim-to-real RL system that enables such capabilities on bimanual multi-fingered hands.
title Twisting Lids Off with Two Hands
topic Robotics
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2403.02338