Harmonic Mobile Manipulation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Ruihan, Kim, Yejin, Hendrix, Rose, Kembhavi, Aniruddha, Wang, Xiaolong, Ehsani, Kiana
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909417681715200
author Yang, Ruihan
Kim, Yejin
Hendrix, Rose
Kembhavi, Aniruddha
Wang, Xiaolong
Ehsani, Kiana
author_facet Yang, Ruihan
Kim, Yejin
Hendrix, Rose
Kembhavi, Aniruddha
Wang, Xiaolong
Ehsani, Kiana
contents Recent advancements in robotics have enabled robots to navigate complex scenes or manipulate diverse objects independently. However, robots are still impotent in many household tasks requiring coordinated behaviors such as opening doors. The factorization of navigation and manipulation, while effective for some tasks, fails in scenarios requiring coordinated actions. To address this challenge, we introduce, HarmonicMM, an end-to-end learning method that optimizes both navigation and manipulation, showing notable improvement over existing techniques in everyday tasks. This approach is validated in simulated and real-world environments and adapts to novel unseen settings without additional tuning. Our contributions include a new benchmark for mobile manipulation and the successful deployment with only RGB visual observation in a real unseen apartment, demonstrating the potential for practical indoor robot deployment in daily life. More results are on our project site: https://rchalyang.github.io/HarmonicMM/
format Preprint
id arxiv_https___arxiv_org_abs_2312_06639
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Harmonic Mobile Manipulation
Yang, Ruihan
Kim, Yejin
Hendrix, Rose
Kembhavi, Aniruddha
Wang, Xiaolong
Ehsani, Kiana
Robotics
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Recent advancements in robotics have enabled robots to navigate complex scenes or manipulate diverse objects independently. However, robots are still impotent in many household tasks requiring coordinated behaviors such as opening doors. The factorization of navigation and manipulation, while effective for some tasks, fails in scenarios requiring coordinated actions. To address this challenge, we introduce, HarmonicMM, an end-to-end learning method that optimizes both navigation and manipulation, showing notable improvement over existing techniques in everyday tasks. This approach is validated in simulated and real-world environments and adapts to novel unseen settings without additional tuning. Our contributions include a new benchmark for mobile manipulation and the successful deployment with only RGB visual observation in a real unseen apartment, demonstrating the potential for practical indoor robot deployment in daily life. More results are on our project site: https://rchalyang.github.io/HarmonicMM/
title Harmonic Mobile Manipulation
topic Robotics
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2312.06639