Visual Imitation Enables Contextual Humanoid Control

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Allshire, Arthur, Choi, Hongsuk, Zhang, Junyi, McAllister, David, Zhang, Anthony, Kim, Chung Min, Darrell, Trevor, Abbeel, Pieter, Malik, Jitendra, Kanazawa, Angjoo
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916924444639232
author Allshire, Arthur
Choi, Hongsuk
Zhang, Junyi
McAllister, David
Zhang, Anthony
Kim, Chung Min
Darrell, Trevor
Abbeel, Pieter
Malik, Jitendra
Kanazawa, Angjoo
author_facet Allshire, Arthur
Choi, Hongsuk
Zhang, Junyi
McAllister, David
Zhang, Anthony
Kim, Chung Min
Darrell, Trevor
Abbeel, Pieter
Malik, Jitendra
Kanazawa, Angjoo
contents How can we teach humanoids to climb staircases and sit on chairs using the surrounding environment context? Arguably, the simplest way is to just show them-casually capture a human motion video and feed it to humanoids. We introduce VIDEOMIMIC, a real-to-sim-to-real pipeline that mines everyday videos, jointly reconstructs the humans and the environment, and produces whole-body control policies for humanoid robots that perform the corresponding skills. We demonstrate the results of our pipeline on real humanoid robots, showing robust, repeatable contextual control such as staircase ascents and descents, sitting and standing from chairs and benches, as well as other dynamic whole-body skills-all from a single policy, conditioned on the environment and global root commands. VIDEOMIMIC offers a scalable path towards teaching humanoids to operate in diverse real-world environments.
format Preprint
id arxiv_https___arxiv_org_abs_2505_03729
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Visual Imitation Enables Contextual Humanoid Control
Allshire, Arthur
Choi, Hongsuk
Zhang, Junyi
McAllister, David
Zhang, Anthony
Kim, Chung Min
Darrell, Trevor
Abbeel, Pieter
Malik, Jitendra
Kanazawa, Angjoo
Robotics
Computer Vision and Pattern Recognition
How can we teach humanoids to climb staircases and sit on chairs using the surrounding environment context? Arguably, the simplest way is to just show them-casually capture a human motion video and feed it to humanoids. We introduce VIDEOMIMIC, a real-to-sim-to-real pipeline that mines everyday videos, jointly reconstructs the humans and the environment, and produces whole-body control policies for humanoid robots that perform the corresponding skills. We demonstrate the results of our pipeline on real humanoid robots, showing robust, repeatable contextual control such as staircase ascents and descents, sitting and standing from chairs and benches, as well as other dynamic whole-body skills-all from a single policy, conditioned on the environment and global root commands. VIDEOMIMIC offers a scalable path towards teaching humanoids to operate in diverse real-world environments.
title Visual Imitation Enables Contextual Humanoid Control
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.03729