PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
June 14, 20245 citationsOpen Access

HumanPlus: Humanoid Shadowing and Imitation from Humans

View Full Paper
ZFZipeng FuQZQingqing ZhaoQWQ. Wu

Key Points

  • Humanoid robots autonomously complete tasks like unloading objects and greeting another robot with a success rate of 60-100%.
  • The study implemented reinforcement learning and behavior cloning using 40-hour human motion datasets for training.
  • A full-stack system was developed to teach humanoids skills through shadowing, using only a RGB camera for real-time tracking. Experience with a 33-DoF humanoid robot shows effective imitation of human activities, such as walking and folding clothes.

Abstract

One of the key arguments for building robots that have similar form factors to human beings is that we can leverage the massive human data for training. Yet, doing so has remained challenging in practice due to the complexities in humanoid perception and control, lingering physical gaps between humanoids and humans in morphologies and actuation, and lack of a data pipeline for humanoids to learn autonomous skills from egocentric vision. In this paper, we introduce a full-stack system for humanoids to learn motion and autonomous skills from human data. We first train a low-level policy in simulation via reinforcement learning using existing 40-hour human motion datasets. This policy transfers to the real world and allows humanoid robots to follow human body and hand motion in real time using only a RGB camera, i.e. shadowing. Through shadowing, human operators can teleoperate humanoids to collect whole-body data for learning different tasks in the real world. Using the data collected, we then perform supervised behavior cloning to train skill policies using egocentric vision, allowing humanoids to complete different tasks autonomously by imitating human skills. We demonstrate the system on our customized 33-DoF 180cm humanoid, autonomously completing tasks such as wearing a shoe to stand up and walk, unloading objects from warehouse racks, folding a sweatshirt, rearranging objects, typing, and greeting another robot with 60-100% success rates using up to 40 demonstrations. Project website: https://humanoid-ai.github.io/

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Fu et al. (2024) studied this question.

synapsesocial.com/papers/68e64b3cb6db6435875dc02fhttps://doi.org/10.48550/arxiv.2406.10454
Ask AI
Helpful
Bookmark
Share
View Full Paper