Berkeley Humanoid: A Research Platform for Learning-based Control

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liao, Qiayuan, Zhang, Bike, Huang, Xuanyu, Huang, Xiaoyu, Li, Zhongyu, Sreenath, Koushil
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913454163492864
author Liao, Qiayuan
Zhang, Bike
Huang, Xuanyu
Huang, Xiaoyu
Li, Zhongyu
Sreenath, Koushil
author_facet Liao, Qiayuan
Zhang, Bike
Huang, Xuanyu
Huang, Xiaoyu
Li, Zhongyu
Sreenath, Koushil
contents We introduce Berkeley Humanoid, a reliable and low-cost mid-scale humanoid research platform for learning-based control. Our lightweight, in-house-built robot is designed specifically for learning algorithms with low simulation complexity, anthropomorphic motion, and high reliability against falls. The robot's narrow sim-to-real gap enables agile and robust locomotion across various terrains in outdoor environments, achieved with a simple reinforcement learning controller using light domain randomization. Furthermore, we demonstrate the robot traversing for hundreds of meters, walking on a steep unpaved trail, and hopping with single and double legs as a testimony to its high performance in dynamical walking. Capable of omnidirectional locomotion and withstanding large perturbations with a compact setup, our system aims for scalable, sim-to-real deployment of learning-based humanoid systems. Please check http://berkeley-humanoid.com for more details.
format Preprint
id arxiv_https___arxiv_org_abs_2407_21781
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Berkeley Humanoid: A Research Platform for Learning-based Control
Liao, Qiayuan
Zhang, Bike
Huang, Xuanyu
Huang, Xiaoyu
Li, Zhongyu
Sreenath, Koushil
Robotics
We introduce Berkeley Humanoid, a reliable and low-cost mid-scale humanoid research platform for learning-based control. Our lightweight, in-house-built robot is designed specifically for learning algorithms with low simulation complexity, anthropomorphic motion, and high reliability against falls. The robot's narrow sim-to-real gap enables agile and robust locomotion across various terrains in outdoor environments, achieved with a simple reinforcement learning controller using light domain randomization. Furthermore, we demonstrate the robot traversing for hundreds of meters, walking on a steep unpaved trail, and hopping with single and double legs as a testimony to its high performance in dynamical walking. Capable of omnidirectional locomotion and withstanding large perturbations with a compact setup, our system aims for scalable, sim-to-real deployment of learning-based humanoid systems. Please check http://berkeley-humanoid.com for more details.
title Berkeley Humanoid: A Research Platform for Learning-based Control
topic Robotics
url https://arxiv.org/abs/2407.21781