Learning quadrupedal locomotion on deformable terrain

地形 强化学习 机器人 计算机科学 四足动物 人工智能 模拟 步行机器人 软机器人 地质学 生态学 生物 古生物学
作者
Suyoung Choi,Gwanghyeon Ji,Jeongsoo Park,Hyeongjun Kim,Juhyeok Mun,Jeong Hyun Lee,Jemin Hwangbo
出处
期刊:Science robotics [American Association for the Advancement of Science]
卷期号:8 (74) 被引量:69
标识
DOI:10.1126/scirobotics.ade2256
摘要

Simulation-based reinforcement learning approaches are leading the next innovations in legged robot control. However, the resulting control policies are still not applicable on soft and deformable terrains, especially at high speed. The primary reason is that reinforcement learning approaches, in general, are not effective beyond the data distribution: The agent cannot perform well in environments that it has not experienced. To this end, we introduce a versatile and computationally efficient granular media model for reinforcement learning. Our model can be parameterized to represent diverse types of terrain from very soft beach sand to hard asphalt. In addition, we introduce an adaptive control architecture that can implicitly identify the terrain properties as the robot feels the terrain. The identified parameters are then used to boost the locomotion performance of the legged robot. We applied our techniques to the Raibo robot, a dynamic quadrupedal robot developed in-house. The trained networks demonstrated high-speed locomotion capabilities on deformable terrains: The robot was able to run on soft beach sand at 3.03 meters per second although the feet were completely buried in the sand during the stance phase. We also demonstrate its ability to generalize to different terrains by presenting running experiments on vinyl tile flooring, athletic track, grass, and a soft air mattress.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
ding应助迷路的初柔采纳,获得10
1秒前
1秒前
2秒前
2秒前
2秒前
guo完成签到,获得积分20
2秒前
2秒前
感动的红酒完成签到,获得积分10
2秒前
2秒前
上官听白发布了新的文献求助10
3秒前
老10完成签到,获得积分10
3秒前
远荒发布了新的文献求助10
3秒前
yaoxuer发布了新的文献求助10
3秒前
Cindy完成签到,获得积分10
3秒前
星之守护者完成签到,获得积分20
4秒前
ggggglllll完成签到,获得积分10
4秒前
yz发布了新的文献求助10
4秒前
nostalgia发布了新的文献求助10
5秒前
研友_08ozgZ完成签到,获得积分10
5秒前
沉默诗柳完成签到,获得积分10
5秒前
欧科狗完成签到,获得积分10
5秒前
5秒前
诚心的冰棍完成签到,获得积分10
5秒前
7秒前
zhanghao完成签到 ,获得积分10
7秒前
虚拟的含灵完成签到,获得积分10
7秒前
7秒前
头上有犄角bb完成签到,获得积分10
7秒前
7秒前
8秒前
ZH发布了新的文献求助10
8秒前
8秒前
8秒前
8秒前
9秒前
落后千雁完成签到,获得积分10
9秒前
年轻半雪完成签到,获得积分10
10秒前
搜集达人应助星之守护者采纳,获得10
10秒前
lemon发布了新的文献求助10
10秒前
大模型应助文静小凝采纳,获得30
10秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3969398
求助须知:如何正确求助?哪些是违规求助? 3514239
关于积分的说明 11173064
捐赠科研通 3249531
什么是DOI,文献DOI怎么找? 1794934
邀请新用户注册赠送积分活动 875501
科研通“疑难数据库(出版商)”最低求助积分说明 804827