Learning robust perceptive locomotion for quadrupedal robots in the wild

机器人 地形 计算机科学 人工智能 感知 步行机器人 稳健性(进化) 步态 计算机视觉 机器人学 模拟 人机交互 心理学 物理医学与康复 生态学 神经科学 医学 生物化学 化学 基因 生物
作者
Takahiro Miki,Joonho Lee,Jemin Hwangbo,Lorenz Wellhausen,Vladlen Koltun,Marco Hutter
出处
期刊:Science robotics [American Association for the Advancement of Science (AAAS)]
卷期号:7 (62) 被引量:434
标识
DOI:10.1126/scirobotics.abk2822
摘要

Legged robots that can operate autonomously in remote and hazardous environments will greatly increase opportunities for exploration into under-explored areas. Exteroceptive perception is crucial for fast and energy-efficient locomotion: perceiving the terrain before making contact with it enables planning and adaptation of the gait ahead of time to maintain speed and stability. However, utilizing exteroceptive perception robustly for locomotion has remained a grand challenge in robotics. Snow, vegetation, and water visually appear as obstacles on which the robot cannot step~-- or are missing altogether due to high reflectance. Additionally, depth perception can degrade due to difficult lighting, dust, fog, reflective or transparent surfaces, sensor occlusion, and more. For this reason, the most robust and general solutions to legged locomotion to date rely solely on proprioception. This severely limits locomotion speed, because the robot has to physically feel out the terrain before adapting its gait accordingly. Here we present a robust and general solution to integrating exteroceptive and proprioceptive perception for legged locomotion. We leverage an attention-based recurrent encoder that integrates proprioceptive and exteroceptive input. The encoder is trained end-to-end and learns to seamlessly combine the different perception modalities without resorting to heuristics. The result is a legged locomotion controller with high robustness and speed. The controller was tested in a variety of challenging natural and urban environments over multiple seasons and completed an hour-long hike in the Alps in the time recommended for human hikers.
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
1秒前
华风完成签到,获得积分10
1秒前
共享精神应助郭郭郭郭采纳,获得20
2秒前
2秒前
2秒前
2秒前
2秒前
2秒前
李健的小迷弟应助冯同学采纳,获得80
3秒前
小豹子发布了新的文献求助10
5秒前
打打应助张两丰采纳,获得10
6秒前
orange发布了新的文献求助10
7秒前
风_Feng发布了新的文献求助10
7秒前
sumugeng完成签到,获得积分10
7秒前
weihuang发布了新的文献求助10
8秒前
李子潭应助tigger采纳,获得20
8秒前
牧鱼完成签到,获得积分10
9秒前
沈括完成签到,获得积分10
9秒前
10秒前
11秒前
11秒前
完美世界应助111ccc采纳,获得10
11秒前
li完成签到 ,获得积分10
13秒前
我我轻轻完成签到 ,获得积分10
13秒前
mmddlj完成签到 ,获得积分10
13秒前
可不可以完成签到 ,获得积分10
13秒前
14秒前
培培完成签到 ,获得积分10
14秒前
科研通AI6应助科研通管家采纳,获得10
14秒前
科目三应助科研通管家采纳,获得10
14秒前
科研通AI6应助科研通管家采纳,获得10
14秒前
CipherSage应助科研通管家采纳,获得10
14秒前
科研通AI2S应助科研通管家采纳,获得10
14秒前
纪汶欣完成签到 ,获得积分10
14秒前
赘婿应助科研通管家采纳,获得10
14秒前
科研通AI6应助科研通管家采纳,获得30
14秒前
科研通AI6应助科研通管家采纳,获得10
14秒前
夏来应助科研通管家采纳,获得10
14秒前
浮游应助科研通管家采纳,获得10
14秒前
浮游应助科研通管家采纳,获得10
14秒前
高分求助中
Encyclopedia of Quaternary Science Third edition 2025 12000
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
The Social Work Ethics Casebook: Cases and Commentary (revised 2nd ed.). Frederic G. Reamer 800
Beyond the sentence : discourse and sentential form / edited by Jessica R. Wirth 600
Holistic Discourse Analysis 600
Vertébrés continentaux du Crétacé supérieur de Provence (Sud-Est de la France) 600
Vertebrate Palaeontology, 5th Edition 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 纳米技术 计算机科学 内科学 化学工程 复合材料 物理化学 基因 遗传学 催化作用 冶金 量子力学 光电子学
热门帖子
关注 科研通微信公众号,转发送积分 5338701
求助须知:如何正确求助?哪些是违规求助? 4475775
关于积分的说明 13929452
捐赠科研通 4371050
什么是DOI,文献DOI怎么找? 2401660
邀请新用户注册赠送积分活动 1394683
关于科研通互助平台的介绍 1366468