📡 Embodied AI Radar具身智能雷达

Labs机构 › ETH Zurich苏黎世联邦理工学院

ETH Zurich · embodied AI & robot learning苏黎世联邦理工学院 · 具身智能与机器人学习

12 curated papers, code, datasets and hardware from ETH Zurich (7 with code), with one-line takeaways.12 个来自苏黎世联邦理工学院的精选论文、代码、数据集与硬件(7 个附代码),均配一句话要点。

Labs are matched from each entry's affiliation field by simple name rules (data/labs.yaml); joint work appears under every lab named. Only curated entries are listed, because daily arXiv papers carry no affiliations.机构由每个条目的机构字段按名称规则匹配(data/labs.yaml),合作工作会出现在所有署名机构下。仅列出精选条目,因为每日 arXiv 论文不含机构信息。

By topic:按主题: Manipulation & Dexterous Hands操作与灵巧手 (2) · Tactile & Visuotactile Sensing触觉与视触觉感知 (1) · Locomotion & Humanoids运动控制与人形机器人 (8) · Navigation & Embodied Agents导航与具身智能体 (1) · Perception, SLAM & 3D Mapping感知、SLAM 与三维建图 (2) · Planning, Control & Safety规划、控制与安全 (2) · Sim-to-Real & Simulators仿真与 Sim-to-Real (2) · Datasets & Benchmarks数据集与基准 (1) · Hardware & Open-Source Robots硬件与开源机器人 (1)

Recently added最近加入

All entries全部条目 (12)

Paper论文 2021 · ETH Zurich, NVIDIA ★

Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning

Thousands of parallel GPU environments train a quadruped walking policy in minutes; legged_gym became a standard starter.数千个 GPU 并行环境几分钟就能训练出四足行走策略;legged_gym 成为标准入门框架。

BibTeX
@misc{rudin2021learning,
  title = {{Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning}},
  author = {Nikita Rudin and David Hoeller and Philipp Reist and Marco Hutter},
  year = {2021},
  eprint = {2109.11978},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2109.11978},
}
Paper论文 2026 · ETH Zurich new新 2026-10-20

Vision as Proprioception: Estimating Humanoid Robot Pose from Video

HumanoidPose recovers a humanoid's full-body joint configuration from video alone — useful when onboard state is unavailable, and for turning online robot videos into training data.HumanoidPose 仅凭视频恢复人形机器人的全身关节构型:适用于拿不到机载状态的场景,也能把网上的机器人视频变成训练数据。

BibTeX
@misc{jiang2026vision,
  title = {{Vision as Proprioception: Estimating Humanoid Robot Pose from Video}},
  author = {Jiaxi Jiang and Matthias Heyrman and René Zurbrügg and Marco Hutter and Christian Holz},
  year = {2026},
  eprint = {2610.25288},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.25288},
}
Hardware硬件 2025 · ETH Zurich

ORCA: An Open-Source, Reliable, Cost-Effective, Anthropomorphic Robotic Hand for Uninterrupted Dexterous Task Learning

A 3D-printable, 17-DoF tendon-driven hand with fingertip tactile sensing, under CHF 2,000 in materials; design files and code are open, and the paper reports long continuous runs for teleoperation and learning.可 3D 打印的 17 自由度腱驱动灵巧手,指尖带触觉传感,材料成本低于 2000 瑞士法郎;设计文件与代码开源,论文报告了可长时间连续运行用于遥操作与学习。

BibTeX
@misc{christoph2025orca,
  title = {{ORCA: An Open-Source, Reliable, Cost-Effective, Anthropomorphic Robotic Hand for Uninterrupted Dexterous Task Learning}},
  author = {Clemens C. Christoph and Maximilian Eberlein and Filippos Katsimalis and Arturo Roberti and Aristotelis Sympetheros and Michel R. Vogt and Davide Liconti and Chenyu Yang and Barnabas Gavin Cangan and Ronan J. Hinchet and Robert K. Katzschmann},
  year = {2025},
  eprint = {2504.04259},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2504.04259},
}
Paper论文 2024 · CMU, ETH Zurich RSS 2024

Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion

ABS pairs an agile RL locomotion policy with a learned reach-avoid value network and a recovery policy that takes over near obstacles, so a quadruped can run fast without crashing.ABS 将敏捷的强化学习运动策略与学习的可达-规避价值网络及恢复策略结合,接近障碍时由恢复策略接管,让四足机器人高速奔跑而不碰撞。

BibTeX
@misc{he2024agile,
  title = {{Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion}},
  author = {Tairan He and Chong Zhang and Wenli Xiao and Guanqi He and Changliu Liu and Guanya Shi},
  year = {2024},
  eprint = {2401.17583},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2401.17583},
}
Paper论文 2023 · ETH Zurich, NVIDIA

ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robots

A learned navigation policy sequences pre-trained skills (walk, jump, climb, crouch) using a learned obstacle reconstruction; reports up to 2 m/s on hardware (Science Robotics).分层的全学习系统:导航策略结合学习到的障碍物重建来调度预训练技能(行走、跳跃、攀爬、下蹲);报告实机速度可达 2 米/秒。发表于 Science Robotics。

BibTeX
@misc{hoeller2023anymal,
  title = {{ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robots}},
  author = {David Hoeller and Nikita Rudin and Dhionis Sako and Marco Hutter},
  year = {2023},
  eprint = {2306.14874},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2306.14874},
}
Locomotion & Humanoids运动控制与人形机器人Quadruped / legged四足 / 足式realquadrupedparkourhierarchicalperception
Paper论文 2023 · ETH Zurich, NVIDIA, Toronto

Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments

The framework that became Isaac Lab — modular robots, sensors and tasks on top of Isaac Sim.Isaac Lab 的前身,在 Isaac Sim 之上提供模块化的机器人、传感器与任务。

BibTeX
@misc{mittal2023orbit,
  title = {{Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments}},
  author = {Mayank Mittal and Calvin Yu and Qinxi Yu and Jingzhou Liu and Nikita Rudin and David Hoeller and Jia Lin Yuan and Ritvik Singh and Yunrong Guo and Hammad Mazhar and Ajay Mandlekar and Buck Babich and Gavriel State and Marco Hutter and Animesh Garg},
  year = {2023},
  eprint = {2301.04195},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2301.04195},
}
Sim-to-Real & Simulators仿真与 Sim-to-Realgpu-parallelframeworkopen-source
Dataset数据集 2022 · ETH Zürich · MPI for Intelligent Systems CVPR 2023

ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation

2.1M video frames of two hands manipulating articulated objects (scissors, laptops…) with accurate 3D hand and object meshes from motion capture; a reference for bimanual hand-object reconstruction.210 万帧双手操作铰接物体(剪刀、笔记本电脑等)的视频,借助动作捕捉提供精确的手与物体三维网格;双手-物体重建的常用基准。

BibTeX
@misc{fan2022arctic,
  title = {{ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation}},
  author = {Zicong Fan and Omid Taheri and Dimitrios Tzionas and Muhammed Kocabas and Manuel Kaufmann and Michael J. Black and Otmar Hilliges},
  year = {2022},
  eprint = {2204.13662},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2204.13662},
}
Paper论文 2022 · ETH Zurich, Intel Science Robotics 2022

Learning robust perceptive locomotion for quadrupedal robots in the wild

ANYmal fuses proprioception with noisy height-map perception through a learned belief encoder, and is shown hiking an alpine trail and other rough terrain.ANYmal 通过学习的信念编码器融合本体感知与带噪声的高程图感知,在高山徒步路线等复杂地形上完成行走。

BibTeX
@misc{miki2022learning,
  title = {{Learning robust perceptive locomotion for quadrupedal robots in the wild}},
  author = {Takahiro Miki and Joonho Lee and Jemin Hwangbo and Lorenz Wellhausen and Vladlen Koltun and Marco Hutter},
  year = {2022},
  eprint = {2201.08117},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2201.08117},
}
Locomotion & Humanoids运动控制与人形机器人Quadruped / legged四足 / 足式quadrupedrlperceptionrealsim-to-real
Code代码 2021 · ETH Zurich (Robotic Systems Lab)

OCS2: Optimal Control for Switched Systems

C++ toolbox for nonlinear MPC on switched systems (SLQ, DDP, SQP) with robot examples for legged robots and mobile manipulators; the base of many open-source legged MPC + whole-body control stacks.面向切换系统的非线性 MPC C++ 工具箱(SLQ、DDP、SQP),附足式机器人与移动操作臂示例;许多开源足式 MPC + 全身控制方案都基于它。

Planning, Control & Safety规划、控制与安全Locomotion & Humanoids运动控制与人形机器人Robot arm机械臂Quadruped / legged四足 / 足式Mobile robot移动机器人librarympcoptimal-controlleggedmobile-manipulation
Paper论文 2020 · ETH Zurich

Learning Quadrupedal Locomotion over Challenging Terrain

A teacher-student, proprioception-only policy that walks ANYmal over mud, snow and rubble in the wild.仅依赖本体感知的师生策略,让 ANYmal 在泥地、雪地和碎石等野外地形行走。

BibTeX
@misc{lee2020learning,
  title = {{Learning Quadrupedal Locomotion over Challenging Terrain}},
  author = {Joonho Lee and Jemin Hwangbo and Lorenz Wellhausen and Vladlen Koltun and Marco Hutter},
  year = {2020},
  eprint = {2010.11251},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2010.11251},
}
Locomotion & Humanoids运动控制与人形机器人Quadruped / legged四足 / 足式sim2realquadrupedrlproprioception
Paper论文 2020 · University of Oxford, ETH Zurich, IMT Lucca, Stanford

OSQP: An Operator Splitting Solver for Quadratic Programs

A fast, robust ADMM-based QP solver with warm starting and embedded C code generation; widely used inside MPC and whole-body controllers.基于 ADMM 的快速、鲁棒二次规划求解器,支持热启动与嵌入式 C 代码生成,广泛用于 MPC 与全身控制器。

BibTeX
@misc{stellato2017osqp,
  title = {{OSQP: An Operator Splitting Solver for Quadratic Programs}},
  author = {Bartolomeo Stellato and Goran Banjac and Paul Goulart and Alberto Bemporad and Stephen Boyd},
  year = {2017},
  eprint = {1711.08013},
  archivePrefix = {arXiv},
  primaryClass = {math.OC},
  url = {https://arxiv.org/abs/1711.08013},
}
Planning, Control & Safety规划、控制与安全optimizationqp-solvermpcopen-source
Paper论文 2019 · ETH Zurich

Learning Agile and Dynamic Motor Skills for Legged Robots

A learned actuator model closes the sim-to-real gap so RL policies run and recover from falls on ANYmal.学习的执行器模型缩小仿真与现实差距,使强化学习策略能让 ANYmal 奔跑并摔倒后起身。

BibTeX
@misc{hwangbo2019learning,
  title = {{Learning Agile and Dynamic Motor Skills for Legged Robots}},
  author = {Jemin Hwangbo and Joonho Lee and Alexey Dosovitskiy and Dario Bellicoso and Vassilios Tsounis and Vladlen Koltun and Marco Hutter},
  year = {2019},
  eprint = {1901.08652},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/1901.08652},
}
Locomotion & Humanoids运动控制与人形机器人Quadruped / legged四足 / 足式sim2realquadrupedrlactuator-net