awesome-humanoid-learning

A curated list of resources relevant to humanoid robots learning.

Given the similarities between the locomotion of humanoid robots and bipedal robots, we have included some works on bipedal locomotion for reference.

Robot models

Bipeds

Name	Maker	Formats	License	Meshes	Inertias	Collisions
Bolt	ODRI	URDF	BSD-3-Clause	✔️	✔️	✔️
Cassie (MJCF)	Agility Robotics	MJCF	MIT	✔️	✔️	✔️
Cassie (URDF)	Agility Robotics	URDF	MIT	✔️	✔️	✔️
Spryped	Benjamin Bokser	URDF	GPL-3.0	✔️	✔️	✔️
Upkie	Tast's Robots	URDF	Apache-2.0	✔️	✔️	✔️
Hector	USC DRCL	URDF	BSD-3-Clause	✔️	✔️	✔️

Humanoids

Name	Maker	Formats	License	Meshes	Inertias	Collisions
Atlas DRC (v3)	Boston Dynamics	URDF	BSD-3-Clause	✔️	✔️	✔️
Atlas v4	Boston Dynamics	URDF	MIT	✔️	✔️	✔️
Digit	Agility Robotics	URDF	✖️	✔️	✔️	✔️
iCub	IIT	URDF	CC-BY-SA-4.0	✔️	✔️	✔️
JAXON	JSK	COLLADA, URDF, VRML	CC-BY-SA-4.0	✔️	✔️	✔️
JVRC-1	AIST	MJCF, URDF	BSD-2-Clause	✔️	✔️	✔️
NAO	SoftBank Robotics	URDF, Xacro	BSD-3-Clause	➖	✔️	✔️
Robonaut 2	NASA JSC Robotics	URDF	NASA-1.3	✔️	✔️	✔️
Romeo	Aldebaran Robotics	URDF	BSD-3-Clause	✔️	✔️	✔️
SigmaBan	Rhoban	URDF	MIT	✔️	✔️	✔️
TALOS	PAL Robotics	URDF	LGPL-3.0	✔️	✔️	✔️
Valkyrie	NASA JSC Robotics	URDF, Xacro	NASA-1.3	✔️	✔️	✔️
WALK-MAN	IIT	Xacro	BSD-3-Clause	✔️	✔️	✔️
H1	Unitree	URDF & MJCF	BSD-3-Clause	✔️	✔️	✔️

News

[20240417] All New Atlas | Boston Dynamics [YouTube | IEEE SPECTRUM]
[20240416] Farewell to HD Atlas 😢❤️ For almost a decade, Atlas has sparked our imagination, inspired the next generations of roboticists, and leapt over technical barriers in the field. ❤️ [YouTube]
[20240408] Sanctuary AI - Phoenix at Human-Equivalent Speed [YouTube]
[20240320] Unitree H1 The World's First Full-size Motor Drive Humanoid Robot Flips on Ground! AWESOME! [YouTube]
[20240318] NVIDIA showcase the intelligent future of humanoid robots at GTC 2024 and announce a new project called GR00T [project | video1 | video2]
[20240306] Robot Era releases their humanoid reinforcement sim2real code! [project | Code]
[20240302] Unitree H1 Breaking humanoid robot speed world record [full-size humanoid] Evolution V3.0 [YouTube]
[20240229] PNDbotics announces their humanoid robot 'Adam' [project | paper | YouTube]
[20240119] Figure announces commercial agreement with BMW Manufacturing to bring general purpose robots into automotive production [PR Newswire | YouTube]
[20240116] Tesla Optimus Bot Folds Laundry [ X | YouTube ]

Papers

2024

[2024] Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer [paper][code]
[2024] Humanoid Robots at work: where are we ? [Survey] [paper]
[2024] Diffusing in Someone Else's Shoes: Robotic Perspective Taking with Diffusion [Manipulation] [paper]
[2024] Large Language Models for Orchestrating Bimanual Robots [Manipulation] [paper]
[2024] Humanoid Locomotion as Next Token Prediction [paper]
[2024] HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation [benchmark] [project] [paper] [code]
[2024] Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation [paper] [video]
[2024] Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control [paper] [video]
[2024] Whole-body Humanoid Robot Locomotion with Human Reference [imitation] [project] [paper] [video]
[2024] Expressive Whole-Body Control for Humanoid Robots [imitation] [project] [paper]

2023

[Nature-Machine-Intelligence] Hierarchical generative modelling for autonomous robots [paper]
[ICRA] Optimizing Bipedal Locomotion for The 100m Dash With Comparison to Human Running. [paper]
[2023] Learning Vision-Based Bipedal Locomotion for Challenging Terrain. [paper]
[IROS] Development of a Whole-body Work Imitation Learning System by a Biped and Bi-armed Humanoid [paper] [project]
[2023] Learning Bipedal Walking for Humanoids with Current Feedback. [paper] [code]
[2023] Learning Humanoid Locomotion with Transformers. [paper]
[Humanoid] Deep Imitation Learning for Humanoid Loco-manipulation through Human Teleoperation [imitation] [paper] [project] [code]
[ICRA] Benchmarking Potential Based Rewards for Learning Humanoid Locomotion. [paper]
[IEEE-RAL] Learning Complex Motor Skills for Legged Robot Fall Recovery. [paper]

2022

[2022] MoCapAct: A Multi-Task Dataset for Simulated Humanoid Control. [imitation] [paper] [project]
[2022] Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviors. [imitation] [paper]
[2022] NeRF2Real: Sim2real Transfer of Vision-guided Bipedal Motion Skills using Neural Radiance Fields. [paper]
[2022] Learning Bipedal Walking On Planned Footsteps For Humanoid Robots. [paper] [code]
[2022] Dynamic Bipedal Maneuvers through Sim-to-Real Reinforcement Learning. [paper]
[2022] Sim-to-Real Learning of Compliant Bipedal Locomotion on Torque Sensor-Less Gear-Driven Humanoid. [paper]
[PMLR] Towards Real Robot Learning in the Wild: A Case Study in Bipedal Locomotion. [paper]
[PMLR] Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning. [platform] [paper] [code]
[ICRA] Sim-to-Real Learning of Footstep-Constrained Bipedal Dynamic Walking. [paper]
[ACM GRAPH] ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters [paper]
[ICMA] Custom Sine Waves Are Enough for Imitation Learning of Bipedal Gaits with Different Styles. [paper]
[Machines] Deep Reinforcement Learning for Model Predictive Controller Based on Disturbed Single Rigid Body Model of Biped Robots. [paper]
[IEEE-RAS] Improving Sample Efficiency of Deep Reinforcement Learning for Bipedal Walking. [paper] [code]
[IEEE-RAS] Dynamic Bipedal Turning through Sim-to-Real Reinforcement Learning. [paper]
[IEEE-RAS] Learning Bipedal Walking On Planned Footsteps For Humanoid Robots. [paper] [code]
[TCAS-II] Parallel Deep Reinforcement Learning Method for Gait Control of Biped Robot. [paper]
[IEEE-RAL] Linear Policies are Sufficient to Realize Robust Bipedal Walking on Challenging Terrains. [paper]

2021

[2021] Pushing the Limits: Running at 3.2m/s on Cassie. [sim2real][paper]
[ICRA] Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots. [sim2real] [paper]
[ICRA] Sim-to-Real Learning of All Common Bipedal Gaits via Periodic Reward Composition. [paper]
[ICRA] Deepwalk: Omnidirectional bipedal gait by deep reinforcement learning. [paper]
[IROS] Robust Feedback Motion Policy Design Using Reinforcement Learning on a 3D Digit Bipedal Robot. [paper]
[RSS] Blind Bipedal Stair Traversal via Sim-to-Real Reinforcement Learning. [paper]
[ICRA] Learning Task Space Actions for Bipedal Locomotion [paper]

2020

[RSS] Learning Memory-Based Control for Human-Scale Bipedal Locomotion. [sim2real] [paper] [unofficial_code]
[PMLR] Learning Locomotion Skills for Cassie: Iterative Design and Sim-to-Real. [paper]
[IEEE-RAL] Learning Natural Locomotion Behaviors for Humanoid Robots Using Human Bias. [paper]
[3DV] Grasping Field: Learning Implicit Representations for Human Grasps [paper]

2019

[IROS] Sim-to-Real Transfer for Biped Locomotion. [paper]
[SIG GRAPH] Catch & Carry: Reusable Neural Controllers for Vision-Guided Whole-Body Tasks [paper]
[Science Robotics] Learning Agile and Dynamic Motor Skills for Legged Robots. [paper] [code]

2018

[IEEE RAS] Learning Whole-body Motor Skills for Humanoids. [paper]

duanyiqun/awesome-humanoid-learning