Basic Info. This repo collects academic papers about humanoid robot learning. They are mainly categorized by the tasks they focus on. The papers with real robot experiments are preferred in this list. The papers with open-sourced code are added with a starπ.
Feel free to pull a request for new papers/codes about humanoid robot learning.
- arXiv 2025.08, A Whole-Body Motion Imitation Framework from Human Data for Full-Size Humanoid Robot
- arXiv 2025.07, EMP: Executable Motion Prior for Humanoid Robot Standing Upper-body Motion Imitation
- arXiv 2025.07, UniTracker: Learning Universal Whole-Body Motion Tracker for Humanoid Robots
- arXiv 2025.07, ULC: A Unified and Fine-Grained Controller for Humanoid Loco-Manipulation, website
- arXiv 2025.06, LeVERB: Humanoid Whole-Body Control with Latent Vision-Language Instruction, website
- arXiv 2025.06, General Motion Tracking for Humanoid Whole-Body Control, website
- arXiv 2025.06, KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills, website
- arXiv 2025.06, SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill Blending
- arXiv 2025.06, CLONE: Holistic Closed-Loop Whole-Body Teleoperation for Long-Horizon Humanoid Control, website
- arXiv 2025.05, TWIST: Teleoperated Whole-Body Imitation System
- arXiv 2025.05, Learning Gentle Humanoid Locomotion and End-Effector Stabilization Control
- arXiv 2025.05, Mobi-Ο: Mobilizing Your Robot Learning Policy, website
- arXiv 2025.05, Unleashing Humanoid Reaching Potential via Real-world-Ready Skill Space
- arXiv 2025.05, HuB: Learning Extreme Humanoid Balance, website,
- arXiv 2025.05, FALCON: Learning Force-Adaptive Humanoid Loco-Manipulation, website
- arXiv 2025.05, PyRoki: A Modular Toolkit for Robot Kinematic Optimization, website
- arXiv 2025.05, AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control, website
- arXiv 2025.04, Physically Consistent Humanoid Loco-Manipulation using Latent Diffusion Models
- arXiv 2025.04, LangWBC: Language-directed Humanoid Whole-Body Control via End-to-end Learning
- arXiv 2025.04, Adversarial Locomotion and Motion Imitation for Humanoid Policy Learning, website
- arXiv 2025.03, Being-0: A Humanoid Robotic Agent with Vision-Language Models and Modular Skills, website
- π arXiv 2025.03, BEHAVIOR Robot Suite: Streamlining Real-World Whole-Body Manipulation for Everyday Household Activities, websie
- arXiv 2025.03, Whole-Body Model-Predictive Control of Legged Robots with MuJoCo
- arXiv 2025.02, HiFAR: Multi-Stage Curriculum Learning for High-Dynamics Humanoid Fall Recovery
- π arXiv 2025.02, HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit, website / github
- arXiv 2025.02, Learning Getting-Up Policies for Real-World Humanoid Robots, website
- arXiv 2025.02, Learning Humanoid Standing-up Control across Diverse Postures
- arXiv 2025.02, HugWBC: A Unified and General Humanoid Whole-Body Controller for Fine-Grained Locomotion, website
- arXiv 2025.02, SPARK: A Toolbox for Safe Humanoid Autonomy and Teleoperation, website
- arXiv 2025.02, ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills, website
- arXiv 2025.02, Embrace Collisions: Humanoid Shadowing for Deployable Contact-Agnostics Motions, website
- arXiv 2024.12, Human-Humanoid Robots Cross-Embodiment Behavior-Skill Transfer Using Decomposed Adversarial Learning from Demonstration
- arXiv 2024.12, Learning from Massive Human Videos for Universal Humanoid Pose Control, website
- arXiv 2024.12, ExBody2: Advanced Expressive Humanoid Whole-Body Control, website
- arXiv 2024.12, Mobile-TeleVision: Predictive Motion Priors for Humanoid Whole-Body Control, website
- arXiv 2024.11, A Behavior Architecture for Fast Humanoid Robot Door Traversals, video
- arXiv 2024.11, The Role of Domain Randomization in Training Diffusion Policies for Whole-Body Humanoid Control
- arXiv 2024.10, EMOTION: Expressive Motion Sequence Generation for Humanoid Robots with In-Context Learning
- arXiv 2024.10, HOVER: Versatile Neural Whole-Body Controller for Humanoid Robots, website
- arXiv 2024.10, Harmon: Whole-Body Motion Generation of Humanoid Robots from Language Descriptions, website
- arXiv 2024.10, Whole-Body Dynamic Throwing with Legged Manipulators
- arXiv 2024.09, Opt2Skill: Imitating Dynamically-feasible Whole-Body Trajectories for Versatile Humanoid Loco-Manipulation, Website
- 2024.08, VMP: Versatile Motion Priors for Robustly Tracking Motion on Physical Characters, website
- 2024.07, Robot Motion Diffusion Model: Motion Generation for Robotic Characters,
- arXiv 2024.07, Flow Multi-Support: Flow Matching Imitation Learning for Multi-Support Manipulation, video / website
- arXiv 2024.06, HYPERmotion: Learning Hybrid Behavior Planning for Autonomous Loco-manipulation, website
- π arXiv 2024.06, HumanPlus: Humanoid Shadowing and Imitation from Humans, website / code
- arXiv 2024.06, WoCoCo: Learning Whole-Body Humanoid Control with Sequential Contacts, website
- π arXiv 2024.06, OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning, website / code
- π arXiv 2024.03, Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation, website / code
- π arXiv 2024.02, Expressive Whole-Body Control for Humanoid Robots, website / code
- arXiv 2023.10, Sim-to-Real Learning for Humanoid Box Loco-Manipulation
- arXiv 2025.07, H-RDT: Human Manipulation Enhanced Bimanual Robotic Manipulation
- arXiv 2025.07, Robot Drummer: Learning Rhythmic Skills for Humanoid Drumming
- arXiv 2025.07, EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos, website
- arXiv 2025.06, Vision in Action: Learning Active Perception from Human Demonstrations
- arXiv 2025.05, DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation, website
- arXiv 2025.05, EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video
- arXiv 2025.05, DreamGen: Unlocking Generalization in Robot Learning through Neural Trajectories
- arXiv 2025.03, Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation, website
- arXiv 2025.03, GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- arXiv 2025.03, Humanoids in Hospitals: A Technical Study of Humanoid Surrogates for Dexterous Medical Interventions
- arXiv 2025.03, Humanoid Policy ~ Human Policy, website
- arXiv 2025.02, Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids, website
- arXiv 2025.02, Dexterous Safe Control for Humanoids in Cluttered Environments via Projected Safe Set Algorithm
- arXiv 2025.01, MobileH2R: Learning Generalizable Human to Mobile Robot Handover Exclusively from Scalable and Diverse Synthetic Data
- arXiv 2024.12, ARMADA: Augmented Reality for Robot Manipulation and Robot-Free Data Acquisition, website
- arXiv 2024.12, ARMOR: Egocentric Perception for Humanoid Robot Collision Avoidance and Motion Planning
- arXiv 2024.11, Object-Centric Dexterous Manipulation from Human Motion Data, website
- arXiv 2024.11, DexHub and DART: Towards Internet-Scale Robot Data Collection, website
- arXiv 2024.11, Learning to Look Around: Enhancing Teleoperation and Learning with a Human-like Actuated Neck
- π arXiv 2024.10, Generalizable Humanoid Manipulation with Improved 3D Diffusion Policies, website / code
- π arXiv 2024.10, EgoMimic: Scaling Imitation Learning via Egocentric Video, website / code
- arXiv 2024.10, Learning to Look: Seeking Information for Decision Making via Policy Factorization, website
- arXiv 2024.10, OKAMI: Teaching Humanoid Robots Manipulation Skills through Single Video Imitation, website
- 2024.09, Bimanual Dexterity for Complex Tasks, website
- π arXiv 2024.08, ACE: A Cross-Platform Visual-Exoskeletons System for Low-Cost Dexterous Teleoperation, website / code
- π arXiv 2024.07, Open-TeleVision: Teleoperation with Immersive Active Visual Feedback, website / code
- π arXiv 2024.07, Bunny-VisionPro: Real-Time Bimanual Dexterous Teleoperation for Imitation Learning, website / code
- π arXiv 2024.04, Learning Visuotactile Skills with Two Multifingered Hands, website / code
- π arXiv 2024.03, DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation, website / code
- 1999, Is imitation learning the route to humanoid robots?
- arXiv 2025.08, CHILD: Controller for Humanoid Imitation and Live Demonstration a Whole-Body Humanoid Teleoperation System, website
- arXiv 2025.05, Heavy lifting tasks via haptic teleoperation of a wheeled humanoid
- arXiv 2025.05, TWIST: Teleoperated Whole-Body Imitation System
- arXiv 2025.05, TeleOpBench: A Simulator-Centric Benchmark for Dual-Arm Dexterous Teleoperation, website
- π arXiv 2025.02, HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit, code
- arXiv 2024.12, Mobile-TeleVision: Predictive Motion Priors for Humanoid Whole-Body Control
- π arXiv 2024.10, Generalizable Humanoid Manipulation with 3D Diffusion Policies, website / code
- π arXiv 2024.08, ACE: A Cross-Platform Visual-Exoskeletons System for Low-Cost Dexterous Teleoperation, website / code
- π arXiv 2024.07, Bunny-VisionPro: Real-Time Bimanual Dexterous Teleoperation for Imitation Learning, website / code
- π arXiv 2024.07, Open-TeleVision: Teleoperation with Immersive Active Visual Feedback, website / code
- π arXiv 2024.06, HumanPlus: Humanoid Shadowing and Imitation from Humans, website / code
- π arXiv 2024.06, OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning, website / code
- arXiv 2024.03, Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation, website
- π arXiv 2023.09, Deep Imitation Learning for Humanoid Loco-manipulation through Human Teleoperation, website / code
- arXiv 2023.01, Teleoperation of Humanoid Robots: A Survey, webpage
- arXiv 2022.03, iCub3 Avatar System: Enabling Remote Fully-Immersive Embodiment of Humanoid Robots, Science Robotics / github
- arXiv 2025.08, Optimizing Bipedal Locomotion for The 100m Dash With Comparison to Human Running
- arXiv 2025.08, Hand-Eye Autonomous Delivery: Learning Humanoid Navigation, Locomotion and Reaching
- arXiv 2025.08, Coordinated Humanoid Robot Locomotion with Symmetry Equivariant Reinforcement Learning Policy
- arXiv 2025.07, Humanoid Occupancy: Enabling A Generalized Multimodal Occupancy Perception System on Humanoid Robots
- arXiv 2025.07, LOVON: Legged Open-Vocabulary Object Navigator, website
- arXiv 2025.06, MoRE: Mixture of Residual Experts for Humanoid Lifelike Gaits Learning on Complex Terrains, website
- arXiv 2025.05, FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control, website
- arXiv 2025.05, VideoMimic: Visual imitation enables contextual humanoid control, website
- arXiv 2025.05, Dribble Master: Learning Agile Humanoid Dribbling Through Legged Locomotion
- arXiv 2025.05, NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidance
- arXiv 2025.03, HWC-Loco: A Hierarchical Whole-Body Control Approach to Robust Humanoid Locomotion, website
- arXiv 2025.03, HumanoidPano: Hybrid Spherical Panoramic-LiDAR Cross-Modal Perception for Humanoid Robots
- arXiv 2025.03, Natural Humanoid Robot Locomotion with Generative Motion Prior
- arXiv 2025.03, Learning Perceptive Humanoid Locomotion over Challenging Terrain
- arXiv 2025.02, Learning Humanoid Locomotion with World Model Reconstruction
- arXiv 2025.02, Humanoid Whole-Body Locomotion on Narrow Terrain via Dynamic Balance and Reinforcement Learning
- arXiv 2025.02, VB-Com: Learning Vision-Blind Composite Humanoid Locomotion Against Deficient Perception, website
- arXiv 2025.02, BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds, website
- arXiv 2024.12, NaVILA: Legged Robot Vision-Language-Action Model for Navigation, website
- arXiv 2024.11, Learning Humanoid Locomotion with Perceptive Internal Model
- π arXiv 2024.11, Real-Time Polygonal Semantic Mapping for Humanoid Robot Stair Climbing, code
- π arXiv 2024.10, Learning Smooth Humanoid Locomotion through Lipschitz-Constrained Policies, website / code
- arXiv 2024.10, Learning Humanoid Locomotion over Challenging Terrain, website
- 2024.10, Adapting Humanoid Locomotion over Challenging Terrain via Two-Phase Training, website
- 2024.10, Bi-Level Motion Imitation for Humanoid Robots, website
- arXiv 2024.08, Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning
- arXiv 2024.06, Humanoid Parkour Learning, website
- arXiv 2024.02, Humanoid Locomotion as Next Token Prediction, website
- arXiv 2024.02, Whole-body Humanoid Robot Locomotion with Human Reference, website
- arXiv 2024.01, Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control
- arXiv 2023.09, Learning to Walk and Fly with Adversarial Motion Priors
- arXiv 2023.07, Benchmarking Potential Based Rewards for Learning Humanoid Locomotion,
- arXiv 2023.03, Real-World Humanoid Locomotion with Reinforcement Learning, website
- arXiv 2023.02, Robust and Versatile Bipedal Jumping Control through Reinforcement Learning
- arXiv 2025.02, Bridging the Sim-to-Real Gap for Athletic Loco-Manipulation
- arXiv 2019.01, Learning Agile and Dynamic Motor Skills for Legged Robots
- arXiv:2025.05, Sampling-Based System Identification with Active Exploration for Legged Robot Sim2Real Learning
- arXiv 2025.06, iRonCub 3: The Jet-Powered Flying Humanoid Robot
- arXiv 2025.04, Berkeley Humanoid Lite: An Open-source, Accessible, and Customizable 3D-printed Humanoid Robot, website
- arXiv 2025.04, RUKA: Rethinking the Design of Humanoid Hands with Learning, website
- arXiv 2025.04, ORCA: Open-Source, Reliable, Cost-Effective, Anthropomorphic Robotic Hand for Uninterrupted Dexterous Task Learning, website
- arXiv 2025.03, Control of Humanoid Robots with Parallel Mechanisms using Kinematic Actuation Models
- π arXiv 2025.02, ToddlerBot: Open-Source ML-Compatible Humanoid Platform for Loco-Manipulation, website / github
- arXiv 2025.01, Design and Control of a Bipedal Robotic Character
- 2024.11, Zeroth Bot, Github
- π arXiv 2024.09, The Duke Humanoid: Design and Control For Energy Efficient Bipedal Locomotion Using Passive Dynamics, website / code
- π arXiv 2024.07, Berkeley Humanoid: A Research Platform for Learning-based Control, website / code
- 2024.07, Design and Control of a Bipedal Robotic Character, youtube
- arXiv 2021.04, The MIT Humanoid Robot: Design, Motion Planning, and Control For Acrobatic Behaviors
- arXiv 2019.04, Quasi-Direct Drive for Low-Cost Compliant Robotic Manipulation, website
- π arXiv 2025.07, HumanoidGen: Data Generation for Bimanual Dexterous Manipulation via LLM Reasoning, website
- π 2025.01, MuJoCo Playground, github / website
- arXiv 2024.12, Mimicking-Bench: A Benchmark for Generalizable Humanoid-Scene Interaction Learning via Human Mimicking, website
- π arXiv 2024.12, ManiSkill-HAB: A Benchmark for Low-Level Manipulation in Home Rearrangement Tasks, website
- arXiv 2024.12, Genesis: A Generative and Universal Physics Engine for Robotics and Beyond, code / website
- arXiv 2024.10, DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learning, website
- π arXiv 2024.10, ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI, website / code
- π arXiv 2024.07, BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark, website / code
- π arXiv, GRUtopia: Dream General Robots in a City at Scale, website
- π arXiv 2024.06, RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots, website / code
- π arXiv 2024.04, Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer, website / code
- π arXiv 2024.03, HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation, website / code
- arXiv 2025.07, Feature-Based vs. GAN-Based Learning from Demonstrations: When and Why
- arXiv 2025.05, AMOR: Adaptive Character Control through Multi-Objective Reinforcement Learning
- arXiv 2025.05, MaskedManipulator: Versatile Whole-Body Control for Loco-Manipulation
- arXiv 2025.05, Emergent Active Perception and Dexterity of Simulated Humanoids from Visual Reinforcement Learning, website
- arXiv 2025.05, ADD: Physics-Based Motion Imitation with Adversarial Differential Discriminators
- SIGGRAPH 2025, PARC: Physics-based Augmentation with Reinforcement Learning for Character Controllers, website
- arXiv 2025.04, Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models
- π arXiv 2025.03 / CVPR 2025 Oral, TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization, website
- π arXiv 2025.02, InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions, website, code
- arXib 2024.10, CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control, website
- π arXiv 2024.09, MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting, website
- arXiv 2024.08, SkillMimic: Learning Basketball Interaction Skills from Demonstrations
- arXiv 2023.06, Hierarchical Planning and Control for Box Loco-Manipulation
- TOG 2023, AdaptNet: Policy Adaptation for Physics-Based Character Control
- TOG 2023, Composite Motion Learning with Task Control
- π arXiv 2023.09, Unified Human-Scene Interaction via Prompted Chain-of-Contacts, website
- π arXiv 2023.05, Perpetual Humanoid Control for Real-time Simulated Avatars, code
- π arXiv 2022.08, ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters, website / code
- π arXiv 2021.08, AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control, website / code
- arXiv 2018.11, Hierarchical visuomotor control of humanoids
- arXiv 2018.09, Multi-task Deep Reinforcement Learning with PopArt
- π arXiv 2018.08, DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills, website / code
- arXiv 2025.07, Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data, website
- arXiv 2025.05, GENMO: A GENeralist Model for Human MOtion, website
- arXiv 2025.03, FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video, website
- arXiv 2025.04, HUMOTO: A 4D Dataset of Mocap Human Object Interactions, website
- arXiv 2025.04, Climber Force and Motion Estimation from Video, website
- arXiv 2025.03, ClimbingCap: Multi-Modal Dataset and Method for Rock Climbing in World Coordinate
- arXiv 2024.10, Scaling Large Motion Models with Million-Level Human Motions
- arXiv 2024.04, Taming Diffusion Probabilistic Models for Character Control
- arXiv 2023.07, TEDi: Temporally-Entangled Diffusion for Long-Term Motion Synthesis
- arXiv 2023.06, Example-based Motion Synthesis via Generative Motion Matching
- arXiv 2022.12, PhysDiff: Physics-Guided Human Motion Diffusion Model, website
- CVPR 2022, Generating Diverse and Natural 3D Human Motions From Text
If you have questions/suggestions, feel free to email Yanjie Ze.