mlsanityData to 14 Oct 2026

BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds

arXiv 2502.10363 ↗First posted 14 Feb 2025cs.RO cs.AI cs.LGcited by 46

Not on the map. Why?

Cited by 21 in Deep reinforcement learning methods, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Traversing risky terrains with sparse footholds poses a significant challenge for humanoid robots, requiring precise foot placements and stable locomotion. Existing learning-based approaches often struggle on such complex terrains due to sparse foothold rewards and inefficient learning processes. To address these challenges, we introduce BeamDojo, a reinforcement learning (RL) framework designed for enabling agile humanoid locomotion on sparse footholds. BeamDojo begins by introducing a sampling-based foothold reward tailored for polygonal feet, along with a double critic to balancing the learning process between dense locomotion rewards and sparse foothold rewards. To encourage sufficient trial-and-error exploration, BeamDojo incorporates a two-stage RL approach: the first stage relaxes the terrain dynamics by training the humanoid on flat terrain while providing it with task-terrain perceptive observations, and the second stage fine-tunes the policy on the actual task terrain. Moreover, we implement a onboard LiDAR-based elevation map to enable real-world deployment. Extensive simulation and real-world experiments demonstrate that BeamDojo achieves efficient learning in simulation and enables agile locomotion with precise foot placement on sparse footholds in the real world, maintaining a high success rate even under significant external disturbances.

Key facts. Cited by 46 papers in the map (data through 14 Oct 2026). Builds on 49 of its 69 references that are in the map. First posted on arXiv 14 Feb 2025.

Builds on

49 of 69 references.

References · 49

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  3. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  4. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  5. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 604
  6. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 508
  7. 2022Learning robust perceptive locomotion for quadrupedal robots in the wildcited by 382
  8. 2024OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learningcited by 189
  9. 2024HumanPlus: Humanoid Shadowing and Imitation from Humanscited by 185
  10. 2021FAST-LIO2: Fast Direct LiDAR-inertial Odometrycited by 183
  11. 2022Rapid Locomotion via Reinforcement Learningcited by 168
  12. 2017Emergence of Locomotion Behaviours in Rich Environmentscited by 165
37 more
  1. 2023Extreme Parkour with Legged Robotscited by 164
  2. 2022Legged Locomotion in Challenging Terrains using Egocentric Visioncited by 151
  3. 2023Robot Parkour Learningcited by 149
  4. 2024Expressive Whole-Body Control for Humanoid Robotscited by 139
  5. 2022Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behaviorcited by 138
  6. 2024Learning Human-to-Humanoid Real-Time Whole-Body Teleoperationcited by 130
  7. 2024Humanoid Parkour Learningcited by 96
  8. 2024HOVER: Versatile Neural Whole-Body Controller for Humanoid Robotscited by 91
  9. 2021Minimizing Energy Consumption Leads to the Emergence of Gaits in Legged Robotscited by 76
  10. 2020FAST-LIO: A Fast, Robust LiDAR-inertial Odometry Package by Tightly-Coupled Iterated Kalman Filtercited by 74
  11. 2024Agile But Safe: Learning Collision-Free High-Speed Legged Locomotioncited by 73
  12. 2024Humanoid Locomotion as Next Token Predictioncited by 69
  13. 2023DreamWaQ: Learning Robust Quadrupedal Locomotion With Implicit Terrain Imagination via Deep Reinforcement Learningcited by 66
  14. 2020Dynamics Randomization Revisited:A Case Study for Quadrupedal Locomotioncited by 59
  15. 2020RLOC: Terrain-Aware Legged Locomotion using Reinforcement Learning and Optimal Controlcited by 59
  16. 2023DTC: Deep Tracking Controlcited by 56
  17. 2024Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learningcited by 56
  18. 2024Learning Humanoid Locomotion with Perceptive Internal Modelcited by 50
  19. 2021Learning to Jump from Pixelscited by 45
  20. 2023Neural Volumetric Memory for Visual Locomotion Controlcited by 44
  21. 2023Hybrid Internal Model: Learning Agile Legged Locomotion with Simulated Robot Responsecited by 39
  22. 2022Perceptive Locomotion through Nonlinear Model Predictive Controlcited by 38
  23. 2024Learning Smooth Humanoid Locomotion through Lipschitz-Constrained Policiescited by 30
  24. 2023Composite Motion Learning with Task Controlcited by 28
  25. 2024Learning Humanoid Locomotion over Challenging Terraincited by 26
  26. 2021GLiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Modelcited by 25
  27. 2024Harmon: Whole-Body Motion Generation of Humanoid Robots from Language Descriptionscited by 23
  28. 2023Learning Agile Locomotion on Risky Terrainscited by 21
  29. 2024Revisiting Reward Design and Evaluation for Robust Humanoid Standing and Walkingcited by 21
  30. 2024RobotKeyframing: Learning Locomotion with High-Level Objectives via Mixture of Dense and Sparse Rewardscited by 18
  31. 2021Reward-Adaptive Reinforcement Learning: Dynamic Policy Gradient Optimization for Bipedal Locomotioncited by 13
  32. 2020Motion Planning for Quadrupedal Locomotion: Coupled Planning, Terrain Mapping and Whole-Body Controlcited by 11
  33. 2021Receding-Horizon Perceptive Trajectory Optimization for Dynamic Legged Locomotion with Learned Initializationcited by 10
  34. 2019Footstep Planning for Autonomous Walking Over Rough Terraincited by 8
  35. 2024Walking with Terrain Reconstruction: Learning to Traverse Risky Sparse Footholdscited by 8
  36. 2024Robust Robot Walker: Learning Agile Locomotion over Tiny Trapscited by 7
  37. 2024Learning an Adaptive Fall Recovery Controller for Quadrupeds on Complex Terrainscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 24; 2026: 22.

46 papers.

Sort:

By area:

  1. 2025Visual Imitation Enables Contextual Humanoid Controlcited by 68
  2. 2025KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skillscited by 52
  3. 2025TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenizationcited by 51
  4. 2025TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection Systemcited by 44
  5. 2025WholeBodyVLA: Towards Unified Latent VLA for Whole-Body Loco-Manipulation Controlcited by 36
  6. 2025LocoFormer: Generalist Locomotion via Long-context Adaptationcited by 20
  7. 2026Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matchingcited by 19
  8. 2025PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction Systemcited by 18
  9. 2025Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfercited by 15
  10. 2026HumanX: Toward Agile and Generalizable Humanoid Interaction Skills from Human Videoscited by 14
  11. 2025KungfuBot2: Learning Versatile Motion Skills for Humanoid Whole-Body Controlcited by 13
  12. 2026Hiking in the Wild: A Scalable Perceptive Parkour Framework for Humanoidscited by 13
34 more
  1. 2025Humanoid Whole-Body Locomotion on Narrow Terrain via Dynamic Balance and Reinforcement Learningcited by 11
  2. 2025MoRE: Mixture of Residual Experts for Humanoid Lifelike Gaits Learning on Complex Terrainscited by 10
  3. 2026FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructionscited by 10
  4. 2025Towards Adaptable Humanoid Control via Adaptive Motion Trackingcited by 8
  5. 2025Multi-Loco: Unifying Multi-Embodiment Legged Locomotion via Reinforcement Learning Augmented Diffusioncited by 7
  6. 2025RoboMirror: Understand Before You Imitate for Video to Humanoid Locomotioncited by 7
  7. 2025DreamPolicy: A Unified World-model Policy for Scalable Humanoid Locomotioncited by 5
  8. 2025Gait-Adaptive Perceptive Humanoid Locomotion with Real-Time Under-Base Terrain Reconstructioncited by 5
  9. 2025Chasing Stability: Humanoid Running via Control Lyapunov Function Guided Reinforcement Learningcited by 4
  10. 2026TTT-Parkour: Rapid Test-Time Training for Perceptive Robot Parkourcited by 4
  11. 2025Contrastive Representation Learning for Robust Sim-to-Real Transfer of Adaptive Humanoid Locomotioncited by 3
  12. 2025Mastering Diverse, Unknown, and Cluttered Tracks for Robust Vision-Based Drone Racingcited by 3
  13. 2025LIPM-Guided Reinforcement Learning for Stable and Perceptive Locomotion in Bipedal Robotscited by 2
  14. 2025PolySim: Bridging the Sim-to-Real Gap for Humanoid Control via Multi-Simulator Dynamics Randomizationcited by 2
  15. 2026REFINE-DP: Diffusion Policy Fine-tuning for Humanoid Loco-manipulation via Reinforcement Learningcited by 2
  16. 2025Physics-Guided Residual Reinforcement Learning for Humanoid Narrow-Path Traversalcited by 1
  17. 2025Architecture Is All You Need: Diversity-Enabled Sweet Spots for Robust Humanoid Locomotioncited by 1
  18. 2026APEX: Learning Adaptive High-Platform Traversal for Humanoid Robotscited by 1
  19. 2026Generalizing from References using a Multi-Task Reference and Goal-Driven RL Frameworkcited by 1
  20. 2026Global-Local Attention Decomposition for Terrain Encoding in Humanoid Perceptive Locomotioncited by 1
  21. 2026Mind Your Steps: A General Learning Framework for Accurate Humanoid Foothold Trackingcited by 1
  22. 2026Trajectory-Level Automatic Curriculum Learning for Legged Locomotion on Unstructured Terraincited by 1
  23. 2025E-SDS: Environment-aware See it, Do it, Sorted - Automated Environment-Aware Reinforcement Learning for Humanoid Locomotioncited by 0
  24. 2026CMR: Contractive Mapping Embeddings for Robust Humanoid Locomotion on Unstructured Terrainscited by 0
  25. 2026PCHC: Enabling Preference Conditioned Humanoid Control via Multi-Objective Reinforcement Learningcited by 0
  26. 2026Terrain Consistent Reference-Guided RL for Humanoid Navigation Autonomycited by 0
  27. 2026CoRe-MoE: Contrastive Reweighted Mixture of Experts for Multi-Terrain Humanoid Locomotion with Gait Adaptationcited by 0
  28. 2026LadderMan: Learning Humanoid Perceptive Ladder Climbingcited by 0
  29. 2026Critic Architecture Matters: Dual vs. Unified Critics for Humanoid Loco-Manipulationcited by 0
  30. 2026TaskNPoint: How to Teach Your Humanoid to Hit a Backhand in Minutescited by 0
  31. 2026Learning Slope-Adaptive Whole-Body Locomotion for Humanoid Robots in Roofing Constructioncited by 0
  32. 2026FootQuery: Future-Touchdown-Guided Retrieval from Depth History for Perceptive Humanoid Locomotioncited by 0
  33. 2026STRIDER: Stepping-Enabled Multi-Gait Hierarchical 3D Loco-Manipulation Framework for Humanoid Robotscited by 0
  34. 2026Reusing Past Samples in Proximal Policy Optimization: When and How Does It Help?cited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Walk the PLANC: Physics-Guided RL for Agile Humanoid Locomotion on Constrained Footholds
  2. 2026MARCH: Model-Assisted Reinforcement Learning for the Perceptive Control of Humanoids over Sparse Footholds
  3. 2024Learning Generic and Dynamic Locomotion of Humanoids Across Discrete Terrains
  4. 2026AGILE: A Comprehensive Workflow for Humanoid Loco-Manipulation Learning
  5. 2026Locomotion Beyond Feet
  6. 2024Learn to Teach: Sample-Efficient Privileged Learning for Humanoid Locomotion over Diverse Terrains
  7. 2025No More Marching: Learning Humanoid Locomotion for Short-Range SE(2) Targets
  8. 2025Robust Humanoid Walking on Compliant and Uneven Terrain with Deep Reinforcement Learning