mlsanityData to 14 Oct 2026

Learning Vision-Based Bipedal Locomotion for Challenging Terrain

arXiv 2309.14594 ↗First posted 26 Sep 2023cs.ROcited by 42

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)

Reinforcement learning (RL) for bipedal locomotion has recently demonstrated robust gaits over moderate terrains using only proprioceptive sensing. However, such blind controllers will fail in environments where robots must anticipate and adapt to local terrain, which requires visual perception. In this paper, we propose a fully-learned system that allows bipedal robots to react to local terrain while maintaining commanded travel speed and direction. Our approach first trains a controller in simulation using a heightmap expressed in the robot's local frame. Next, data is collected in simulation to train a heightmap predictor, whose input is the history of depth images and robot states. We demonstrate that with appropriate domain randomization, this approach allows for successful sim-to-real transfer with no explicit pose estimation and no fine-tuning using real-world data. To the best of our knowledge, this is the first example of sim-to-real learning for vision-based bipedal locomotion over challenging terrains.

Key facts. Cited by 42 papers in the map (data through 14 Oct 2026). First posted on arXiv 26 Sep 2023.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 17; 2025: 18; 2026: 7.

42 papers.

Sort:

By area:

  1. 2024OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learningcited by 189
  2. 2024Deep Reinforcement Learning for Robotics: A Survey of Real-World Successescited by 176
  3. 2024Open-TeleVision: Teleoperation with Immersive Active Visual Feedbackcited by 145
  4. 2024Expressive Whole-Body Control for Humanoid Robotscited by 139
  5. 2024ExBody2: Advanced Expressive Humanoid Whole-Body Controlcited by 88
  6. 2024Agile But Safe: Learning Collision-Free High-Speed Legged Locomotioncited by 73
  7. 2024Visual Whole-Body Control for Legged Loco-Manipulationcited by 62
  8. 2025AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Controlcited by 51
  9. 2024Learning Smooth Humanoid Locomotion through Lipschitz-Constrained Policiescited by 30
  10. 2024CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learningcited by 23
  11. 2025LocoFormer: Generalist Locomotion via Long-context Adaptationcited by 20
  12. 2024World Model-based Perception for Visual Legged Locomotioncited by 18
30 more
  1. 2024Learning Multi-Modal Whole-Body Control for Real-World Humanoid Robotscited by 16
  2. 2024SoloParkour: Constrained Reinforcement Learning for Visual Locomotion from Privileged Experiencecited by 14
  3. 2026Hiking in the Wild: A Scalable Perceptive Parkour Framework for Humanoidscited by 13
  4. 2025Distillation-PPO: A Novel Two-Stage Reinforcement Learning Framework for Humanoid Robot Perceptive Locomotioncited by 10
  5. 2024Deep Reinforcement Learning for Bipedal Locomotion: A Brief Surveycited by 7
  6. 2024Reinforcement Learning Within the Classical Robotics Stack: A Case Study in Robot Soccercited by 7
  7. 2024Learning to Swim: Reinforcement Learning for 6-DOF Control of Thruster-driven Autonomous Underwater Vehiclescited by 6
  8. 2025Gait-Conditioned Reinforcement Learning with Multi-Phase Curriculum for Humanoid Locomotioncited by 6
  9. 2025Humanoid Occupancy: Enabling A Generalized Multimodal Occupancy Perception System on Humanoid Robotscited by 5
  10. 2025Gait-Adaptive Perceptive Humanoid Locomotion with Real-Time Under-Base Terrain Reconstructioncited by 5
  11. 2024Learning Decentralized Multi-Biped Control for Payload Transportcited by 4
  12. 2025Robot Crash Course: Learning Soft and Stylized Fallingcited by 4
  13. 2026TTT-Parkour: Rapid Test-Time Training for Perceptive Robot Parkourcited by 4
  14. 2025LocoMamba: Vision-Driven Locomotion via End-to-End Deep Reinforcement Learning with Mambacited by 3
  15. 2025No More Blind Spots: Learning Vision-Based Omnidirectional Bipedal Locomotion for Challenging Terraincited by 3
  16. 2025Contrastive Representation Learning for Robust Sim-to-Real Transfer of Adaptive Humanoid Locomotioncited by 3
  17. 2025QuadKAN: KAN-Enhanced Quadruped Motion Control via End-to-End Reinforcement Learningcited by 2
  18. 2025LIPM-Guided Reinforcement Learning for Stable and Perceptive Locomotion in Bipedal Robotscited by 2
  19. 2025MASH: Cooperative-Heterogeneous Multi-Agent Reinforcement Learning for Single Humanoid Robot Locomotioncited by 1
  20. 2025Architecture Is All You Need: Diversity-Enabled Sweet Spots for Robust Humanoid Locomotioncited by 1
  21. 2025Bi-Level Reinforcement Learning Pathway for Sim-to-Real Optimalitycited by 1
  22. 2026Global-Local Attention Decomposition for Terrain Encoding in Humanoid Perceptive Locomotioncited by 1
  23. 2024Learning Generic and Dynamic Locomotion of Humanoids Across Discrete Terrainscited by 0
  24. 2025Make Your AUV Adaptive: An Environment-Aware Reinforcement Learning Framework For Underwater Taskscited by 0
  25. 2025Vision-Proprioception Fusion with Mamba2 in End-to-End Reinforcement Learning for Motion Controlcited by 0
  26. 2025Learning Terrain Aware Bipedal Locomotion via Reduced Dimensional Perceptual Representationscited by 0
  27. 2026A Hybrid Autoencoder for Robust Heightmap Generation from Fused Lidar and Depth Data for Humanoid Robot Locomotioncited by 0
  28. 2026Efficient Unsupervised Environment Design through Hierarchical Policy Representation Learningcited by 0
  29. 2026Robot Squid Game: Quadrupedal Locomotion for Traversing Narrow Tunnelscited by 0
  30. 2026FootQuery: Future-Touchdown-Guided Retrieval from Depth History for Perceptive Humanoid Locomotioncited by 0