mlsanityData to 7 Oct 2026

Robot Parkour Learning

arXiv 2309.05665 ↗First posted 11 Sep 2023cs.RO cs.AI cs.CVcited by 115

Not on the map. Why?

Abstract (arXiv)

Parkour is a grand challenge for legged locomotion that requires robots to overcome various obstacles rapidly in complex environments. Existing methods can generate either diverse but blind locomotion skills or vision-based but specialized skills by using reference animal data or complex rewards. However, autonomous parkour requires robots to learn generalizable skills that are both vision-based and diverse to perceive and react to various scenarios. In this work, we propose a system for learning a single end-to-end vision-based parkour policy of diverse parkour skills using a simple reward without any reference motion data. We develop a reinforcement learning method inspired by direct collocation to generate parkour skills, including climbing over high obstacles, leaping over large gaps, crawling beneath low barriers, squeezing through thin slits, and running. We distill these skills into a single vision-based parkour policy and transfer it to a quadrupedal robot using its egocentric depth camera. We demonstrate that our system can empower two different low-cost robots to autonomously select and execute appropriate parkour skills to traverse challenging real-world environments.

Key facts. Cited by 115 papers in the map (data through 7 Oct 2026). Builds on 71 of its 125 references that are in the map. First posted on arXiv 11 Sep 2023.

Builds on

71 of 125 references.

References · 71

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  3. 2018Exploration by Random Network Distillationcited by 966
  4. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 882
  5. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 494
  6. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 430
  7. 2019Learning agile and dynamic motor skills for legged robotscited by 402
  8. 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 395
  9. 2019Learning by Cheatingcited by 361
  10. 2022Learning robust perceptive locomotion for quadrupedal robots in the wildcited by 299
  11. 2018Sim-to-Real: Learning Agile Locomotion For Quadruped Robotscited by 277
  12. 2018Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learningcited by 270
38 more
  1. 2020Learning Agile Robotic Locomotion Skills by Imitating Animalscited by 229
  2. 2018Learning to Walk via Deep Reinforcement Learningcited by 153
  3. 2022Legged Locomotion in Challenging Terrains using Egocentric Visioncited by 131
  4. 2022Rapid Locomotion via Reinforcement Learningcited by 130
  5. 2023Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learningcited by 111
  6. 2020Learning to Walk in the Real World with Minimal Human Effortcited by 103
  7. 2022Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotioncited by 98
  8. 2021Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robotscited by 95
  9. 2021Blind Bipedal Stair Traversal via Sim-to-Real Reinforcement Learningcited by 73
  10. 2021Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformerscited by 71
  11. 2021Minimizing Energy Consumption Leads to the Emergence of Gaits in Legged Robotscited by 67
  12. 2021Legged Robots that Keep on Learning: Fine-Tuning Locomotion Policies in the Real Worldcited by 64
  13. 2020Multi-expert learning of adaptive legged locomotioncited by 62
  14. 2022Concurrent Training of a Control Policy and a State Estimator for Dynamic and Robust Legged Locomotioncited by 61
  15. 2020Dynamics Randomization Revisited:A Case Study for Quadrupedal Locomotioncited by 54
  16. 2019Sim-to-Real Transfer for Biped Locomotioncited by 50
  17. 2021Fast and Efficient Locomotion via Learned Gait Transitionscited by 50
  18. 2021Coupling Vision and Proprioception for Navigation of Legged Robotscited by 46
  19. 2019DeepGait: Planning and Control of Quadrupedal Gaits using Deep Reinforcement Learningcited by 45
  20. 2020Rapidly Adaptable Legged Robots via Evolutionary Meta-Learningcited by 42
  21. 2023Neural Volumetric Memory for Visual Locomotion Controlcited by 40
  22. 2021Learning to Jump from Pixelscited by 39
  23. 2022Advanced Skills by Learning Locomotion and Local Navigation End-to-Endcited by 39
  24. 2023DribbleBot: Dynamic Legged Manipulation in the Wildcited by 33
  25. 2023Barkour: Benchmarking Animal-level Agility with Quadruped Robotscited by 33
  26. 2022Combining Learning-based Locomotion Policy with Model-based Manipulation for Legged Mobile Manipulatorscited by 32
  27. 2022Hierarchical Reinforcement Learning for Precise Soccer Shooting Skills using a Quadrupedal Robotcited by 32
  28. 2022Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrationscited by 30
  29. 2023Legs as Manipulator: Pushing Quadrupedal Agility Beyond Locomotioncited by 30
  30. 2021VILENS: Visual, Inertial, Lidar, and Leg Odometry for All-Terrain Legged Robotscited by 25
  31. 2022Learning to Grasp the Ungraspable with Emergent Extrinsic Dexteritycited by 25
  32. 2023Learning and Adapting Agile Locomotion Skills by Transferring Experiencecited by 25
  33. 2022Learning Visual Locomotion with Cross-Modal Supervisioncited by 23
  34. 2020Learning a Contact-Adaptive Controller for Robust, Efficient Legged Locomotioncited by 22
  35. 2023Event-based Agile Object Catching with a Quadrupedal Robotcited by 21
  36. 2017Learning Ground Traversability from Simulationscited by 20
  37. 2020From Pixels to Legs: Hierarchical Learning of Quadruped Locomotioncited by 20
  38. 2023Learning Arm-Assisted Fall Damage Reduction and Recovery for Legged Mobile Manipulatorscited by 20

50 most cited of 71 All 71 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 45; 2025: 37; 2026: 27.

115 papers.

Sort:

By area:

  1. 2023RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulationcited by 206
  2. 2025ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policycited by 139
  3. 2024Open-TeleVision: Teleoperation with Immersive Active Visual Feedbackcited by 137
  4. 2023Extreme Parkour with Legged Robotscited by 120
  5. 2024Expressive Whole-Body Control for Humanoid Robotscited by 117
  6. 2024HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulationcited by 101
  7. 2024SplatSim: Zero-Shot Sim2Real Transfer of RGB Manipulation Policies Using Gaussian Splattingcited by 63
  8. 2024Visual Whole-Body Control for Legged Loco-Manipulationcited by 58
  9. 2024Agile But Safe: Learning Collision-Free High-Speed Legged Locomotioncited by 53
  10. 2024TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correctioncited by 50
  11. 2025AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Controlcited by 47
  12. 2023Prompt a Robot to Walk with Large Language Modelscited by 44
38 more
  1. 2024One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotioncited by 34
  2. 2025BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholdscited by 32
  3. 2023Hybrid Internal Model: Learning Agile Legged Locomotion with Simulated Robot Responsecited by 31
  4. 2024EgoGen: An Egocentric Synthetic Data Generatorcited by 27
  5. 2024Body Transformer: Leveraging Robot Embodiment for Policy Learningcited by 26
  6. 2024Bootstrapping Reinforcement Learning with Imitation for Vision-Based Agile Flightcited by 22
  7. 2024Learning Quadruped Locomotion Using Differentiable Simulationcited by 22
  8. 2024Local Policies Enable Zero-shot Long-horizon Manipulationcited by 21
  9. 2025VR-Robo: A Real-to-Sim-to-Real Framework for Visual Robot Navigation and Locomotioncited by 20
  10. 2024Learning Force Control for Legged Manipulationcited by 19
  11. 2024Neural MP: A Generalist Neural Motion Plannercited by 18
  12. 2023Generalized Animal Imitator: Agile Locomotion with Versatile Motion Priorcited by 17
  13. 2024Real-Time Simulated Avatar from Head-Mounted Sensorscited by 17
  14. 2024World Model-based Perception for Visual Legged Locomotioncited by 17
  15. 2025MoE-Loco: Mixture of Experts for Multitask Locomotioncited by 17
  16. 2025Learning coordinated badminton skills for legged manipulatorscited by 16
  17. 2024Learning Visual Quadrupedal Loco-Manipulation from Demonstrationscited by 15
  18. 2024Commonsense Reasoning for Legged Robot Adaptation with Vision-Language Modelscited by 15
  19. 2024Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learningcited by 14
  20. 2024Eurekaverse: Environment Curriculum Generation via Large Language Modelscited by 14
  21. 2025LocoFormer: Generalist Locomotion via Long-context Adaptationcited by 14
  22. 2025DreamControl: Human-Inspired Whole-Body Humanoid Control for Scene Interaction via Guided Diffusioncited by 13
  23. 2026Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matchingcited by 13
  24. 2024Safe Reinforcement Learning on the Constraint Manifold: Theory and Applicationscited by 12
  25. 2024Gameplay Filters: Robust Zero-Shot Safety through Adversarial Imaginationcited by 12
  26. 2025Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecificationcited by 12
  27. 2025Towards Embodiment Scaling Laws in Robot Locomotioncited by 12
  28. 2025Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agentscited by 12
  29. 2024CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learningcited by 11
  30. 2025Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robotscited by 11
  31. 2026Hiking in the Wild: A Scalable Perceptive Parkour Framework for Humanoidscited by 11
  32. 2024SoloParkour: Constrained Reinforcement Learning for Visual Locomotion from Privileged Experiencecited by 10
  33. 2025Learning Humanoid Locomotion with World Model Reconstructioncited by 10
  34. 2025ArticuBot: Learning Universal Articulated Object Manipulation Policy via Large Scale Simulationcited by 10
  35. 2024PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learningcited by 9
  36. 2024Proximal Policy Distillationcited by 9
  37. 2024Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Modelscited by 8
  38. 2024One Filter to Deploy Them All: Robust Safety for Quadrupedal Navigation in Unknown Environmentscited by 8

50 most cited of 115 All 115 (JSON)