mlsanityData to 7 Oct 2026

Advanced Skills by Learning Locomotion and Local Navigation End-to-End

arXiv 2209.12827 ↗First posted 26 Sep 2022cs.RO cs.LGcited by 39

Not on the map. Why?

Abstract (arXiv)

The common approach for local navigation on challenging environments with legged robots requires path planning, path following and locomotion, which usually requires a locomotion control policy that accurately tracks a commanded velocity. However, by breaking down the navigation problem into these sub-tasks, we limit the robot's capabilities since the individual tasks do not consider the full solution space. In this work, we propose to solve the complete problem by training an end-to-end policy with deep reinforcement learning. Instead of continuously tracking a precomputed path, the robot needs to reach a target position within a provided time. The task's success is only evaluated at the end of an episode, meaning that the policy does not need to reach the target as fast as possible. It is free to select its path and the locomotion gait. Training a policy in this way opens up a larger set of possible solutions, which allows the robot to learn more complex behaviors. We compare our approach to velocity tracking and additionally show that the time dependence of the task reward is critical to successfully learn these new behaviors. Finally, we demonstrate the successful deployment of policies on a real quadrupedal robot. The robot is able to cross challenging terrains, which were not possible previously, while using a more energy-efficient gait and achieving a higher success rate.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Builds on 21 of its 30 references that are in the map. First posted on arXiv 26 Sep 2022.

Builds on

21 of 30 references.

References · 21

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 882
  3. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 494
  4. 2019Learning agile and dynamic motor skills for legged robotscited by 402
  5. 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 395
  6. 2022Learning robust perceptive locomotion for quadrupedal robots in the wildcited by 299
  7. 2020Learning Agile Robotic Locomotion Skills by Imitating Animalscited by 229
  8. 2021Blind Bipedal Stair Traversal via Sim-to-Real Reinforcement Learningcited by 73
  9. 2022Concurrent Training of a Control Policy and a State Estimator for Dynamic and Robust Legged Locomotioncited by 61
  10. 2021Fast and Efficient Locomotion via Learned Gait Transitionscited by 50
  11. 2019DeepGait: Planning and Control of Quadrupedal Gaits using Deep Reinforcement Learningcited by 45
  12. 2019Highly Dynamic Quadruped Locomotion via Whole-Body Impulse Control and Model Predictive Controlcited by 43
9 more
  1. 2021Learning a State Representation and Navigation in Cluttered and Dynamic Environmentscited by 30
  2. 2021Vision-Guided Quadrupedal Locomotion in the Wild with Multi-Modal Delay Randomizationcited by 18
  3. 2021Imitation Learning from MPC for Quadrupedal Multi-Gait Controlcited by 16
  4. 2017Whole-Body Nonlinear Model Predictive Control Through Contacts for Quadrupedscited by 15
  5. 2021Cat-like Jumping and Landing of Legged Robots in Low-gravity Using Deep Reinforcement Learningcited by 11
  6. 2019Rolling in the Deep -- Hybrid Locomotion for Wheeled-Legged Robots using Online Trajectory Optimizationcited by 4
  7. 2021Mini Cheetah, the Falling Cat: A Case Study in Machine Learning and Trajectory Optimization for Robot Acrobaticscited by 3
  8. 2021Fast Online Planning for Bipedal Locomotion via Centroidal Model Predictive Gait Synthesiscited by 1
  9. 2021Real-time Optimal Landing Control of the MIT Mini Cheetahcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 12; 2024: 15; 2025: 6; 2026: 5.

39 papers.

Sort:

By area:

  1. 2024Deep Reinforcement Learning for Robotics: A Survey of Real-World Successescited by 153
  2. 2023Extreme Parkour with Legged Robotscited by 120
  3. 2023Robot Parkour Learningcited by 115
  4. 2023Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learningcited by 111
  5. 2024Agile But Safe: Learning Collision-Free High-Speed Legged Locomotioncited by 53
  6. 2025Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoidscited by 40
  7. 2023DTC: Deep Tracking Controlcited by 37
  8. 2023DribbleBot: Dynamic Legged Manipulation in the Wildcited by 33
  9. 2023Barkour: Benchmarking Animal-level Agility with Quadruped Robotscited by 33
  10. 2024Learning Robust Autonomous Navigation and Locomotion for Wheeled-Legged Robotscited by 32
  11. 2024Symmetry Considerations for Learning Task Symmetric Robot Policiescited by 18
  12. 2023Resilient Legged Local Navigation: Learning to Traverse with Compromised Perception End-to-Endcited by 16
27 more
  1. 2025Learning coordinated badminton skills for legged manipulatorscited by 16
  2. 2024Learning Visual Quadrupedal Loco-Manipulation from Demonstrationscited by 15
  3. 2024Commonsense Reasoning for Legged Robot Adaptation with Vision-Language Modelscited by 15
  4. 2024RobotKeyframing: Learning Locomotion with High-Level Objectives via Mixture of Dense and Sparse Rewardscited by 12
  5. 2022Visual CPG-RL: Learning Central Pattern Generators for Visually-Guided Quadruped Locomotioncited by 11
  6. 2024SoloParkour: Constrained Reinforcement Learning for Visual Locomotion from Privileged Experiencecited by 10
  7. 2024Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Modelscited by 8
  8. 2024One Filter to Deploy Them All: Robust Safety for Quadrupedal Navigation in Unknown Environmentscited by 8
  9. 2023Learning Diverse Skills for Local Navigation under Multi-constraint Optimalitycited by 7
  10. 2024Robust Robot Walker: Learning Agile Locomotion over Tiny Trapscited by 7
  11. 2024Gaitor: Learning a Unified Representation Across Gaits for Real-World Quadruped Locomotioncited by 6
  12. 2025Unsupervised Skill Discovery as Exploration for Learning Agile Locomotioncited by 5
  13. 2023Natural and Robust Walking using Reinforcement Learning without Demonstrations in High-Dimensional Musculoskeletal Modelscited by 4
  14. 2024Dexterous Legged Locomotion in Confined 3D Spaces with Reinforcement Learningcited by 4
  15. 2025Let Humanoids Hike! Integrative Skill Development on Complex Trailscited by 4
  16. 2026Learning Human-Like Badminton Skills for Humanoid Robotscited by 3
  17. 2026RF-Agent: Automated Reward Function Design via Language Agent Tree Searchcited by 3
  18. 2023DeepTransition: Viability Leads to the Emergence of Gait Transitions in Learning Anticipatory Quadrupedal Locomotion Skillscited by 2
  19. 2024TOP-Nav: Legged Navigation Integrating Terrain, Obstacle and Proprioception Estimationcited by 2
  20. 2023MTAC: Hierarchical Reinforcement Learning-based Multi-gait Terrain-adaptive Quadruped Controllercited by 1
  21. 2025AINav: Large Language Model-Based Adaptive Interactive Navigationcited by 1
  22. 2026DreamFlow: Local Navigation Beyond Observation via Conditional Flow Matching in the Latent Spacecited by 1
  23. 2023A Population-Level Analysis of Neural Dynamics in Robust Legged Robotscited by 0
  24. 2024Impedance Matching: Enabling an RL-Based Running Jump in a Quadruped Robotcited by 0
  25. 2025Parental Guidance: Efficient Lifelong Learning through Evolutionary Distillationcited by 0
  26. 2026CTS-MoE: Implicit Terrain Adaptation via Mixture-of-Experts for Perceptive Locomotioncited by 0
  27. 2026MulDP: Multimodal Diffusion Policy for Autonomous Quadruped Parkour Navigation across Complex Terrainscited by 0