mlsanityData to 7 Oct 2026

Learning Robust Autonomous Navigation and Locomotion for Wheeled-Legged Robots

arXiv 2405.01792 ↗First posted 3 May 2024cs.RO cs.LG cs.SYcited by 32

Not on the map. Why?

Abstract (arXiv)

Autonomous wheeled-legged robots have the potential to transform logistics systems, improving operational efficiency and adaptability in urban environments. Navigating urban environments, however, poses unique challenges for robots, necessitating innovative solutions for locomotion and navigation. These challenges include the need for adaptive locomotion across varied terrains and the ability to navigate efficiently around complex dynamic obstacles. This work introduces a fully integrated system comprising adaptive locomotion control, mobility-aware local navigation planning, and large-scale path planning within the city. Using model-free reinforcement learning (RL) techniques and privileged learning, we develop a versatile locomotion controller. This controller achieves efficient and robust locomotion over various rough terrains, facilitated by smooth transitions between walking and driving modes. It is tightly integrated with a learned navigation controller through a hierarchical RL framework, enabling effective navigation through challenging terrain and various obstacles at high speed. Our controllers are integrated into a large-scale urban navigation system and validated by autonomous, kilometer-scale navigation missions conducted in Zurich, Switzerland, and Seville, Spain. These missions demonstrate the system's robustness and adaptability, underscoring the importance of integrated control systems in achieving seamless navigation in complex environments. Our findings support the feasibility of wheeled-legged robots and hierarchical RL for autonomous navigation, with implications for last-mile delivery and beyond.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 53 of its 82 references that are in the map. First posted on arXiv 3 May 2024.

Builds on

53 of 82 references.

References · 53

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2016Density estimation using Real NVPcited by 2,029
  4. 2018On Evaluation of Embodied Navigation Agentscited by 526
  5. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 494
  6. 2018Data-Efficient Hierarchical Reinforcement Learningcited by 436
  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. 2019DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Framescited by 352
  11. 2017FeUdal Networks for Hierarchical Reinforcement Learningcited by 328
  12. 2022Learning robust perceptive locomotion for quadrupedal robots in the wildcited by 299
38 more
  1. 2018Semi-parametric Topological Memory for Navigationcited by 203
  2. 2021Open-Ended Learning Leads to Generally Capable Agentscited by 177
  3. 2020PLAS: Latent Action Space for Offline Reinforcement Learningcited by 133
  4. 2022Legged Locomotion in Challenging Terrains using Egocentric Visioncited by 131
  5. 2021Learning High-Speed Flight in the Wildcited by 98
  6. 2020BADGR: An Autonomous Self-Supervised Learning-Based Navigation Systemcited by 97
  7. 2018Driving Policy Transfer via Modularity and Abstractioncited by 91
  8. 2021Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformerscited by 71
  9. 2019Why Does Hierarchy (Sometimes) Work So Well in Reinforcement Learning?cited by 66
  10. 2022Concurrent Training of a Control Policy and a State Estimator for Dynamic and Robust Legged Locomotioncited by 61
  11. 2021Fast and Efficient Locomotion via Learned Gait Transitionscited by 50
  12. 2020RLOC: Terrain-Aware Legged Locomotion using Reinforcement Learning and Optimal Controlcited by 46
  13. 2021Coupling Vision and Proprioception for Navigation of Legged Robotscited by 46
  14. 2019DeepGait: Planning and Control of Quadrupedal Gaits using Deep Reinforcement Learningcited by 45
  15. 2022Advanced Skills by Learning Locomotion and Local Navigation End-to-Endcited by 39
  16. 2019Improving Exploration in Soft-Actor-Critic with Normalizing Flows Policiescited by 37
  17. 2023Diffusion Model-Augmented Behavioral Cloningcited by 37
  18. 2018Reinforced Imitation: Sample Efficient Deep Reinforcement Learning for Map-less Navigation by Leveraging Prior Demonstrationscited by 35
  19. 2020Safe Robot Navigation via Multi-Modal Anomaly Detectioncited by 33
  20. 2021LASER: Learning a Latent Action Space for Efficient Reinforcement Learningcited by 32
  21. 2022Elevation Mapping for Locomotion and Navigation using GPUcited by 32
  22. 2023Emergence of Maps in the Memories of Blind Navigation Agentscited by 31
  23. 2019Robust Recovery Controller for a Quadrupedal Robot using Deep Reinforcement Learningcited by 30
  24. 2021Learning a State Representation and Navigation in Cluttered and Dynamic Environmentscited by 30
  25. 2022Locomotion Policy Guided Traversability Learning using Volumetric Representations of Complex Environmentscited by 27
  26. 2020LaND: Learning to Navigate from Disengagementscited by 24
  27. 2017Learning Ground Traversability from Simulationscited by 20
  28. 2019Hierarchical Reinforcement Learning for Quadruped Locomotioncited by 20
  29. 2020From Pixels to Legs: Hierarchical Learning of Quadruped Locomotioncited by 20
  30. 2020Learning Navigation Skills for Legged Robots with Learned Robot Embeddingscited by 14
  31. 2021Learning to Navigate Sidewalks in Outdoor Environmentscited by 14
  32. 2020Deep Reinforcement learning for real autonomous mobile robot navigation in indoor environmentscited by 13
  33. 2020Vision-Based Goal-Conditioned Policies for Underwater Navigation in the Presence of Obstaclescited by 10
  34. 2023Learning-based Design and Control for Quadrupedal Robots with Parallel-Elastic Actuatorscited by 7
  35. 2022Learning Forward Dynamics Model and Informed Trajectory Sampler for Safe Quadruped Navigationcited by 6
  36. 2023ArtPlanner: Robust Legged Robot Navigation in the Fieldcited by 6
  37. 2020Ascento: A Two-Wheeled Jumping Robotcited by 5
  38. 2020Whole-Body MPC and Online Gait Sequence Generation for Wheeled-Legged Robotscited by 5

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 16; 2026: 8.

32 papers.

Sort:

By area:

  1. 2024NaVILA: Legged Robot Vision-Language-Action Model for Navigationcited by 201
  2. 2024Deep Reinforcement Learning for Robotics: A Survey of Real-World Successescited by 153
  3. 2025RSL-RL: A Learning Library for Robotics Researchcited by 28
  4. 2025GaussGym: An open-source real-to-sim framework for learning locomotion from pixelscited by 22
  5. 2024MetaUrban: An Embodied AI Simulation Platform for Urban Micromobilitycited by 19
  6. 2024Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomycited by 16
  7. 2025Towards Autonomous Micromobility through Scalable Urban Simulationcited by 16
  8. 2024RobotKeyframing: Learning Locomotion with High-Level Objectives via Mixture of Dense and Sparse Rewardscited by 12
  9. 2024Preference Aligned Diffusion Planner for Quadrupedal Locomotion Controlcited by 7
  10. 2026CapNav: Benchmarking Vision Language Models on Capability-conditioned Indoor Navigationcited by 6
  11. 2024Learning Whole-Body Loco-Manipulation for Omni-Directional Task Space Pose Tracking with a Wheeled-Quadrupedal-Manipulatorcited by 5
  12. 2025Multi-Loco: Unifying Multi-Embodiment Legged Locomotion via Reinforcement Learning Augmented Diffusioncited by 5
20 more
  1. 2025Let Humanoids Hike! Integrative Skill Development on Complex Trailscited by 4
  2. 2025UWBench: A Comprehensive Vision-Language Benchmark for Underwater Understandingcited by 4
  3. 2025Wanderland: Geometrically Grounded Simulation for Open-World Embodied AIcited by 3
  4. 2026DeFM: Learning Foundation Representations from Depth for Roboticscited by 3
  5. 2025BURNS: Backward Underapproximate Reachability for Neural-Feedback-Loop Systemscited by 2
  6. 2025Arnold: A multi-task, multi-embodiment muscle transformer policycited by 2
  7. 2025ZeST: an VLM-based Zero-Shot Traversability Navigation for Unknown Environmentscited by 2
  8. 2025VLD: Visual Language Goal Distance for Reinforcement Learning Navigationcited by 2
  9. 2025Neural Fidelity Calibration for Informative Sim-to-Real Adaptationcited by 1
  10. 2025Robust Localization, Mapping, and Navigation for Quadruped Robotscited by 1
  11. 2025Toward Real-World Cooperative and Competitive Soccer with Quadrupedal Robot Teamscited by 1
  12. 2026Rainbow-DemoRL: Combining Improvements in Demonstration-Augmented Reinforcement Learningcited by 1
  13. 2024Scalable Hierarchical Reinforcement Learning for Hyper Scale Multi-Robot Task Planningcited by 0
  14. 2025Dynamic Obstacle Avoidance with Bounded Rationality Adversarial Reinforcement Learningcited by 0
  15. 2025Shared Control of Holonomic Wheelchairs through Reinforcement Learningcited by 0
  16. 2026OpenNavMap: Multi-Session Appearance-Based Topometric Mapping for Scalable Visual Navigationcited by 0
  17. 2026CMR: Contractive Mapping Embeddings for Robust Humanoid Locomotion on Unstructured Terrainscited by 0
  18. 2026Learning All-Terrain Locomotion for a Planetary Rover with Actively Articulated Suspensioncited by 0
  19. 2026Path-level Hindsight Instructions for Semantic Exploration in Vision-Language Navigationcited by 0
  20. 2026MulDP: Multimodal Diffusion Policy for Autonomous Quadruped Parkour Navigation across Complex Terrainscited by 0