mlsanityData to 14 Oct 2026

PPL: Point Cloud Supervised Proprioceptive Locomotion Reinforcement Learning for Legged Robots in Crawl Spaces

arXiv 2508.09950 ↗First posted 13 Aug 2025cs.ROcited by 0

On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation

Abstract (arXiv)

Legged locomotion in constrained spaces (called crawl spaces) is challenging. In crawl spaces, current proprioceptive locomotion learning methods are difficult to achieve traverse because only ground features are inferred. In this study, a point cloud supervised RL framework for proprioceptive locomotion in crawl spaces is proposed. A state estimation network is designed to estimate the robot's collision states as well as ground and spatial features for locomotion. A point cloud feature extraction method is proposed to supervise the state estimation network. The method uses representation of the point cloud in polar coordinate frame and MLPs for efficient feature extraction. Experiments demonstrate that, compared with existing methods, our method exhibits faster iteration time in the training and more agile locomotion in crawl spaces. This study enhances the ability of legged robots to traverse constrained spaces without requiring exteroceptive sensors.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 29 of its 35 references that are in the map. First posted on arXiv 13 Aug 2025.

Builds on

29 of 35 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024DreamWaQ++: Obstacle-Aware Quadrupedal Locomotion With Resilient Multi-Modal Reinforcement Learning29 Sep
  2. 2024CTS: Concurrent Teacher-Student Reinforcement Learning for Legged Locomotion17 May
  3. 2024Dexterous Legged Locomotion in Confined 3D Spaces with Reinforcement Learning6 Mar

Other references · 26

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  4. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 604
  5. 2023Point Transformer V3: Simpler, Faster, Strongercited by 589
  6. 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 512
  7. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 508
  8. 2019Learning agile and dynamic motor skills for legged robotscited by 504
  9. 2022Learning robust perceptive locomotion for quadrupedal robots in the wildcited by 382
  10. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 379
  11. 2023Orbit: A Unified Simulation Framework for Interactive Robot Learning Environmentscited by 295
  12. 2023Extreme Parkour with Legged Robotscited by 164
14 more
  1. 2023ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robotscited by 152
  2. 2023Robot Parkour Learningcited by 149
  3. 2022Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behaviorcited by 138
  4. 2022Concurrent Training of a Control Policy and a State Estimator for Dynamic and Robust Legged Locomotioncited by 88
  5. 2023DreamWaQ: Learning Robust Quadrupedal Locomotion With Implicit Terrain Imagination via Deep Reinforcement Learningcited by 66
  6. 2022Elevation Mapping for Locomotion and Navigation using GPUcited by 43
  7. 2024PIE: Parkour with Implicit-Explicit Learning Framework for Legged Robotscited by 25
  8. 2025MoE-Loco: Mixture of Experts for Multitask Locomotioncited by 23
  9. 2024Learning to walk in confined spaces using 3D representationcited by 22
  10. 2022Neural Scene Representation for Locomotion on Structured Terraincited by 12
  11. 2023Learning to See Physical Properties with Active Sensing Motor Policiescited by 10
  12. 2024Quadruped robot traversing 3D complex environments with limited perceptioncited by 10
  13. 2025Omni-Perception: Omnidirectional Collision Avoidance for Legged Locomotion in Dynamic Environmentscited by 8
  14. 2024MOVE: Multi-skill Omnidirectional Legged Locomotion with Limited View in 3D Environmentscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024PointPatchRL -- Masked Reconstruction Improves Reinforcement Learning on Point Clouds
  2. 2023VAPOR: Legged Robot Navigation in Outdoor Vegetation Using Offline Reinforcement Learning
  3. 2025Learning to Crawl: Latent Model-Based Reinforcement Learning for Soft Robotic Adaptive Locomotion
  4. 2025Attention-Based Map Encoding for Learning Generalized Legged Locomotion
  5. 2026VIP-Loco: A Visually Guided Infinite Horizon Planning Framework for Legged Locomotion ↗
  6. 2026JEPLO: Joint-Embedding Predictive Learning for LiDAR-Based Legged Locomotion ↗
  7. 2025APEX: Action Priors Enable Efficient Exploration for Robust Motion Tracking on Legged Robots ↗
  8. 2026Partial Motion Imitation for Learning Cart Pushing with Legged Manipulators ↗