Pith. sign in

REVIEW 9 cited by

Parkour in the Wild: Learning a General and Extensible Agile Locomotion Policy Using Multi-expert Distillation and RL Fine-tuning

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2505.11164 v1 pith:D4SWBTLL submitted 2025-05-16 cs.RO

Nikita Rudin , Junzhe He , Joshua Aurand , Marco Hutter This is my paper · ORCID
classification cs.RO
keywords policylocomotionfine-tuningleggedrobotsterrainsacrossagile
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Legged robots are well-suited for navigating terrains inaccessible to wheeled robots, making them ideal for applications in search and rescue or space exploration. However, current control methods often struggle to generalize across diverse, unstructured environments. This paper introduces a novel framework for agile locomotion of legged robots by combining multi-expert distillation with reinforcement learning (RL) fine-tuning to achieve robust generalization. Initially, terrain-specific expert policies are trained to develop specialized locomotion skills. These policies are then distilled into a unified foundation policy via the DAgger algorithm. The distilled policy is subsequently fine-tuned using RL on a broader terrain set, including real-world 3D scans. The framework allows further adaptation to new terrains through repeated fine-tuning. The proposed policy leverages depth images as exteroceptive inputs, enabling robust navigation across diverse, unstructured terrains. Experimental results demonstrate significant performance improvements over existing methods in synthesizing multi-terrain skills into a single controller. Deployment on the ANYmal D robot validates the policy's ability to navigate complex environments with agility and robustness, setting a new benchmark for legged robot locomotion.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Light-Loco-Parkour: Versatile Perceptive Whole-Body Locomotion via Multi-Skill Distillation

    cs.RO 2026-08 conditional novelty 7.0 of 10

    A single neural-network policy, trained in simulation, makes a humanoid climb, vault, and traverse uneven terrain from onboard depth and a velocity command, with no skill labels or runtime motion graphs.

  2. Extreme-RGMT: Continual Learning of Highly Dynamic Skills for Robust Generalist Humanoid Control

    cs.RO 2026-07 conditional novelty 6.0 of 10

    A two-stage continual-learning framework lets a generalist humanoid tracking policy acquire highly dynamic acrobatic skills while preserving its general-purpose motion capabilities.

  3. EgoHTR: Egocentric 4D Demonstrations of Human Terrain Traversal

    cs.RO 2026-07 conditional novelty 6.0 of 10

    EgoHTR is a 55-sequence, 150k-frame egocentric 4D human-terrain dataset with a reconstruction pipeline, MoCap-validated benchmark, and perceptive locomotion policies deployed on a Unitree G1.

  4. StairMaster: Learning to Conquer Risky Hollow Stairs for Agile Quadrupedal Robots

    cs.RO 2026-06 unverdicted novelty 6.0 of 10

    StairMaster trains an RL policy that lets a Unitree Go2 quadruped climb hollow stairs up to 55 degrees via zero-shot sim-to-real transfer using cross-attention, SRU memory, and active-perception rewards.

  5. Online World Modeling Enables Real-World Inverse Reinforcement Learning from Observation

    cs.RO 2026-02 conditional novelty 6.0 of 10

    MPAIL2 demonstrates real-world manipulation learning from observation alone, without rewards or action labels, plus positive online transfer.

  6. Continual-RL for Generalization in Autonomous Racing on the RoboRacer Platform

    cs.RO 2026-07 conditional novelty 5.0 of 10

    SAC plus Continual Backpropagation, trained only on real multi-track data, fine-tunes in ~15 minutes on an unseen lower-friction RoboRacer track and outperforms MAP and MPC.

  7. DPL: Depth-only Perceptive Humanoid Locomotion via Realistic Depth Synthesis and Cross-Attention Terrain Reconstruction

    cs.RO 2025-10 conditional novelty 5.0 of 10

    Combining a blind-backbone policy, cross-attention terrain reconstruction from depth plus proprioception, and realistic synthetic depth with noise enables depth-only full-sized humanoid locomotion over stairs, slopes,...

  8. HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation

    cs.RO 2025-08 conditional novelty 5.0 of 10

    HERMES converts a single human motion demonstration into a deployable mobile bimanual dexterous manipulation policy, using RL, depth-image distillation, and closed-loop PnP pose refinement.

  9. Humanoid Occupancy: Enabling A Generalized Multimodal Occupancy Perception System on Humanoid Robots

    cs.RO 2025-07 conditional novelty 5.0 of 10

    A humanoid-specific multimodal occupancy perception system with a new dataset, sensor layout, and a fusion network that claims state-of-the-art results on its own benchmark.

Pith tools