Enregistré dans:
Détails bibliographiques
Auteurs principaux: Liu, Jialong, Shen, Dehan, Wen, Yanbo, Jiang, Zeyu, Chen, Changhao
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2603.17653
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915871960596480
author Liu, Jialong
Shen, Dehan
Wen, Yanbo
Jiang, Zeyu
Chen, Changhao
author_facet Liu, Jialong
Shen, Dehan
Wen, Yanbo
Jiang, Zeyu
Chen, Changhao
contents Extreme legged parkour demands rapid terrain assessment and precise foot placement under highly dynamic conditions. While recent learning-based systems achieve impressive agility, they remain fundamentally fragile to perceptual degradation, where even brief visual noise or latency can cause catastrophic failure. To overcome this, we propose Robust Extreme Agility Learning (REAL), an end-to-end framework for reliable parkour under sensory corruption. Instead of relying on perfectly clean perception, REAL tightly couples vision, proprioceptive history, and temporal memory. We distill a cross-modal teacher policy into a deployable student equipped with a FiLM-modulated Mamba backbone to actively filter visual noise and build short-term terrain memory actively. Furthermore, a physics-guided Bayesian state estimator enforces rigid-body consistency during high-impact maneuvers. Validated on a Unitree Go2 quadruped, REAL successfully traverses extreme obstacles even with a 1-meter visual blind zone, while strictly satisfying real-time control constraints with a bounded 13.1 ms inference time.
format Preprint
id arxiv_https___arxiv_org_abs_2603_17653
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle REAL: Robust Extreme Agility via Spatio-Temporal Policy Learning and Physics-Guided Filtering
Liu, Jialong
Shen, Dehan
Wen, Yanbo
Jiang, Zeyu
Chen, Changhao
Robotics
Extreme legged parkour demands rapid terrain assessment and precise foot placement under highly dynamic conditions. While recent learning-based systems achieve impressive agility, they remain fundamentally fragile to perceptual degradation, where even brief visual noise or latency can cause catastrophic failure. To overcome this, we propose Robust Extreme Agility Learning (REAL), an end-to-end framework for reliable parkour under sensory corruption. Instead of relying on perfectly clean perception, REAL tightly couples vision, proprioceptive history, and temporal memory. We distill a cross-modal teacher policy into a deployable student equipped with a FiLM-modulated Mamba backbone to actively filter visual noise and build short-term terrain memory actively. Furthermore, a physics-guided Bayesian state estimator enforces rigid-body consistency during high-impact maneuvers. Validated on a Unitree Go2 quadruped, REAL successfully traverses extreme obstacles even with a 1-meter visual blind zone, while strictly satisfying real-time control constraints with a bounded 13.1 ms inference time.
title REAL: Robust Extreme Agility via Spatio-Temporal Policy Learning and Physics-Guided Filtering
topic Robotics
url https://arxiv.org/abs/2603.17653