PUMA: Perception-driven Unified Foothold Prior for Mobility Augmented Quadruped Parkour

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Liang, Yao, Kanzhong, Liu, Yang, Qin, Weikai, Wu, Jun, Sun, Zhe, Zhu, Qiuguo
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917217738686464
author Wang, Liang
Yao, Kanzhong
Liu, Yang
Qin, Weikai
Wu, Jun
Sun, Zhe
Zhu, Qiuguo
author_facet Wang, Liang
Yao, Kanzhong
Liu, Yang
Qin, Weikai
Wu, Jun
Sun, Zhe
Zhu, Qiuguo
contents Parkour tasks for quadrupeds have emerged as a promising benchmark for agile locomotion. While human athletes can effectively perceive environmental characteristics to select appropriate footholds for obstacle traversal, endowing legged robots with similar perceptual reasoning remains a significant challenge. Existing methods often rely on hierarchical controllers that follow pre-computed footholds, thereby constraining the robot's real-time adaptability and the exploratory potential of reinforcement learning. To overcome these challenges, we present PUMA, an end-to-end learning framework that integrates visual perception and foothold priors into a single-stage training process. This approach leverages terrain features to estimate egocentric polar foothold priors, composed of relative distance and heading, guiding the robot in active posture adaptation for parkour tasks. Extensive experiments conducted in simulation and real-world environments across various discrete complex terrains, demonstrate PUMA's exceptional agility and robustness in challenging scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2601_15995
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PUMA: Perception-driven Unified Foothold Prior for Mobility Augmented Quadruped Parkour
Wang, Liang
Yao, Kanzhong
Liu, Yang
Qin, Weikai
Wu, Jun
Sun, Zhe
Zhu, Qiuguo
Robotics
Artificial Intelligence
Machine Learning
Parkour tasks for quadrupeds have emerged as a promising benchmark for agile locomotion. While human athletes can effectively perceive environmental characteristics to select appropriate footholds for obstacle traversal, endowing legged robots with similar perceptual reasoning remains a significant challenge. Existing methods often rely on hierarchical controllers that follow pre-computed footholds, thereby constraining the robot's real-time adaptability and the exploratory potential of reinforcement learning. To overcome these challenges, we present PUMA, an end-to-end learning framework that integrates visual perception and foothold priors into a single-stage training process. This approach leverages terrain features to estimate egocentric polar foothold priors, composed of relative distance and heading, guiding the robot in active posture adaptation for parkour tasks. Extensive experiments conducted in simulation and real-world environments across various discrete complex terrains, demonstrate PUMA's exceptional agility and robustness in challenging scenarios.
title PUMA: Perception-driven Unified Foothold Prior for Mobility Augmented Quadruped Parkour
topic Robotics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2601.15995