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

TL;DR

PUMA is an end-to-end learning framework that combines visual perception and foothold priors to enable quadruped robots to perform agile parkour maneuvers across complex terrains, improving adaptability and robustness.

Contribution

It introduces a unified perception-driven approach that integrates terrain features into foothold estimation, enhancing real-time adaptability for quadruped robot parkour.

Findings

Demonstrates high agility in simulation and real-world tests.

Shows robustness across diverse complex terrains.

Outperforms existing hierarchical control methods.

Abstract

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.