SEA-Nav: Efficient Policy Learning for Safe and Agile Quadruped Navigation in Cluttered Environments

TL;DR

This paper introduces SEA-Nav, a reinforcement learning framework that enables quadruped robots to navigate safely and efficiently in cluttered environments with minimal training time by integrating control barrier functions and adaptive exploration.

Contribution

The paper presents a novel RL-based navigation method combining CBF-based safety constraints, adaptive collision replay, and hazardous exploration rewards for rapid real-world deployment.

Findings

Achieves real-world quadruped navigation with minute-level training.

Ensures safe velocity commands through kinematic constraints.

Demonstrates superior safety and agility in dense environments.

Abstract

Efficiently training quadruped robot navigation in densely cluttered environments remains a significant challenge. Existing methods are either limited by a lack of safety and agility in simple obstacle distributions or suffer from slow locomotion in complex environments, often requiring excessively long training phases. To this end, we propose SEA-Nav (Safe, Efficient, and Agile Navigation), a reinforcement learning framework for quadruped navigation. Within diverse and dense obstacle environments, a differentiable control barrier function (CBF)-based shield constraints the navigation policy to output safe velocity commands. An adaptive collision replay mechanism and hazardous exploration rewards are introduced to increase the probability of learning from critical experiences, guiding efficient exploration and exploitation. Finally, kinematic action constraints are incorporated to ensure safe velocity commands, facilitating successful physical deployment. To the best of our knowledge, this is the first approach that achieves highly challenging quadruped navigation in the real world with minute-level training time.