Unleashing the Agility of Wheeled-Legged Robots for High-Dynamic Reflexive Obstacle Evasion

TL;DR

This paper introduces AWARE, a hierarchical reinforcement learning framework enabling wheeled-legged robots to perform high-dynamic reflexive obstacle evasion with diverse emergent behaviors in complex environments.

Contribution

The work presents a novel RL-based approach that leverages hybrid morphology for agile, reflexive obstacle avoidance, demonstrating effectiveness in simulation and real-world tests.

Findings

AWARE achieves robust obstacle avoidance in dynamic scenarios.

The system exhibits diverse evasive behaviors like lunges and dodges.

Real-world deployment confirms practical effectiveness.

Abstract

Wheeled-legged robots combine the energy efficiency of wheeled locomotion with the terrain adaptability of legged systems, making them promising platforms for agile mobility in complex and dynamic environments. However, enabling high-dynamic reflexive evasion against fast-moving obstacles remains challenging due to the hybrid morphology, mode coupling, and non-holonomic constraints of such platforms. In this work, we propose AWARE, Adaptive Wheeled-Legged Avoidance and Reflexive Evasion, a hierarchical reinforcement learning framework for high-dynamic obstacle avoidance in wheeled-legged robots. The proposed system naturally exhibits diverse emergent gaits and evasive behaviors, including forward lunge and lateral dodge, thereby leveraging the robot's hybrid morphology to enhance agility under highly dynamic threats. Extensive experiments in Isaac Lab simulation and real-world deployment on the M20 platform across diverse dynamic scenarios demonstrate that AWARE achieves robust and agile obstacle avoidance while revealing behaviorally distinct evasive strategies. These results highlight both the practical effectiveness of AWARE and the intrinsic reflexive agility of wheeled-legged robots.