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

arXiv cs.RO / 4/28/2026

📰 NewsDeveloper Stack & InfrastructureSignals & Early TrendsModels & Research

共有:

Key Points

The paper addresses a key challenge for wheeled-legged robots: performing high-dynamic, reflexive obstacle evasion against fast-moving obstacles under hybrid dynamics and non-holonomic constraints.
It introduces AWARE (Adaptive Wheeled-Legged Avoidance and Reflexive Evasion), a hierarchical reinforcement learning framework designed for agile obstacle avoidance in highly dynamic settings.
AWARE is shown to produce diverse emergent gaits and evasion behaviors (e.g., forward lunges and lateral dodges) by leveraging the robot’s hybrid wheeled-and-legged morphology.
Extensive testing in Isaac Lab simulation and real-world deployments on an M20 robot platform across varied dynamic scenarios demonstrates robust, agile avoidance and reveals distinct behavioral strategies.
Overall, the results suggest both the practical effectiveness of the AWARE approach and the inherent “reflexive agility” potential of wheeled-legged robot systems.

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.