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

2026-04-26

AI Summary

This work addresses the challenge of achieving agile, reflexive obstacle avoidance for wheeled-legged robots operating among high-speed dynamic obstacles—a task hindered by their hybrid morphology, motion coupling, and nonholonomic constraints. To overcome these limitations, we propose AWARE, a hierarchical reinforcement learning framework that, for the first time, enables learning-based, highly dynamic reflexive avoidance on wheeled-legged platforms. The learned policy autonomously discovers diverse locomotion strategies, such as forward surges and lateral dodges, effectively unlocking the robot’s inherent agility. Trained in Isaac Lab simulation and deployed on the real-world M20 robot, the system demonstrates robust, efficient, and behaviorally diverse obstacle avoidance across multiple dynamic scenarios, validating both the efficacy and practicality of the proposed approach.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Intelligent Robots: Motion and Path Planning
• Multiagent Systems: Multiagent Learning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Agentic search

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.

Problem

• wheeled-legged robots
• high-dynamic obstacle evasion
• reflexive avoidance
• agile mobility
• non-holonomic constraints

Innovation

• wheeled-legged robots
• hierarchical reinforcement learning
• reflexive evasion
• dynamic obstacle avoidance
• emergent gaits