REBot: Reflexive Evasion Robot for Instantaneous Dynamic Obstacle Avoidance

TL;DR

REBot is a control framework that enables quadrupedal robots to perform real-time, reflexive obstacle avoidance in dynamic environments, overcoming the limitations of traditional trajectory replanning methods.

Contribution

This paper introduces REBot, a novel reflexive evasion control framework that combines avoidance and recovery policies for instantaneous obstacle avoidance in quadrupedal robots.

Findings

REBot significantly improves obstacle avoidance success rates.

REBot demonstrates robustness against fast-moving obstacles.

REBot achieves energy-efficient and rapid stabilization during evasion.

Abstract

Dynamic obstacle avoidance (DOA) is critical for quadrupedal robots operating in environments with moving obstacles or humans. Existing approaches typically rely on navigation-based trajectory replanning, which assumes sufficient reaction time and leading to fails when obstacles approach rapidly. In such scenarios, quadrupedal robots require reflexive evasion capabilities to perform instantaneous, low-latency maneuvers. This paper introduces Reflexive Evasion Robot (REBot), a control framework that enables quadrupedal robots to achieve real-time reflexive obstacle avoidance. REBot integrates an avoidance policy and a recovery policy within a finite-state machine. With carefully designed learning curricula and by incorporating regularization and adaptive rewards, REBot achieves robust evasion and rapid stabilization in instantaneous DOA tasks. We validate REBot through extensive simulations and real-world experiments, demonstrating notable improvements in avoidance success rates, energy efficiency, and robustness to fast-moving obstacles. Videos and appendix are available on https://rebot-2025.github.io/.