APREBot: Active Perception System for Reflexive Evasion Robot
ZIHAO XU, Kuankuan Sima, Junhao Deng, Zixuan Zhuang, Chunzheng Wang, Ce Hao, Jin Song Dong
AI summary
Problem
Single-sensor systems fail to provide both global coverage and high-resolution detail needed for legged robots to reliably detect and evade dynamic obstacles within strict reaction time windows.
Approach
APREBot uses a three-stage pipeline where LiDAR continuously monitors threats, the robot actively turns to focus an RGB-D camera on the most dangerous obstacle, and a unified threat metric drives adaptive avoidance behaviors.
Key results
- Active hierarchical perception framework for quadruped dynamic obstacle avoidance
- Threat-aware perception mechanisms combining LiDAR scanning, camera tracking, and short-horizon prediction
- Extensive Sim2Real validation showing consistent safety, efficiency, and robustness gains over baselines
- Adaptive threat-aware avoidance blending navigation retreat with reflexive evasion gaits
Why it matters
Enables safer, more agile autonomous navigation for legged robots in dynamic, safety-critical environments where rapid and reliable obstacle avoidance is essential.
Abstract
Reliable onboard perception is critical for quadruped robots navigating dynamic environments, where obstacles can emerge from any direction under strict reaction time constraints. Single-sensor systems face inherent limitations: LiDAR provides omnidirectional coverage but lacks rich texture information, while cameras capture high-resolution detail but suffer from restricted field of view. We introduce APREBot (Active Perception System for Reflexive Evasion Robot), a novel framework that integrates reflexive evasion with active hierarchical perception. APREBot strategically combines LiDAR- based omnidirectional scanning with camera-based active focusing, achieving comprehensive environmental awareness essential for agile obstacle avoidance in quadruped robots. We validate APREBot through extensive Sim2Real experiments on a quadruped platform, evaluating diverse obstacle types, trajectories, and approach directions. Our results demonstrate substantial improvements over strong baselines in both safety metrics and operational efficiency, highlighting APREBot’s potential for dependable autonomy in safety-critical scenarios. Paper homepage: https://aprebot-2026.github.io/.