REBot: Reflexive Evasion Robot for Instantaneous Dynamic Obstacle Avoidance
- 11 December 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (2) , 1746-1753
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 letter 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.Keywords
All Related Versions
This publication has 28 references indexed in Scilit:
- Catch It! Learning to Catch in Flight with Mobile Dexterous Hands2025
- Reinforcement Learning for Quadrupedal Locomotion: Current Advancements and Future Perspectives2025
- SYNLOCO: Synthesizing Central Pattern Generator and Reinforcement Learning for Quadruped Locomotion2024
- MPC-based Optimization Design for 3D Collision Avoidance of a Mobile Manipulator Based-on Obstacle Velocity Estimation2024
- Deployment of Whole-Body Locomotion and Manipulation Algorithm Based on NMPC Onto Unitree Go2Quadruped Robot2024
- Dexterous Legged Locomotion in Confined 3D Spaces with Reinforcement Learning2024
- Creating a Dynamic Quadrupedal Robotic Goalkeeper with Reinforcement Learning2023
- A Linearization of Centroidal Dynamics for the Model-Predictive Control of Quadruped Robots2022
- Adaptive gait planning for quadruped robot based on center of inertia over rough terrainBiomimetic Intelligence and Robotics, 2022
- Robust Autonomous Navigation of a Small-Scale Quadruped Robot in Real-World Environments2020