REFLEX: A Learned On-Board Reflex for Robust Autonomous Collision Recovery of Soft Quadrotors

cs.RO

Submitted: 2026-10-11

Updated: 2026-10-11

Comments: J.H. and L.G. contributed equally;S.L. and S.M. jointly advised;Supplementary video: https://youtu.be/Q76GmW9cNgE;Supported by EU Horizon Europe project SPEAR (grant no. 101119774);Submitted to ICRA 2027

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Collision-tolerant Aerial Robots: A Survey
• Bioinspired Soft Quadrotors Jointly Unlock Agility, Squeezability, and Collision Resilience
• Agile Fall Recovery for Quadrotors with Bidirectional Thrust via Reinforcement Learning
• A Neural Network Mode for PX4 on Embedded Flight Controllers

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies