Learning Robust Policy for Multi-UAV Collision Avoidance via Compact Causal Feature

Deepreinforcementlearning(DRL)-basedmulti-UAVcollisionavoidance methods often exhibit limited generalization when deployed in unseen environments, primarily due to the reliance on noncausal and redundant visual features. Such overfitting to spurious correlations compromises both robustness and safety during realworld deployment. To address these limitations, this study proposes a novel Compact Causal Feature Learning (CCFL) framework that enables UAVs to learn compact and generalizable causal representations. Specifically, a Causal Feature Identification module is designed to disentangle input representations into causal and noncausalcomponents, ensuringthatthelearnedfeaturespreservetrue environmental causality. Furthermore, a Redundancy Feature Compression module is introduced to remove redundant dependencies and compact the causal subspace, thereby enhancing generalization to previously unseen scenarios. Extensive experiments on a challenging UAV collision avoidance benchmark demonstrate that CCFL achieves substantial performance gains over state-of-the-art baselines, increasing individual success rates by 42. 0% and swarm success rates by 61. 6%. These results validate the effectiveness of compact causal feature learning for improving the adaptability, robustness, and safety of autonomous UAV systems operating in complex dynamic environments.

Authors

• Zhun Fan Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China & Shenzhen Loop Area Institute
• Gaofei Han Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China
• Che Lin Shantou University
• Wenji Li Shantou University
• Jie Xu Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)
• Jiafan Zhuang Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China

Keywords

• Multi-UAVSystems
• CollisionAvoidance
• DeepReinforcementLearning
• Compact Causal Feature Learning