Review on multimodal robust learning for dynamic traffic scenario understanding

LI Yidong; ZHANG Zhao; ZHANG Zikai; ZHANG Xu; RONG Xiao; LI Ziyi

doi:10.11860/j.issn.1673-0291.20250127

Abstract：Due to constantly interacting targets,rapidly shifting environments,and the inherent hetero-geneity of multi-sensor data,dynamic traffic scenarios impose stringent demands on the perceptual ro-bustness and decision reliability of intelligent systems.Multi-modal learning emerges as a critical solu-tion to overcome bottlenecks in dynamic scenario understanding by fusing heterogeneous modalities.This paper offers a systematic review on multimodal robust learning for dynamic traffic scenarios.First,we clarify the definition of multimodal dynamic traffic scenarios,and analyzes the types and dy-namic characteristics of multi-source modalities(e.g.,optical,radio frequency,and acoustic).Next,we lay out the fundamental principles of multi-modal learning,paying particular attention to key tech-niques that enhance robustness across data-level processing,model architectures,and training strate-gies.Furthermore,we delve into core challenges currently confronting the field and future research di-rections.The review highlights current challenging of data imperfections,model limitations,and the absence of evaluation benchmarks,and chart future directions toward three aspects:technological inno-vation,technology integration,and collaborative industry efforts.Our aim is to provide a systematic reference for both theoretical research and practical deployment of multimodal robust learning in dy-namic traffic scenarios,facilitate the evolution of intelligent transportation systems from being"avail-able in limited scenarios"to achieving"reliability across all conditions,"and provide critical technical support for the widespread adoption of intelligent transportation solutions.