计算机科学与探索2025，Vol.19Issue(5)：1177-1197,21.DOI:10.3778/j.issn.1673-9418.2407029
道路行人行为轨迹预测研究综述
Review of Research on Trajectory Prediction of Road Pedestrian Behavior
摘要
Abstract
In path planning for shared spaces between autonomous vehicles and pedestrians,accurate and efficient pedes-trian trajectory prediction is critical for ensuring road safety.Pedestrian trajectory prediction not only relies on historical behavior data but also requires a comprehensive consideration of the complex dynamic interactions between pedestrians and vehicles,traffic infrastructure,and multi-directional vehicles.Significant advancements have been made in this field in recent years,making it a focal point of research.This paper provides a systematic review of the current research.Firstly,it defines the core concepts of pedestrian trajectory prediction and conducts an in-depth analysis of the main pre-diction methods.It then comprehensively outlines the primary data sources for pedestrian behavior,including LiDAR,cameras,and other multimodal sensing devices,while exploring key feature extraction methods,such as pedestrian motion features,contextual scene characteristics,the impact of traffic infrastructure,etc.Based on these data,this paper systematically reviews both physics-based and data-driven prediction approaches,with a focus on the development of statistical models,deep learning,and reinforcement learning models.Special emphasis is placed on deep learning methods,categorized by network architecture into sequential models,convolutional neural networks,graph convolutional networks,generative adversarial networks,etc.This paper also reviews commonly used datasets and evaluation metrics in the field,providing a thorough evaluation of current algorithmic performance.Finally,it addresses the challenges in pedestrian trajectory predic-tion for autonomous driving,particularly the dynamic coupling between pedestrians with multi-directional traffic and infrastructure,offering potential solutions and discussing future research directions.关键词
自动驾驶/行人轨迹预测/深度学习Key words
autonomous driving/pedestrian trajectory prediction/deep learning分类
计算机与自动化引用本文复制引用
杨智勇,郭洁铷,郭子杭,张瑞祥,周瑜..道路行人行为轨迹预测研究综述[J].计算机科学与探索,2025,19(5):1177-1197,21.基金项目
重庆市自然科学基金(cstc2021ycjh-bgzxm0088) （cstc2021ycjh-bgzxm0088）
重庆市教育委员会科学技术研究计划项目(KJZD-M202303401) （KJZD-M202303401）
重庆市高校创新研究群体项目(CXQT21032). This work was supported by the Natural Science Foundation of Chongqing(cstc2021ycjh-bgzxm0088),the Science and Technology Research Project of Chongqing Municipal Education Commission(KJZD-M202303401),and the Program for Innovation Research Groups at Institutions of Higher Education in Chongqing(CXQT21032). （CXQT21032）
