Motion Planning for Autonomous Driving with Real Traffic Data Validation

Wenbo Chu ¹Kai Yang ²Shen Li ³Xiaolin Tang²

扫码查看

作者信息

1. Western China Science City Innovation Center of Intelligent and Connected Vehicle,Chongqing 400044,China;College of Mechanical and Vehicle Engineering,Chongqing University,Chongqing 400044,China
2. College of Mechanical and Vehicle Engineering,Chongqing University,Chongqing 400044,China
3. School of Civil Engineering,Tsinghua University,Beijing 100084,China
折叠

Abstract

Accurate trajectory prediction of surrounding road users is the fundamental input for motion planning,which enables safe autonomous driving on public roads.in this paper,a safe motion planning approach is proposed based on the deep learning-based trajectory prediction method.To begin with,a trajectory prediction model is established based on the graph neural network(GNN)that is trained utilizing the INTERACTION dataset.Then,the validated trajectory prediction model is used to predict the future trajectories of surrounding road users,including pedestrians and vehicles.In addition,a GNN prediction model-enabled motion planner is developed based on the model predic-tive control technique.Furthermore,two driving scenarios are extracted from the INTERACTION dataset to validate and evaluate the effectiveness of the proposed motion planning approach,i.e.,merging and roundabout sce-narios.The results demonstrate that the proposed method can lower the risk and improve driving safety compared with the baseline method.

Key words

Trajectory prediction/Graph neural network/Motion planning/INTERACTION dataset

引用本文复制引用

基金项目

国家自然科学基金(52222215)

国家自然科学基金(52072051)

Chongqing Municipal Natural Science Foundation of China(CSTB2023NSCQ-JQX0003)

出版年

2024

中国机械工程学报

中国机械工程学会

中国机械工程学报

CSTPCDCSCD

影响因子：0.765

ISSN：1000-9345

参考文献量37

段落导航