Risk Assessment and Mitigation in Local Path Planning for Autonomous Vehicles With LSTM Based Predictive Model

作     者：Wang, Hong Lu, Bing Li, Jun Liu, Teng Xing, Yang Lv, Chen Cao, Dongpu Li, Jingxuan Zhang, Jinwei Hashemi, Ehsan 

作者机构：Tsinghua Univ Tsinghua Intelligent Vehicle Design & Safety Res Beijing 100084 Peoples R China Beijing Inst Technol Beijing 100811 Peoples R China Waterloo Univ Dept Mech & Mechatron Engn Waterloo ON N2L 3G1 Canada Nanyang Technol Univ Sch Mech & Aerosp Engn Singapore Singapore Nanjing Univ Aeronaut & Astronaut Coll Energy & Power Engn Nanjing 210016 Peoples R China 

出 版 物：《IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING》 (IEEE Trans. Autom. Sci. Eng.)

年 卷 期：2022年第19卷第4期

页      面：2738-2749页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 0811[工学-控制科学与工程] 

基　　金：National Science Foundation of China [52072215, U1964203] National Key Research and Development Program of China [2020YFB1600303] 

主　　题：Safety Risk management Trajectory Tires Prediction algorithms Accidents Predictive models HighD dataset local path planning long short-term memory (LSTM) model predictive control (MPC) risk assessment risk mitigation 

摘      要：Accurate trajectory prediction of surrounding vehicles enables lower risk path planning in advance for autonomous vehicles, thus promising the safety of automated driving. A low-risk and high-efficiency path planning approach is proposed for autonomous driving based on the high-performance and practical trajectory prediction method. A long short-term memory (LSTM) network is trained and tested using the highD dataset, and the validated LSTM is used to predict the trajectories of surrounding vehicles combining the information extracted from vehicle-to-vehicle (V2V) technology. A risk assessment and mitigation-based local path planning algorithm is proposed according to the information of predicted trajectories of surrounding vehicles. Two driving scenarios are extracted and reconstructed from the highD dataset for validation and evaluation, i.e., an active lane-change scenario and a longitudinal collision-avoidance scenario. The results illustrate that the risk is mitigated and the driving efficiency is improved with the proposed path planning algorithm comparing to the constant-velocity prediction and the prediction method of the nonlinear input-output (NIO) network, especially when the velocity and trajectory with sudden changes.