Adaptive Lane Change Trajectory Planning Scheme for Autonomous Vehicles Under Various Road Frictions and Vehicle Speeds

被引:37
作者
Hu, Juqi [1 ]
Zhang, Youmin [2 ]
Rakheja, Subhash [2 ]
机构
[1] Anhui Univ, Sch Artificial Intelligence, Hefei 230601, Peoples R China
[2] Concordia Univ, Dept Mech Ind & Aerosp Engn, Montreal, PQ H3G 1M8, Canada
来源
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES | 2023年 / 8卷 / 02期
基金
加拿大自然科学与工程研究理事会;
关键词
Trajectory; Roads; Trajectory planning; Planning; Friction; Safety; Heuristic algorithms; Autonomous lane change; trajectory planning; adaptive comfort limit; road friction; driving safety; OF-THE-ART; COEFFICIENT ESTIMATION; TRACKING; COMPUTATION;
D O I
10.1109/TIV.2022.3178061
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper proposes an adaptive lane change trajectory planning scheme to road friction and vehicle speed for autonomous driving, while considering both the maneuver safety and the comfort of occupants. In regard to achieve smooth trajectory, a 7th-order polynomial function is constructed to ensure continuity of the planned trajectory up to the derivative of the curvature (jerk). Unlike traditional planning methods that only consider very limited maneuvering conditions, the proposed scheme adapts to a wide range of road friction and vehicle speed, while ensuring enhanced occupants' ride comfort and acceptance. The proposed trajectory planning scheme creatively integrates all the dynamic constraints which are defined by road friction, safety, comfort and human-like driving style. It is shown that the proposed lane change planning algorithm reduces to the identification of exclusively the lane change duration given a constant forward speed. Illustrative simulation examples in MATLAB/Simulink have been conducted to demonstrate the validity of the proposed scheme. The acceptable traceability of the planned lane change trajectories is further demonstrated through path tracking analysis of a full-vehicle model in CarSim. Finally, experimental tests have been conducted based on Quanser's latest self-driving car (QCar) to verify the practical effectiveness of the proposed trajectory planning scheme.
引用
收藏
页码:1252 / 1265
页数:14
相关论文
共 55 条
[1]  
[Anonymous], 2014, MATH PROBLEMS ENG
[2]  
Bae I, 2020, Arxiv, DOI arXiv:2001.03908
[3]   Toward a Comfortable Driving Experience for a Self-Driving Shuttle Bus [J].
Bae, Il ;
Moon, Jaeyoung ;
Seo, Jeongseok .
ELECTRONICS, 2019, 8 (09)
[4]   On the human control of vehicles: an experimental study of acceleration [J].
Bosetti, Paolo ;
Da Lio, Mauro ;
Saroldi, Andrea .
EUROPEAN TRANSPORT RESEARCH REVIEW, 2014, 6 (02) :157-170
[5]   Conditional DQN-Based Motion Planning With Fuzzy Logic for Autonomous Driving [J].
Chen, Long ;
Hu, Xuemin ;
Tang, Bo ;
Cheng, Yu .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2022, 23 (04) :2966-2977
[6]   Motion Planning With Velocity Prediction and Composite Nonlinear Feedback Tracking Control for Lane-Change Strategy of Autonomous Vehicles [J].
Chen, Yimin ;
Hu, Chuan ;
Wang, Junmin .
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES, 2020, 5 (01) :63-74
[7]   Trajectory planning and tracking for autonomous overtaking: State-of-the-art and future prospects [J].
Dixit, Shilp ;
Fallah, Saber ;
Montanaro, Umberto ;
Dianati, Mehrdad ;
Stevens, Alan ;
Mccullough, Francis ;
Mouzakitis, Alexandros .
ANNUAL REVIEWS IN CONTROL, 2018, 45 :76-86
[8]   Study on Path Planning Method for Imitating the Lane-Changing Operation of Excellent Drivers [J].
Geng, Guoqing ;
Wu, Zhen ;
Jiang, Haobin ;
Sun, Liqin ;
Duan, Chen .
APPLIED SCIENCES-BASEL, 2018, 8 (05)
[9]   Spline-Based Motion Planning for Automated Driving [J].
Goette, Christian ;
Keller, Martin ;
Nattermann, Till ;
Hass, Carsten ;
Glander, Karl-Heinz ;
Bertram, Torsten .
IFAC PAPERSONLINE, 2017, 50 (01) :9114-9119
[10]   A Review of Motion Planning Techniques for Automated Vehicles [J].
Gonzalez, David ;
Perez, Joshue ;
Milanes, Vicente ;
Nashashibi, Fawzi .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2016, 17 (04) :1135-1145