基于高斯混合模型的个性化自动驾驶决策控制研究

doi:10.3901/JME.2022.16.280

机械工程学报 ›› 2022, Vol. 58 ›› Issue (16): 280-289.doi: 10.3901/JME.2022.16.280

扫码分享

基于高斯混合模型的个性化自动驾驶决策控制研究

杨威^1,2, 郑玲^1,2, 李以农^1,2

1. 重庆大学汽车工程学院重庆 400044;
2. 重庆大学机械传动国家重点实验室重庆 400044

收稿日期:2021-03-05 修回日期:2022-02-10 出版日期:2022-08-20 发布日期:2022-11-03
通讯作者: 郑玲(通信作者)，女，1963年出生，博士，教授，博士研究生导师。主要研究方向为汽车振动噪声分析与控制、智能汽车感知与控制理论方法。E-mail：zling@cqu.edu.cn
作者简介:杨威，男，1992年出生，博士研究生。主要研究方向为智能汽车路径规划与控制。E-mail：yangwei07@cqu.edu.cn;
李以农，男，1961年出生，博士，教授，博士研究生导师。主要研究方向为车辆系统动力学与控制、智能车辆运动控制。E-mail：ynli@cqu.edu.cn
基金资助:
国家自然科学基金(51875061)、国家重点研发计划(2016YFB0100904)和重庆市技术创新与应用发展专项(cstc2019jscx-zdztzxX0032)资助项目

Personalized Automated Driving Decision Based on the Gaussian Mixture Model

YANG Wei^1,2, ZHENG Ling^1,2, LI Yinong^1,2

1. College of Automotive Engineering, Chongqing University, Chongqing 400044;
2. State Key Laboratory of Mechanical Transmission, Chongqing University, Chongqing 400044

Received:2021-03-05 Revised:2022-02-10 Online:2022-08-20 Published:2022-11-03

摘要/Abstract

摘要： 大数据时代背景下，借助对自然驾驶员行驶数据的研究和分析，获取个性化的驾驶决策方法，将进一步提升自动驾驶决策过程的安全性和舒适性。采用改进贝塞尔曲线方法生成备选路径，建立二次规划模型规划车辆速度与加速度，提出基于高斯过程的自然驾驶员行驶速度预测模型预测障碍物运动，有效地规划出安全的参考行驶路径。研究并提出基于高斯混合模型的参考路径个性化评价策略，与路径合理性、规划一致性及速度波动性能目标相结合得到一条最优行驶路径。建立最优控制二次规划模型生成满足参考路径目标的车辆动力学状态，保证智能汽车决策系统能够从时空角度输出完整的控制目标。所提出的自动驾驶决策控制方法采用自然驾驶员行驶数据，是对个性化自动驾驶决策控制的探索与实践。

关键词: 贝塞尔曲线, 路径规划, 高斯过程, 高斯混合模型, 最优控制

Abstract: Under the era of big data, a personalized driving decision system would further improve the safety and comfort of the intelligent vehicle with the help of the research on naturalistic driving data. An improving method for Bézier curve path is proposed to achieve the efficient path planning for intelligent vehicle, and then, the quadratic programming for speed and acceleration of ego vehicle is developed, and a speed predictive model for naturalistic driver is built based on the Gaussian process theory, which lay the foundation for collision avoidance in path planning. A personalized path assessing method is developed based on Gaussian mixture model and combining with path rationality, planning homogeneity and speed fluctuation objectives to filter the personalized and agreeable target path. With the consideration of complete control targets, an optimal controller with quadratic programming is designed, and the reference path and target control parameters for automated driving are obtained simultaneously. The naturalistic driving data could be effectively applied with the proposed methods and the driving performance such as safety, comfort, personality would be improved.

Key words: Bézier curve, path planning, Gaussian process, Gaussian mixture model, optimal control

中图分类号:

TG156

杨威, 郑玲, 李以农. 基于高斯混合模型的个性化自动驾驶决策控制研究[J]. 机械工程学报, 2022, 58(16): 280-289.

YANG Wei, ZHENG Ling, LI Yinong. Personalized Automated Driving Decision Based on the Gaussian Mixture Model[J]. Journal of Mechanical Engineering, 2022, 58(16): 280-289.

参考文献

[1] SINGH, SANTOKH. Critical reasons for crashes investigated in the national motor vehicle crash causation survey[EB/OL]. [2015-02]. http://www-nrd.nhtsa.dot.gov/Pubs/812115.pdf
[2] HUH, KUNSOO, CHANWON S, et. al. An experimental investigation of a CW/CA system for automobiles using hardware-in-the-loop simulations[C]//American Control Conference. Warrendale PA, 1999: 724-728.
[3] RASEKHIPOUR, YADOLLAH, AMIR K, et al. A potential field-based model predictive path-planning controller for autonomous road vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2017, 18(5): 1255-1267.
[4] SHIM, TAEHYUN, GANESH A, et al. Autonomous vehicle collision avoidance system using path planning and model-predictive-control-based active front steering and wheel torque control[J]. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, 2012, 226(6): 767-778.
[5] GUTJAHR, BENJAMIN, LUTZ G, et al. Lateral vehicle trajectory optimization using constrained linear time-varying MPC[J]. IEEE Transactions on Intelligent Transportation Systems. 2016, 18(6): 1586-1595.
[6] YAOQIONG D, YIZHOU W, CHING-YAO C. Autonomous lane-change controller via mixed logical dynamical[C]//2014 IEEE 17th International Conference on Intelligent Transportation Systems (ITSC). Qingdao, 2014: 1154-1159.
[7] CHANG L, SEUNGHO L, SCOTT V, et al. Path planning for autonomous vehicles using model predictive control[C]//IEEE Intelligent Vehicles Symposium (Ⅳ). Redondo Beach CA, 2017: 174-179.
[8] DA Y, SHIYU Z, CHENG W, et al. A dynamic lane-changing trajectory planning model for automated vehicles[J]. Transportation Research Part C: Emerging Technologies, 2018(95): 228-247.
[9] HEIL T, ALEXANDER L, STEPHANIE C. Adaptive and efficient lane change path planning for automated vehicles[C]//2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC). Rio de Janeiro, 2016: 479-484.
[10] GHOMMAM, JAWHAR, HASAN M, et al. Formation path following control of unicycle-type mobile robots[J]. Robotics and Autonomous Systems, 2010, 58(5): 727-736.
[11] HONGDA C, KUOCHU C, CRAIG S A. UAV path planning with tangent-plus-Lyapunov vector field guidance and obstacle avoidance[J]. IEEE Transactions on Aerospace and Electronic Systems, 2013, 49(2): 840-856.
[12] UPADHYAY, SAURABH, ASHWINI R. Continuous-curvature path planning with obstacle avoidance using four parameter logistic curves[J]. IEEE Robotics and Automation Letters, 2016, 1(2): 609-616.
[13] XIANGJUN Q, INAKI N, ARNAUD D L, et al. Motion planning for urban autonomous driving using Bézier curves and MPC[C]//2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC). Rio de Janeiro, 2016: 826-833.
[14] JI-WUNG C, RENWICK C, GABRIEL E. Path planning based on bézier curve for autonomous ground vehicles[C]//In World Congress on Engineering and Computer Science 2008, WCECS'08. San Francisco CA, 2008: 158-166.
[15] LIU Zhaolin, CHEN Jiqing, LAN Fengchong, et al, Methodology on comprehensive mapping of multi-information of autonomous driving based on trajectory tensor[J]. Journal of Mechanical Engineering, 2020, 56(16): 214-226. 刘照麟, 陈吉清, 兰凤崇, 等. 基于轨迹张量的自动驾驶复合信息综合映射方法[J]. 机械工程学报, 2020, 56(16): 214-226.
[16] PHILLIP N, WESAM A, JESSE T, et al. An analysis of regression models for predicting the speed of a wave glider autonomous surface vehicle[C]//In Proceedings of Australasian Conference on Robotics and Automation. Australian, 2013: 1-9.
[17] EDUARDO R, LUIS M B, ROBERTO A. Need data for driver behaviour analysis? Presenting the public UAH-DriveSet[C]//2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC). Rio de Janeiro, 2016: 387-392.
[18] GEOFFREY M, THRIYAMBAKAM K. The EM algorithm and extensions[M]. New York: John Wiley & Sons, 2007.
[19] XUEMIN H, LONG C, BO T, et al. Dynamic path planning for autonomous driving on various roads with avoidance of static and moving obstacles[J]. Mechanical Systems and Signal Processing, 2018(100): 482-500.
[20] MENDES D S, ANDRÉ, MARKO A, et al. Yaw stability analysis of articulated vehicles using phase trajectory method[C]//In International Symposium on Dynamic Problems of Mechanics. Sao Paulo, 2017: 445-457.

基于高斯混合模型的个性化自动驾驶决策控制研究

Personalized Automated Driving Decision Based on the Gaussian Mixture Model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	邓建新, 袁邦颐, 黄秋林, 丁度坤, 辛曼玉, 刘光明. 基于工业机器人的复杂曲面磨抛关键技术综述[J]. 机械工程学报, 2024, 60(7): 1-21.
[2]	张伟民, 徐森生, 张月. 基于改进A^*算法的室内巡检机器人路径规划研究[J]. 机械工程学报, 2024, 60(20): 315-326.
[3]	王晓飞, 许家忠, 丁亮, 黄成, 杨怀广, 刘美军. 趋向性锁链式路径规划算法[J]. 机械工程学报, 2024, 60(19): 53-61.
[4]	王洪亮, 雍健羽, 皮大伟, 谢伯元, 王尔烈, 王显会. 基于贝塞尔曲线和多目标优化方法的多车队形切换轨迹规划[J]. 机械工程学报, 2024, 60(16): 270-279.
[5]	徐文琳, 彭羽, 何智成, 姜潮. 复杂路径规划的机构分区运动学拓扑构型设计[J]. 机械工程学报, 2024, 60(11): 62-73.
[6]	闫守鑫, 王伟, 苏鹏飞, 贠超. 大型复杂锻件打磨路径的智能化规划方法[J]. 机械工程学报, 2024, 60(11): 216-225.
[7]	胡林, 杨冬兆, 张新, 章杰, 廖家才. 基于DQP-LMPC的智能车超车换道动态路径规划[J]. 机械工程学报, 2024, 60(10): 171-181.
[8]	聂士达, 刘辉, 廖志昊, 谢雨佳, 项昌乐, 韩立金, 林思豪. 考虑复杂地形的越野环境无人车辆路径规划研究[J]. 机械工程学报, 2024, 60(10): 261-272.
[9]	陈晓明, 李柏, 范丽丽, 王涯舟, 张坦探, 张友民, 曹东璞. 基于半空间约束理论的自动泊车高性能轨迹优化方法[J]. 机械工程学报, 2024, 60(10): 273-288.
[10]	林晨, 魏洪乾, 荆威, 张幽彤. 汽车功能安全：面向敏感指令攻击场景的自主驾驶车辆路径规划风险缓解控制[J]. 机械工程学报, 2024, 60(10): 302-316.
[11]	刘聪, 刘辉, 韩立金, 聂士达. 基于学习型滑模预测控制的无人驾驶车辆非结构化环境轨迹跟踪及稳定性控制[J]. 机械工程学报, 2024, 60(10): 399-412.
[12]	李兵兵, 庄伟超, 刘昊吉, 张昊, 殷国栋, 张建润. 基于自学习型MPC的网联电动汽车生态驾驶控制策略研究[J]. 机械工程学报, 2024, 60(10): 453-462.
[13]	普雪洁, 张建辉, 李建勇, 张健楠. 复杂技术系统隐性冲突求解路径规划方法[J]. 机械工程学报, 2024, 60(1): 309-328.
[14]	向红标, 杨大虎, 杨璐, 王收军, 张冕, 黄显, 霍文星. 复杂环境下磁弹性微型游泳机器人的路径规划与识别跟踪[J]. 机械工程学报, 2023, 59(5): 89-99.
[15]	吴宏宇, 牛文栋, 张玉玲, 王树新, 阎绍泽. 水下滑翔机多点探测能耗最低路径的规划方法[J]. 机械工程学报, 2023, 59(5): 156-166.