基于轨迹张量的自动驾驶复合信息综合映射方法

doi:10.3901/JME.2020.16.214

机械工程学报 ›› 2020, Vol. 56 ›› Issue (16): 214-226.doi: 10.3901/JME.2020.16.214

扫码分享

基于轨迹张量的自动驾驶复合信息综合映射方法

刘照麟^1,2, 陈吉清^1,2, 兰凤崇^1,2, 夏红阳^1,2

1. 华南理工大学机械与汽车工程学院广州 510640;
2. 广东省汽车工程重点实验室广州 510640

收稿日期:2019-12-17 修回日期:2020-03-18 出版日期:2020-08-20 发布日期:2020-10-19
通讯作者: 兰凤崇(通信作者),男,1959年出生,博士,教授,博士研究生导师。主要研究方向为汽车结构与安全及汽车环境适应性。E-mail:fclan@scut.edu.cn
作者简介:刘照麟,男,1989年出生,博士研究生。主要研究方向为自动驾驶轨迹规划与轨迹跟随方法。E-mail:liuzhaolin_2013@126.com;陈吉清,女,1966年出生,博士,教授,博士研究生导师。主要研究方向为车身结构优化及汽车环境适应性。E-mail:chjq@scut.edu.cn;夏红阳,男,1990年出生,博士研究生。主要研究方向为自动驾驶轨迹规划与轨迹跟随方法。E-mail:xhysummer@163.com
基金资助:
国家自然科学基金（51775193）、广东省科技计划（2015B01037002）和广东省自然科学基金（2018A030313727）资助项目。

Methodology on Comprehensive Mapping of Multi-information of Autonomous Driving Based on Trajectory Tensor

LIU Zhaolin^1,2, CHEN Jiqing^1,2, LAN Fengchong^1,2, XIA Hongyang^1,2

1. School of Mechanical&Automotive Engineering, South China University of Technology, Guangzhou 510640;
2. Guangdong Provincial Key Laboratory of Automotive, Guangzhou 510640

Received:2019-12-17 Revised:2020-03-18 Online:2020-08-20 Published:2020-10-19

摘要/Abstract

摘要： 信息映射的精度和效率不足制约着自动驾驶汽车的性能。对自动驾复合信息进行数据结构和映射方式的优化以提高运算效率和精度；建立自动驾驶轨迹分类求解模型，根据操纵输入求解轨迹信息和姿态信息；通过多重拟合实现操纵、轨迹和姿态信息的参数化表达。针对自动驾驶信息的参数化特征，提出轨迹张量的概念；利用张量系统高阶次、多维度的数据结构，形成轨迹规划和轨迹跟随中两类基本映射关系的数据样本；利用样本在离线环境下充分训练深度学习系统，得到两类基本映射关系模型。经仿真试验证明，所有组别驾驶数据映射计算效率均高于常规微分方程法，且计算误差均在允许范围内。基于轨迹张量的信息映射模型可有效提升轨迹规划和跟随的精度和效率，提高自动驾驶汽车的安全性和适应性。

关键词: 自动驾驶, 轨迹张量, 信息映射

Abstract: The performance of an autonomous driving vehicle is limited by low levels of accuracy and efficiency for information mapping, which can be improved by the optimization of data structure and mapping manner. A trajectory categorical-calculating model for autonomous driving vehicle is built for solving trajectory and attitude by given handling data. Handling information, trajectory information and attitude information are parameterized through multi-fitting. A model of trajectory tensor is proposed according to the characteristics of trajectory parameterization. By taking advantage of the data structure of a tensor with high-order and multi-dimensions, samples of two basic types of mapping in trajectory planning and tracking are worked out. An in-depth learning system is constructed and the mathematic model of the basic relation of two types of mapping is obtained by training offline adequately. In simulation experiments compared with the usual method of differential equations, calculation efficiencies of the trajectory tensor method are higher in all experimental data groups, while the standards required by calculation accuracy are entirely reached. The accuracy and efficiency of trajectory planning and tracking can be improved through the trajectory-tensor-based model of information mapping, and the safety as well as the flexibility of autonomous driving vehicles can be therefore enhanced.

Key words: autonomous driving, trajectory tensor, information mapping

中图分类号:

U462

刘照麟, 陈吉清, 兰凤崇, 夏红阳. 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.

LIU Zhaolin, CHEN Jiqing, LAN Fengchong, XIA Hongyang. Methodology on Comprehensive Mapping of Multi-information of Autonomous Driving Based on Trajectory Tensor[J]. Journal of Mechanical Engineering, 2020, 56(16): 214-226.

参考文献

[1] 李柏. 复杂约束下自动驾驶车辆运动规划的计算最优控制方法研究[D]. 杭州:浙江大学,2018. LI Bai. Research on computational optimal control methods for automated vehicle motion planning problems with complicated constraints[D]. Hangzhou:Zhejiang University, 2018.
[2] GU T. Improved trajectory planning for on-road self-driving vehicles via combined graph search, optimization & topology analysis[D]. Pittsburgh:Carnegie Mellon University, 2017.
[3] KONAR A, GOSWAMI I, SINGH S, et al. A deterministic improved Q-learning for path planning of a mobile robot[J]. IEEE Transactions on Systems Man Cybernetics-Systems, 2013, 43(5):1141-1153.
[4] KATRAKAZAS C, QUDDUS M, CHEN W, et al. Real-time motion planning methods for autonomous on-road driving:State-of-the-art and future research directions[J]. Transportation Research Part C-Emerging Technologies, 2015, 60:416-442.
[5] 冯来春. 基于引导域的参数RRT无人驾驶车辆运动规划算法研究[D]. 合肥:中国科学技术大学, 2017. FENG Laichun. Research on autonomous vehicle motion planning method using parameterized RRT based on guiding area[D]. Hefei:University of Science and Technology of China, 2017.
[6] ELBANHAWI M, SIMIC M. Sampling-based robot motion planning:A review[J]. IEEE Access, 2014, 2(1):56-77.
[7] DUBINS L. On curves of minimal length with a constraint on average curvature, and with prescribed initial and terminal positions and tangents[J]. American Journal of Mathematics, 1957, 79(3):497-516.
[8] REEDS J, SHEPP L. Optimal paths for a car that goes both forwards and backwards[J]. Pacific Journal of Mathematics, 1990, 145(2):367-393.
[9] GUO Lie, GE Pingshu, YUE Ming, et al. Lane changing trajectory planning and tracking controller design for intelligent vehicle running on curved road[J]. Mathe-matical Problems in Engineering, 2014, 2014:1-9.
[10] URMSON C, RAGUSA C, RAY D, et al. A robust approach to high-speed navigation for unrehearsed desert terrain[J]. Journal of Field Robotics, 2006, 23(8):467-508.
[11] TAI M. Experimental study of lateral control of heavy vehicles for automated highway systems (AHS)[C]//American Control Conference, May 5-8, 2002, Anchorage, Alaska. New York:IEEE, 2002:851-856.
[12] GUO Jinghua, LI Linhui, LI Keqiang, et al. An adaptive fuzzy-sliding lateral control strategy of automated vehicles based on vision navigation[J]. Vehicle System Dynamics, 2013, 51(10):1502-1517.
[13] FALCONE P, BORRELLI F, ASGARI J, et al. Predictive active steering control for autonomous vehicle systems[J]. IEEE Transactions on Control Systems Technology, 2007, 15(3):566-580.
[14] CHEN B, LUAN B, LEE K. Design of lane keeping system using adaptive model predictive control[C]//IEEE International Conference on Automation Science and Engineering, August 18-22, 2014, Taipei, Taiwan, China. New York:CASE, 2014:922-926.
[15] KARAMAN S, FRAZZOLI E. Sampling-based algorithms for optimal motion planning[J]. The International Journal of Robotics Research, 2011, 30(7):846-894.
[16] YOU F, ZHANG R, LIE G, et al. Trajectory planning and tracking control for autonomous lane change maneuver based on the cooperative vehicle infrastructure system[J]. Expert Systems with Applications, 2015, 42(14):5932-5946.
[17] LAVALLE S. Planning algorithms[M]. New York:Cambridge University Press, 2006.
[18] 刘凯,龚建伟,陈舒平,等. 高速无人驾驶车辆最优运动规划与控制的动力学建模分析[J]. 机械工程学报,2018,54(14):141-151. LIU Kai, GONG Jianwei, CHEN Shuping, et al. Dynamic modeling analysis of optimal motion planning and control for high-speed self-driving vehicles[J]. Journal of Mechanical Engineering, 2018, 54(14):141-151.
[19] 余德浩,汤华中. 微分方程数值解法[M]. 北京:科学出版社,2003. YU Dehao, TANG Huazhong. Numerical method of differential equations[M]. Beijing:Science Press, 2003.
[20] 章仁燮,熊璐,余卓平,等. 基于条件积分算法的无人驾驶车辆轨迹跟踪鲁棒控制方法[J]. 机械工程学报,2018,54(18):129-139. ZHANG Renxie, XIONG Lu, YU Zhuoping, et al. Robust trajectory tracking control of autonomous vehicles based on conditional integration method[J]. Journal of Mechanical Engineering, 2018, 54(18):129-139.
[21] 孙银健. 基于模型预测控制的无人驾驶车辆轨迹跟踪控制算法研究[D]. 北京:北京理工大学, 2015. SUN Yinjian. Research on model predictive control-based trajectory tracking algorithm for unmanned vehicles[D]. Beijing:Beijing Institute of Technology, 2015.
[22] PACEJKA H. Tire and vehicle dynamics[M]. Amsterdam:Elsevier, 2005.
[23] 徐长青,许志闻,郭晓新. 计算机图形学[M]. 北京:机械工业出版社,2004. XU Changqing, XU Zhiwen, GUO Xiaoxin. Computer graphics[M]. Beijing:China Machine Press, 2004.

基于轨迹张量的自动驾驶复合信息综合映射方法

Methodology on Comprehensive Mapping of Multi-information of Autonomous Driving Based on Trajectory Tensor

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价

[1]	辛喆, 陈海亮, 林子钰, 孙恩鑫, 孙琪, 李升波. 智能汽车的路面附着极限横向轨迹跟踪控制[J]. 机械工程学报, 2020, 56(14): 138-145.
[2]	武和全, 旷世杰, 胡林. 老年乘员在自动驾驶车辆中的碰撞响应研究[J]. 机械工程学报, 2020, 56(12): 144-154.