基于非结构化环境点云稀疏表示的无人驾驶汽车局部路径规划方法

doi:10.3901/JME.2020.02.163

机械工程学报 ›› 2020, Vol. 56 ›› Issue (2): 163-173.doi: 10.3901/JME.2020.02.163

扫码分享

基于非结构化环境点云稀疏表示的无人驾驶汽车局部路径规划方法

刘梓林¹, 黎予生^2,3, 郑玲^3,4

1. 重庆大学机械工程学院重庆 400044;
2. 长安汽车股份有限公司汽车工程智能化研究院重庆 401120;
3. "国家2011计划"-重庆自主品牌汽车协同创新中心重庆 400044;
4. 重庆大学汽车工程学院重庆 400044

收稿日期:2019-02-15 修回日期:2019-10-21 出版日期:2020-01-20 发布日期:2020-03-11
通讯作者: 黎予生(通信作者),男,1960年出生,博士,研究员,博士研究生导师。主要研究方向为主动安全、智能车辆平台技术、智能车辆网联技术。E-mail:liys@changan.com.cn
作者简介:刘梓林,男,1988年出生,博士研究生。主要研究方向为智能汽车自主导航、高精度定位及环境重构。E-mail:zilinliu@foxmail.com;郑玲,女,1963年出生,博士,教授,重庆大学汽车系主任,博士研究生导师。主要研究方向为智能汽车的环境感知、决策与动力学控制。E-mail:zling@cqu.edu.cn
基金资助:
国家自然科学基金（51875061）和中国汽车产业创新发展联合基金重点（U1564208）资助项目。

Local Path Planning for Autonomous Vehicles Based on Sparse Representation of Point Cloud in Unstructured Environments

LIU Zilin¹, LI Yusheng^2,3, ZHENG Ling^3,4

1. College of Mechanical Engineering, ChongQing University, Chongqing 400044;
2. Chongqing Changan Auto R&D Center, Changan Automobile Co., Ltd., Chongqing 401120;
3. Chongqing Automotive Collaborative Innovation Center, Chongqing 400044;
4. School of Automative Engineering, Chongqing University, Chongqing 400044

Received:2019-02-15 Revised:2019-10-21 Online:2020-01-20 Published:2020-03-11

摘要/Abstract

摘要： 非结构化环境下，无人驾驶汽车的局部路径规划方法面临数据冗余及环境结构适用性问题。提出一种基于3维Lidar数据稀疏表示的局部路径规划建模方法——势场字典法（Potential field dictionary，PFD）。该方法以预置本地过完备DCT字典替代正交基，应用投影追踪方法（MP）结合环境采样预处理结果，对Lidar点云信息进行稀疏化分解；直接将稀疏分解矢量用于势场法局部路径规划，并提出"动态势场"以应对非结构化环境。实车试验表明：环境采样预处理结果储存空间小，且更能体现结构复杂程度；PFD算法以小稀疏度可以规划出完整连续可行路径，且性能优于RRT*算法以及传统势场算法。PFD算法在保证信息表达精度的前提下，减少了数据传输、储存成本，也可规划出适用于非结构化环境的局部路径。

关键词: 局部路径规划, 非结构化环境, 稀疏表示, 势场字典法*

Abstract: The local path planning methods for autonomous vehicles face the data redundancy and the applicability to the environmental structure in unstructured environments. A modeling method using the sparse representation of 3D Lidar data is presented, which is called potential field dictionary(PFD). The environmental sampling pretreatment results of Lidar signal are sparsely decomposed with Match Pursuit algorithm(MP), whose orthonormal basis is replaced by a preset over-complete DCT dictionary; the sparse decomposition vector is directly applied to the potential field method of the local path planning; dynamic potential field is used to deal with unstructured environments. The results of vehicle test show that the preprocessing result needs little storage space and can express the complexity of the environmental structure better. Afterwards, the PFD algorithm can plan full sequential feasible paths with small sparsity and its performance is superior to the traditional potential field method and RRT* method. The PFD algorithm can reduce the costs of data transmission and storage on the premise of the precision of surrounding information and plan feasible local paths in unstructured environments.

Key words: local path planning, unstructured environments, sparse representation, potential field dictionary

中图分类号:

TG156

刘梓林, 黎予生, 郑玲. 基于非结构化环境点云稀疏表示的无人驾驶汽车局部路径规划方法[J]. 机械工程学报, 2020, 56(2): 163-173.

LIU Zilin, LI Yusheng, ZHENG Ling. Local Path Planning for Autonomous Vehicles Based on Sparse Representation of Point Cloud in Unstructured Environments[J]. Journal of Mechanical Engineering, 2020, 56(2): 163-173.

参考文献

[1] 姜岩,王琦,龚建伟,等. 无人驾驶车辆局部路径规划的时间一致性与鲁棒性研究[J]. 自动化学报,2015,41(3):518-527. JIANG Yan,WANG Qi,GONG Jianwei,et al. Research on temporal consistency and robustness in local planning of intelligent vehicles[J]. Acta Automatica Sinica,2015,41(3):518-527.
[2] 江浩斌,沈峥楠,马世典,等. 基于信息融合的自动泊车系统车位智能识别[J]. 机械工程学报,2017,53(22):125-133. JIANG Haobin,SHEN Zhengnan,MA Shidian,et al. Intelligent identification of automatic parking system based on information fusion[J]. Journal of Mechanical Engineering,2017,53(22):125-133.
[3] On-Road Automated Vehicle Standards Committee,Society of Automotive Engineers. SAE J3016 Taxonomy and definitions for terms related to on-road motor vehicle automated driving systems[S]. Warrendale:SAE International,2016.
[4] URMSON C,ANHALT J,BAGNELL D,et al. Autonomous driving in urban environments:boss and the urban challenge[J]. Journal of Field Robotics,2008,25(8):425-466.
[5] 姜岩,赵熙俊,龚建伟,等. 简单城市环境下地面无人驾驶系统的设计研究[J]. 机械工程学报,2012,48(20):103-112. JIANG Yan,ZHAO Xijun,GONG Jianwei,et al. System design of self-driving in simplified urban environments[J]. Journal of Mechanical Engineering,2012,48(20):103-112.
[6] VON H F,HIMMELSBACH M,HECKER F,et al. Driving with tentacles:Integral structures for sensing and motion[J]. Journal of Field Robotics,2008,25(9):640-673.
[7] HART P E,NILSSON N J,RAPHAEL B. A formal basis for the heuristic determination of minimum cost paths[J]. IEEE Transactions on Systems Science and Cybernetics,1968,4(2):100-107.
[8] FERGUSON D,STENTZ A. Using interpolation to improve path planning:The field D* algorithm[J]. Journal of Field Robotics,2006,23(2):79-101.
[9] LIKHACHEV M,FERGUSON D. Planning long dynamically feasible maneuvers for autonomous vehicles[J]. The International Journal of Robotics Research,2009,28(8):933-945.
[10] DOLGOV D,THRUN S,MONTEMERLO M,et al. Path planning for autonomous vehicles in unknown semi-structured environments[J]. International Journal of Robotics Research,2010,29(5):485-501.
[11] LAVALLE S M. Rapidly-Exploring random trees:a new tool for path planning[J]. Algorithmic & Computational Robotics New Directions,1998,11(3):293-308.
[12] ELBANHAWI M,SIMIC M. Randomised kinodynamic motion planning for an autonomous vehicle in semi-structured agricultural areas[J]. Biosystems Engineering, 2014,126(39):30-44.
[13] LEE J,KWON O,ZHANG L,et al. A selective retraction-based RRT planner for various environments[J]. IEEE Transactions on Robotics,2014,30(4):1002-1011.
[14] MONTIEL O,OROZCO-ROSAS U,SEPÚLVEDA R. Path planning for mobile robots using bacterial potential field for avoiding static and dynamic obstacles[J]. Expert Systems with Applications,2015,42(12):5177-5191.
[15] 王其东,魏振亚,陈无畏,等. 基于参数时变人工势场的车道保持协调控制[J]. 机械工程学报,2018,54(18):105-114. WANG Qidong, WEI Zhenya, CHEN Wuwei,et al. Lane keeping coordination control based on parameter-varying artificial potential field[J]. Journal of Mechanical Engineering,2018,54(18):105-114.
[16] MALONE N,CHIANG H T,LESSER K,et al. Hybrid dynamic moving obstacle avoidance using a stochastic reachable set-based potential field[J]. IEEE Transactions on Robotics,2017(99):1-15.

基于非结构化环境点云稀疏表示的无人驾驶汽车局部路径规划方法

Local Path Planning for Autonomous Vehicles Based on Sparse Representation of Point Cloud in Unstructured Environments

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 12

编辑推荐

Metrics

本文评价

[1]	焦敬品, 孙延东, 李光海, 赵鹏经, 吴斌, 何存富. 基于声发射信号稀疏表示的铝合金板材拉伸过程识别方法[J]. 机械工程学报, 2024, 60(2): 1-9.
[2]	徐亚飞, 王星雨, 钟舜聪, 张留洋, 陈雪峰. 基于稀疏表示的叶片热障涂层太赫兹检测回波信号定位分离方法[J]. 机械工程学报, 2023, 59(8): 9-19.
[3]	陆向宁, 刘凡, 何贞志, 廖广兰, 史铁林. 稀疏重构SAM芯片焊点检测方法研究[J]. 机械工程学报, 2023, 59(6): 95-102.
[4]	张晗, 田毅, 杜朝辉. 基于时变噪声结构的自适应加权稀疏模型及航空轴承故障诊断[J]. 机械工程学报, 2023, 59(17): 162-174.
[5]	郑琛, 丁康, 何国林, 林慧斌, 蒋飞. 冲击响应机理驱动稀疏表示自编码网络的滚动轴承故障特征提取[J]. 机械工程学报, 2023, 59(13): 175-183.
[6]	王华庆, 任帮月, 宋浏阳, 董方, 王梦阳. 基于终止准则改进K-SVD字典学习的稀疏表示特征增强方法[J]. 机械工程学报, 2019, 55(7): 35-43.
[7]	郭俊锋, 石斌, 魏兴春, 李海燕, 王智明. 基于K-SVD字典学习算法的稀疏表示振动信号压缩测量重构方法[J]. 机械工程学报, 2018, 54(7): 97-106.
[8]	郭俊锋, 石斌, 雷春丽, 魏兴春, 李海燕. 基于双稀疏字典模型机械振动信号压缩感知方法[J]. 机械工程学报, 2018, 54(6): 118-127.
[9]	贺王鹏, 訾艳阳, 陈彬强, 姚斌, 张周锁. 周期稀疏导向超小波在风力发电设备发电机轴承故障诊断中的应用[J]. 机械工程学报, 2016, 52(3): 41-48.
[10]	樊薇李双蔡改改沈长青黄伟国朱忠奎. 瞬态成分Laplace小波稀疏表示及其轴承故障特征提取应用[J]. 机械工程学报, 2015, 51(15): 110-118.
[11]	栗茂林;梁霖;王孙安. 基于稀疏表示的故障敏感特征提取方法[J]. , 2013, 49(1): 73-80.
[12]	姜岩;赵熙俊;龚建伟;熊光明;陈慧岩. 简单城市环境下地面无人驾驶系统的设计研究[J]. , 2012, 48(20): 103-112.