考虑路径平滑性和避撞稳定性的智能汽车弯道轨迹规划研究

doi:10.19562/j.chinasae.qcgc.2022.05.002

汽车工程 ›› 2022, Vol. 44 ›› Issue (5): 656-663.doi: 10.19562/j.chinasae.qcgc.2022.05.002

所属专题：智能网联汽车技术专题-规划&控制2022年

考虑路径平滑性和避撞稳定性的智能汽车弯道轨迹规划研究

余嘉星^1,²,Aliasghar Arab²,裴晓飞¹(),过学迅¹

^1.湖北省汽车零部件重点实验室，武汉理工大学，武汉　430070
^2.罗格斯大学机械与航空航天工程系，新泽西，皮斯卡塔韦 ;08854 美国

收稿日期:2021-12-14 修回日期:2021-12-28 出版日期:2022-05-25 发布日期:2022-05-27
通讯作者: 裴晓飞 E-mail:peixiaofei7@whut.edu.cn
基金资助:
湖北省技术创新重大专项(2020DEB014);现代汽车零部件技术湖北省重点实验室开放基金(XDQCKF2021009)

Research on Cornering Trajectory Planning for Intelligent Vehicle Considering Trajectory Smoothness and Stability for Collision Avoidance

Jiaxing Yu^1,²,Arab Aliasghar²,Xiaofei Pei¹(),Xuexun Guo¹

^1.The Hubei Key Laboratory of Advanced Technology of Automotive Components，Wuhan University of Technology，Wuhan 　430070
^2.The Department of Mechanical and Aerospace Engineering，Rutgers University，Piscataway，NJ　08854 USA

Received:2021-12-14 Revised:2021-12-28 Online:2022-05-25 Published:2022-05-27
Contact: Xiaofei Pei E-mail:peixiaofei7@whut.edu.cn

摘要/Abstract

摘要：

针对智能汽车弯道避障问题，提出了一种兼顾规划曲线平滑度和车辆稳定性的轨迹规划方法。将轨迹规划分为解耦的路径规划和速度规划处理，利用改进的快速随机搜索树（RRT）构建曲率连续且曲率变化量最小的无碰撞的螺旋线路径。改进后的RRT基于深度神经网络的度量函数，选取并连接代价函数最小的树节点，并通过搜索附近节点寻找是否存在代价函数更小的节点。而在速度规划中首先根据道路限速规则，采用梯形规划输出连续的目标加速度曲线。然后基于螺旋线路径曲率和自车状态，采用预瞄加速度矢量控制（PGVC）动态调整目标加速度，最后通过加速度控制逻辑获得最终的期望加速度。仿真结果表明，所提出的轨迹规划方法不仅能使智能汽车满足弯道避撞和路径跟踪的目标要求，且提高了车辆高速过弯的稳定性能，同时本文还验证RRT的快速收敛性质、路径平滑性和基于并行计算的实时性。

关键词: 智能汽车, 轨迹规划, 快速随机搜索树, 速度规划, 弯道避撞

Abstract:

A trajectory planning is proposed for collision avoidance in a corner of intelligent vehicle considering trajectory smoothness and vehicle stability. The trajectory planning is decomposed into path planning and speed planning. The improved rapidly exploring random tree （RRT） is used to construct a collision-free continuous-curvature clothoids with minimum curvature change. Based on the measurement function of deep neural network， the improved RRT selects and connects the tree nodes with the smallest cost function， and searches the nearby nodes to find whether there are nodes with smaller cost function near the selected nodes. In speed planning， trapezoidal velocity profiles are used to output continuous target acceleration curve according to the road speed limit rules. Then， based on the curvature of clothoids and vehicle state， the target acceleration is dynamically adjusted by Preview G-Vectoring control （PGVC）. Finally， the final expected acceleration is obtained through acceleration control logic. The simulation results show that the proposed trajectory planning method can not only achieve collision avoidance in a corner and guarantee a good tracking performance， but also improve the stability in a corner at high speed. Besides， the paper also verifies the fast convergence， path smoothness and real-time performance based on parallel computing of RRT.

Key words: intelligent vehicle, trajectory planning, rapidly exploring random tree, speed planning, cornering collision avoidance

余嘉星,Aliasghar Arab,裴晓飞,过学迅. 考虑路径平滑性和避撞稳定性的智能汽车弯道轨迹规划研究[J]. 汽车工程, 2022, 44(5): 656-663.

Jiaxing Yu,Arab Aliasghar,Xiaofei Pei,Xuexun Guo. Research on Cornering Trajectory Planning for Intelligent Vehicle Considering Trajectory Smoothness and Stability for Collision Avoidance[J]. Automotive Engineering, 2022, 44(5): 656-663.

图/表 10

图1

表 1

改进的RRT"

$V ← x i n i t, S o l F o u n d = F a l s e$
For i=1 to i=N do
$x r ← S a m p l e (S o l F o u n d)$ ；
$x b e s t n e a r ← B e s t N e a r e s t (V, S o l F o u n d)$ ；
$S t e e r (x n e a r, x r)$ ；
$c m i n ← C o s t (x r)$ ；
If no collision and filtering?then
For each $x n e a r ∈ X n e a r$ do
$S t e e r (x n e a r, x r)$ ；
If no collision?then
$C ← C o s t (x r)$ ；
End
$x b e s t n e a r ← F i n d m i n c o s t (C, c m i n)$ ；
$x i n t e r m e d ← I n t e r m e d i a t e (x b e s t n e a r, x r)$ ；
For $x i n t e r m e d ? E$ do
$V ←$ AddNodetoTree $(x i n t e r m e d)$ ；
If $x i n t e r m e d ? X g$ then
SolFound=True；
End
End

表 1

图2

图3

图4

图5

图6

图7

图8

图9

参考文献 13

1	ESKANDARIAN A， WU C， SUN C. Research advances and challenges of autonomous and connected ground vehicles ［J］. IEEE Transactions on Intelligent Transportation Systems， 2021， 22（2）： 683-711.
2	CLAUSSMANN L， REVILLOUD M， GRUYER D， et al. A review of motion planning for highway autonomous driving ［J］. IEEE Transactions on Intelligent Transportation Systems， 2020， 21（5）： 1826-1848.
3	PAE D S， KIM G H， KANG T K， et al. Path planning based on obstacle-dependent gaussian model predictive control for autonomous driving ［J］. Applied Sciences， 2021， 11（8）： 3703.
4	DIXIT S， FALLAH S， MONTANARO U， et al. Trajectory planning and tracking for autonomous overtaking： State-of-the-art and future prospects ［J］. Annual Reviews in Control， 2018， 45： 76-86.
5	ZHANG Y， CHEN H， WASLANDER S L， et al. Speed planning for autonomous driving via convex optimization［C］. 2018 21st International Conference on Intelligent Transportation Systems （ITSC）， 2018： 1089-1094.
6	LI B,KONG Q,ZHANG Y,et al. On-road trajectory planning with spatio-temporal RRT* and always-feasible quadratic program［C］. 2020 IEEE 16th International Conference on Automation Science and Engineering （CASE）， 2020： 942-947.
7	FAN H Y，ZHU F，LIU C C，et al. Baidu apollo EM motion planner ［J/OL］. System and Control，2018.
8	夏天. 智能车速度规划及路径跟踪控制方法研究［D］. 北京：北京工业大学， 2017.
	XIA T. The research of velocity planning and path tracking control method for intelligent vehicle［D］. Beijing： Beijing University of Technology， 2017.
9	MENG Y， WU Y， GU Q， et al. A decoupled trajectory planning framework based on the integration of lattice searching and convex optimization ［J］. IEEE Access， 2019， 7： 130530-130551.
10	YU J， PEI X， GUO X， et al. Path tracking framework synthesizing robust model predictive control and stability control for autonomous vehicle ［J］. Proceedings of the Institution of Mechanical Engineers， Part D： Journal of Automobile Engineering， 2020， 234（9）： 2330-2341.
11	BERTOLAZZI E， FREGO M. On the G2 Hermite interpolation problem with clothoids ［J］. Journal of Computational and Applied Mathematics， 2018， 341： 99-116.
12	LI X， SUN Z， CAO D， et al. Development of a new integrated local trajectory planning and tracking control framework for autonomous ground vehicles ［J］. Mechanical Systems and Signal Processing， 2017， 87： 118-137.
13	TAKAHASHI J， YAMAKADO M， ZLOCKI A， et al. Development of an adaptive longitudinal control system with predicted lateral motion information［C］. 22nd Aachen Colloquium Automobile and Engine Technology， 2013： 767-789.

[1]	关书睿,李克强,周俊宇,石佳,孔伟伟,罗禹贡. 面向强制换道场景的智能网联汽车协同换道策略[J]. 汽车工程, 2024, 46(2): 201-210.
[2]	郝建平,苏炎召,钟志华,黄晋. 面向智能汽车的SOA架构及服务调度机制研究[J]. 汽车工程, 2023, 45(9): 1563-1572.
[3]	赵高士,陈龙,蔡英凤,廉玉波,王海,刘擎超,滕成龙. 融合复杂网络和记忆增强网络的轨迹预测技术[J]. 汽车工程, 2023, 45(9): 1608-1616.
[4]	胡启慧,蔡英凤,王海,陈龙,董钊志,刘擎超. 基于层次图注意的异构多目标轨迹预测方法[J]. 汽车工程, 2023, 45(8): 1448-1456.
[5]	李军, 周伟, 唐爽. 基于自适应拟合的智能车换道避障轨迹规划[J]. 汽车工程, 2023, 45(7): 1174-1183.
[6]	钱立军,陈晨,陈健. 无信控交叉口环境下考虑驾驶员误差的集中式轨迹规划[J]. 汽车工程, 2023, 45(5): 768-776.
[7]	张彬,邹渊,张旭东,孙逢春,吴喆,孟逸豪. 混动履带式无人平台轨迹跟踪控制研究[J]. 汽车工程, 2023, 45(4): 579-587.
[8]	高翔,陈龙,王歆叶,熊晓夏,李祎承,陈月霞. 基于轨迹预测的智能汽车行驶风险评估方法[J]. 汽车工程, 2023, 45(4): 588-597.
[9]	胡杰,朱琪,陈锐鹏,张敏超,张志豪,刘昊岩. 引入必经点约束的智能汽车全局路径规划[J]. 汽车工程, 2023, 45(3): 350-360.
[10]	张紫微,郑玲,李以农,乔旭强,郑浩,王戡. 考虑前车运动不确定性的多目标自适应巡航控制[J]. 汽车工程, 2023, 45(3): 361-371.
[11]	张洪昌,宁鹏,杨杰,宋建伟,郝麟,曾娟. 基于双层求解策略的平行泊车轨迹规划[J]. 汽车工程, 2023, 45(12): 2299-2309.
[12]	刘正发,吴亚,刘佩根,顾荣琦,陈广. 基于特征和标签联合分布匹配的智能驾驶跨域自适应目标检测[J]. 汽车工程, 2023, 45(11): 2082-2091.
[13]	芦勇,何一超,田贺,江昆,杨殿阁. 面向量产的自适应巡航控制系统纵向加速度规划方法研究[J]. 汽车工程, 2023, 45(10): 1803-1814.
[14]	赵树廉,来飞,李克强,陈涛,孟璋劼,唐逸超,吴思宇,田浩东. 基于数字孪生技术的智能汽车测试方法研究[J]. 汽车工程, 2023, 45(1): 42-51.
[15]	邵文博,李骏,张玉新,王红. 智能汽车预期功能安全保障关键技术[J]. 汽车工程, 2022, 44(9): 1289-1304.

考虑路径平滑性和避撞稳定性的智能汽车弯道轨迹规划研究

Research on Cornering Trajectory Planning for Intelligent Vehicle Considering Trajectory Smoothness and Stability for Collision Avoidance

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 13

相关文章 15

Metrics

本文评价

推荐阅读 10