复杂环境下基于RRT的智能车辆运动规划算法

doi:10.13973/j.cnki.robot.2015.0443

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (662 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
杜明博, 梅涛, 陈佳佳, 赵盼, 梁华为, 黄如林, 陶翔. 复杂环境下基于RRT的智能车辆运动规划算法[J]. 机器人, 2015, 37(4): 443-450.DOI: 10.13973/j.cnki.robot.2015.0443. DU Mingbo, MEI Tao, CHEN Jiajia, ZHAO Pan, LIANG Huawei, HUANG Rulin, TAO Xiang. RRT-based Motion Planning Algorithm for Intelligent Vehicle in Complex Environments. ROBOT, 2015, 37(4): 443-450. DOI: 10.13973/j.cnki.robot.2015.0443.

摘要

在存在大量无规则障碍物且障碍物分布不均匀的复杂环境下，现有规划算法不能很好地解决智能车辆的运动规划问题.为此，本文提出了一种简单实用的基于 RRT(快速搜索随机树)的运动规划算法——连续曲率 RRT 算法.该算法在 RRT 框架中结合了环境约束以及车辆自身的约束.它首先引入了目标偏向采样策略以及合理的度量函数，大大地提高了规划速度和质量；接着提出了一种基于最大曲率约束的后处理方法以生成平滑的且曲率连续的可执行轨迹.通过仿真实验和实车测试，证实了该算法的正确性、有效性和实用性.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	杜明博
	梅涛
	陈佳佳
	赵盼
	梁华为
	黄如林
	陶翔

关键词 ：运动规划, 智能车辆, 快速搜索随机树, 曲率约束

Abstract：

The existing planning algorithms can not properly solve the motion planning problem of intelligent vehicle in complex environments with many irregular and random obstacles. To solve the problem, a simple and practical RRT-based algorithm, continuous-curvature RRT algorithm, is proposed. This algorithm combines the environmental constraints and the constraints of intelligent vehicle with RRTs. Firstly, a goal-biased sampling strategy and a reasonable metric function are introduced to greatly increase the planning speed and quality. And then, a post-processing method based on the maximum curvature constraint is presented to generate a smooth, continuous-curvature and executable trajectory. Simulation experiments and real intelligent vehicle test verify the correctness, validity and practicability of this algorithm.

Key words： motion planning intelligent vehicle RRT (rapidly-exploring random tree) curvature constraint

收稿日期: 2015-02-10 录用日期: 2015-04-28

TP242

基金资助:

国家自然科学基金重大研究计划重点项目(91120307);国家自然科学基金重大研究计划集成项目(91320301);国家自然科学基金青年基金资助项目(61304100)

通讯作者: 梅涛,tmei@iim.ac.cn E-mail: tmei@iim.ac.cn

作者简介: 杜明博(1988-),男,博士生.研究领域:机器人,智能车辆,运动规划.
梅涛(1962-),男,博士,研究员.研究领域:机器人,传感器技术,人工智能.
陈佳佳(1986-),男,博士.研究领域:机器人,智能决策,机器学习.

链接本文:

https://robot.sia.cn/CN/10.13973/j.cnki.robot.2015.0443 或 https://robot.sia.cn/CN/Y2015/V37/I4/443

[1] 刘华军,杨静宇,陆建峰,等.移动机器人运动规划研究综述 [J].中国工程科学,2006,8(1):85-94. Liu H J, Yang J Y, Lu J F, et al. Research on mobile robots motion planning: A survey[J]. Engineering Science, 2006, 8(1): 85-94.

[2] 康亮,赵春霞,郭剑辉.基于模糊滚动 RRT 算法的移动机器人路径规划 [J].南京理工大学学报:自然科学版,2010,34(5):642-648. Kang L, Zhao C X, Guo J H. Path planning based on fuzzy rolling rapidly-exploring random tree for mobile robot[J]. Journal of Nanjing University of Science and Technology: Natural Science, 2010, 34(5): 642-648.

[3] 宋金泽,戴斌,单恩忠,等.一种改进的 RRT 路径规划算法 [J].电子学报,2010,38(B02):225-228. Song J Z, Dai B, Shan E Z, et al. An improved RRT path planning algorithm[J]. Acta Electronica Sinica, 2010, 38(B02): 225-228.

[4] 徐娜,陈雄,孔庆生,等.非完整约束下的机器人运动规划算法 [J].机器人,2011,33(6):666-672. Xu N, Chen X, Kong Q S, et al. Motion planning for robot with nonholonomic constraints[J]. Robot, 2011, 33(6): 666-672.

[5] Kuwata Y, Teo J, Fiore G, et al. Real-time motion planning with applications to autonomous urban driving[J]. IEEE Transactions on Control Systems Technology, 2009, 17(5): 1105-1118.

[6] Fraichard T, Scheuer A. From Reeds and Shepp's to continuous-curvature paths[J]. IEEE Transactions on Robotics, 2004, 20(6): 1025-1035.

[7] Elbanhawi M, Simic M. Randomised kinodynamic motion planning for an autonomous vehicle in semi-structured agricultural areas[J]. Biosystems Engineering, 2014, 126: 30-44.

[8] Elbanhawi M, Simic M, Jazar R. Continuous-curvature bounded trajectory planning using parametric splines[M]//Frontiers in Artificial Intelligence and Applications, vol.262. Amsterdam, Netherlands: IOS Press, 2014: 513-522.

[9] Gómez-Bravo F, Cuesta F, Ollero A, et al. Continuous curvature path generation based on β -spline curves for parking manoeuvres[J]. Robotics and Autonomous Systems, 2008, 56(4): 360-372.

[10] Du M B, Chen J J, Zhao P, et al. An improved RRT-based motion planner for autonomous vehicle in cluttered environments[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2014: 4674-4679.

[11] Lee J, Kwon O, Zhang L, et al. SR-RRT: Selective retraction-based RRT planner[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2012: 2543-2550.

[12] Rodriguez S, Tang X, Lien J M, et al. An obstacle-based rapidly-exploring random tree[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2006: 895-900.

[13] LaValle S M, Kuffner J J. Rapidly-exploring random trees: Progress and prospects[C]//4th International Workshop on Algorithmic Foundations of Robotics. Wellesley, USA: A K Peters, 2000: 293-308.

[14] Kuffner J J Jr, LaValle S M. RRT-connect: An efficient approach to single-query path planning[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2000: 995-1001.

[15] Lau B, Sprunk C, Burgard W. Kinodynamic motion planning for mobile robots using splines[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA: IEEE, 2009: 2427-2433.

[16] Koyuncu E, Inalhan G. A probabilistic B-spline motion planning algorithm for unmanned helicopters flying in dense 3D environments[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA: IEEE, 2008: 815-821.

[17] Cheng P. Reducing RRT metric sensitivity for motion planning with differential constraints[D]. Ames, USA: Iowa State University, 2001.

[18] LaValle S M. Rapidly-exploring random trees: A new tool path pla