未知环境下单目视觉移动机器人路径规划
|
摘要
针对室内未知环境下的避障和局部路径规划,提出了一种单目移动机器人路径规划算法,该算法通过对环境图像的自适应阈值分割,获取障碍物与地面交线轮廓点集。通过对现有几种单目测距方法的分析比较,提出一种改进的空间几何约束单目视觉测距计算方法,并依据单目测距的几何关系建立了图像坐标系与机器人坐标系的映射,绘建了一定比例的局部地图。在局部地图上通过改进的人工势场算法为机器人规划路径,改进的人工势场算法解决了传统算法目标点不可到达的问题。通过MATLAB进行仿真实验,结果表明该方法可以规划出有效合理的路径。
Aiming to the obstacle avoidance and local path planning in unknown indoor environments, a monocular vision-based mobile robot path planning algorithm is proposed. The contour points of the obstacles and the ground are obtained by the algorithm adaptive threshold segmented to the environment images. Analyzing and comparing the present several monocular measuring methods, a spatial geometric constrains with monocular visual measuring calculation method is improved. the mapping between the image coordinate system and the robot coordinate system is established according to the geometric relationship of monocular measuring method, and a certain scale of the local map is built. The improved artificial potential field algorithm is used for robot to plan a path in a local map. The unreachable target point problem of the traditional algorithm has been solved by the improved artificial potential field algorithm. Through MATLAB simulation experiments, the result shows that the method can plan the effective and reasonable path.
Aiming to the obstacle avoidance and local path planning in unknown indoor environments, a monocular vision-based mobile robot path planning algorithm is proposed. The contour points of the obstacles and the ground are obtained by the algorithm adaptive threshold segmented to the environment images. Analyzing and comparing the present several monocular measuring methods, a spatial geometric constrains with monocular visual measuring calculation method is improved. the mapping between the image coordinate system and the robot coordinate system is established according to the geometric relationship of monocular measuring method, and a certain scale of the local map is built. The improved artificial potential field algorithm is used for robot to plan a path in a local map. The unreachable target point problem of the traditional algorithm has been solved by the improved artificial potential field algorithm. Through MATLAB simulation experiments, the result shows that the method can plan the effective and reasonable path.
引文
[1]Mon Y J.Vision-based obstacle avoidance controller design for mobile robot by using single camera[J].International Journal of Computer Science Issues,2013.
[2]李庆,郑力新,潘书万,等.使用单目视觉的移动机器人导航方法[J].计算机工程与应用,2017,53(4):223-227.
[3]王伟,熊庆宇,王楷.面向室内未知环境的无障碍物区域单目视觉检测算法研究[C]//中国电子学会、中国振动工程学会.2010振动与噪声测试峰会论文集,2010:5.
[4]战强,吴佳.未知环境下移动机器人单目视觉导航算法[J].北京航空航天大学学报,2008,34(6):613-617.
[5]Lee T J L,Yi D H,Cho D I.A monocular vision sensorbased obstacle detection algorithm for autonomous robots[J].Sensors,2016,16(3):311.
[6]陈祥章.基于单目视觉的机器人人工势场法路径规划研究[J].南京师大学报:自然科学版,2014,37(1):61-65.
[7]Siegwart R,Nourbakhsh I R.自主移动机器人导论[M].2版.李人厚,宋青松,译.西安:西安交通大学出版社,2013.
[8]陈易婷.基于单目视觉的移动智能机器人的导航定位技术的研究和应用[D].成都:电子科技大学,2016.
[9]林剑冰,苏成悦,郑俊波,等.机器视觉导引的室内自动运输车定位系统[J].机械科学与技术,2015,34(11):1675-1681.
[10]李惠光,李金超,李国友,等.双向型单目视觉自动导引车路径识别及测量[J].计算机工程与应用,2015,51(8):260-265.
[11]吴刚,唐振民.单目式自主机器人视觉导航中的测距研究[J].机器人,2010,32(6):828-832.
[12]单宝明,周培培.基于改进人工势场法的机器人路径规划研究[J].信息技术,2014(1):170-173.
[13]王超,朱大奇.基于人工势场与速度合成的AUV路径规划[J].控制工程,2015,22(3):418-424.
[14]Luo Nengqiang,Liu Li,Gong Dongying,et al.Study on robot path planning based on an improved artificial potential field method[J].通讯和计算机:中英文版,2013(10):1360-1363.
[15]Ni Tianwei,Jiang Hong,Lin Jinzhu,et al.An anti-collision path planning algorithm based on improved artificial potential field method for mobile robot[J].Journal of Changzhou University:Natural Science Edition,2016(5).
[2]李庆,郑力新,潘书万,等.使用单目视觉的移动机器人导航方法[J].计算机工程与应用,2017,53(4):223-227.
[3]王伟,熊庆宇,王楷.面向室内未知环境的无障碍物区域单目视觉检测算法研究[C]//中国电子学会、中国振动工程学会.2010振动与噪声测试峰会论文集,2010:5.
[4]战强,吴佳.未知环境下移动机器人单目视觉导航算法[J].北京航空航天大学学报,2008,34(6):613-617.
[5]Lee T J L,Yi D H,Cho D I.A monocular vision sensorbased obstacle detection algorithm for autonomous robots[J].Sensors,2016,16(3):311.
[6]陈祥章.基于单目视觉的机器人人工势场法路径规划研究[J].南京师大学报:自然科学版,2014,37(1):61-65.
[7]Siegwart R,Nourbakhsh I R.自主移动机器人导论[M].2版.李人厚,宋青松,译.西安:西安交通大学出版社,2013.
[8]陈易婷.基于单目视觉的移动智能机器人的导航定位技术的研究和应用[D].成都:电子科技大学,2016.
[9]林剑冰,苏成悦,郑俊波,等.机器视觉导引的室内自动运输车定位系统[J].机械科学与技术,2015,34(11):1675-1681.
[10]李惠光,李金超,李国友,等.双向型单目视觉自动导引车路径识别及测量[J].计算机工程与应用,2015,51(8):260-265.
[11]吴刚,唐振民.单目式自主机器人视觉导航中的测距研究[J].机器人,2010,32(6):828-832.
[12]单宝明,周培培.基于改进人工势场法的机器人路径规划研究[J].信息技术,2014(1):170-173.
[13]王超,朱大奇.基于人工势场与速度合成的AUV路径规划[J].控制工程,2015,22(3):418-424.
[14]Luo Nengqiang,Liu Li,Gong Dongying,et al.Study on robot path planning based on an improved artificial potential field method[J].通讯和计算机:中英文版,2013(10):1360-1363.
[15]Ni Tianwei,Jiang Hong,Lin Jinzhu,et al.An anti-collision path planning algorithm based on improved artificial potential field method for mobile robot[J].Journal of Changzhou University:Natural Science Edition,2016(5).