作者：王中立, 牛颖

作者单位：太原理工大学信息工程学院, 山西 太原 030024

关键词：障碍物检测;信息融合;联合卡尔曼滤波;视觉传感器;Zernike矩;Hough变换

摘要：

针对单一传感器在机器人避障过程中不能全面且准确定位障碍物的缺点，提出基于多传感器信息融合的障碍物检测方法。第一阶段使用视觉传感器检测未知环境中的障碍物，通过Zernike矩边缘检测方法提取障碍物图像边缘，然后采用Hough变换原理提取障碍物的直线特征，获得障碍物大概位置；第二阶段使用超声波传感器和红外传感器对障碍物进行检测，获得障碍物准确位置；最后使用联合卡尔曼滤波对3种传感器获得的信息进行融合，得出融合后的障碍物位置信息。实验结果表明：该方法克服视觉传感器、超声波传感器和红外传感器的局限性，可以精确感知机器人周围的未知环境信息，并能够检测和定位机器人路径上的障碍物，定位误差6 cm，满足机器人避障的实时性和可靠性需求。

Obstacle detection of robot based on multi-sensor information fusion

WANG Zhongli, NIU Ying

College of Information Engineering, Taiyuan University of Technology, Taiyuan 030024, China

Abstract: Aiming at the shortcoming that the single sensor could not locate the obstacle completely and accurately in the process of obstacle avoidance of the robot, an obstacle detection method based on multi-sensor information fusion was proposed. Firstly, vision sensor was used to detect the obstacle in unknown environment. The edge of the obstacle image was extracted by the Zernike moment edge detection method, then the Hough transform principle was used to extract the straight line feature of the obstacle, so as to obtain the approximate position of the obstacle. Secondly, ultrasonic sensor and infrared sensor were used to detect the obstacle to obtain the exact position of obstacles. Finally, the federated Kalman filter was used to fuse the information obtained by the three sensors to gain information of the obstacle position after fusion. The test result shows that this method can overcome the limitations of vision sensors, ultrasonic sensors and infrared sensors, and can accurately detect the unknown environmental information around the robot and detect and locate the obstacles on the path of robot with positioning error less than 6 cm, meeting the real-time and reliability of robot obstacle avoidance.

Keywords: obstacle detection;information fusion;federated Kalman filter;vision sensor;Zernike moment;Hough transform

2017, 43(8): 80-85  收稿日期: 2017-03-13;收到修改稿日期: 2017-04-21

基金项目: 

作者简介: 王中立(1989-),男,山东菏泽市人,硕士研究生,专业方向为检测技术与智能仪表。

参考文献

[1] 李灿. 智能移动机器人导航策略研究与实现[D]. 杭州:浙江工业大学,2013.
[2] 程虹霞,骆云志,朱松柏,等. 多传感器信息融合技术在无人平台避障中的应用[J]. 兵工自动化,2010,29(6):89-91.
[3] 宋明月. 基于多传感器信息融合的关键技术的研究[D].哈尔滨:哈尔滨工程大学,2011.
[4] 咸宝金. 基于专家系统的数据融合技术及在机器人避障中的应用[D]. 北京:北方工业大学,2008.
[5] 崔平远,黄晓瑞. 基于联合卡尔曼滤波的多传感器信息融合算法及其应用[J]. 电机与控制学报,2001,5(3):204-207.
[6] 唐建平,宋红生,王东署. 一种移动机器人动态环境下的路径规划[J]. 郑州大学学报(理学版),2012,44(1):75-78.
[7] 龙清. 图像边缘检测中的微分算子法及其比较[J]. 信息技术,2011(6):98-101.
[8] 蔡小帅,张荣国,李富萍,等. 基于Zernike矩的模糊与仿射混合不变量研究[J]. 计算机工程,2014,40(11):215-219.
[9] 李金泉,陈善本,吴林. 一种基于Zernike矩的直线提取算法[J]. 光电子·激光,2003,14(8):851-854.
[10] 杨全银. 基于Hough变换的图像形状特征检测[D]. 济南:山东大学,2009.
[11] 杨芳沛,李伟光,郑少华,等. 基于超声波传感器的AGV避障模块设计与实现[J]. 电子设计工程,2015,23(22):56-60.
[12] 闫俊旭,侯超. 基于红外反射式光电传感器的智能循迹小车[J]. 山西电子技术,2012(2):34-35.
[13] 刘国海,李沁雪,施维,等. 动态卡尔曼滤波在导航试验状态估计中的应用[J]. 仪器仪表学报,2009,30(2):396-400.