移动机器人SLAM与路径规划在ROS框架下的实现  

SLAM and path planning of mobile robot in ROS framework

作　　者：陈卓[1] 苏卫华[1] 安慰宁 秦晓丽[1] 

机构地区：[1]军事医学科学院卫生装备研究所,天津300161

出　　处：《医疗卫生装备》2017年第2期109-113,共5页Chinese Medical Equipment Journal

基　　金：原总后卫生部重点项目(BWS14C054);军队后勤科研计划重大项目(AWS16J001);天津科技支撑计划重点研发计划(16YFZCSF00590)

摘　　要：目的:实现移动机器人的即时定位与地图构建(simultaneous localization and mapping,SLAM)和路径规划,解决移动过程中的数据关联实时性问题和更新状态协方差矩阵的计算复杂度问题。方法:建立SLAM问题的数学模型,通过分析对比,选用基于粒子滤波器的Fast Slam算法并结合A*和动态窗口法(dynamic window approach,DWA)在ROS(robot operating system)框架下编写gmapping功能包。结果:实现了移动机器人在ROS框架下的运动实验仿真、路径规划和动态避障。结论:利用ROS平台,移动机器人在完成自身定位和地图构建的同时能够实时、高效地完成路径轨迹规划。Objective To realize SLAM and path planning of mobile robot to solve the problem of real-time data association in the process of moving and to update the computational complexity of the state covariance matrix. Methods The mathematical model of SLAM was built, and Fast Slam algorithm based on particle filter, A＊ and dynamic window approach（DWA） were used to prepare gmapping function package in the ROS framework. Results The motion simulation, path planning and dynamic obstacle avoidance of mobile robot in the ROS framework were realized. Conclusion By using ROS platform, mobile robots can execute path planning efficiently while completing self-localization and map building.

关 键 词：移动机器人 SLAM 路径规划 ROS 算法实现 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]