基于Kinect的移动机器人实时局部路径规划  

Real-time Local Path Planning for Mobile Robot Based on Kinect

作　　者：于振中 郑为凑 刘鑫 惠晶 

机构地区：[1]江南大学轻工过程先进控制教育部重点实验室,江苏无锡214122

出　　处：《计算机工程》2013年第4期243-247,共5页Computer Engineering

基　　金：中央高校基本科研业务费专项基金资助项目(JUSRP11A48)

摘　　要：传统路径规划方法计算复杂、效率低,且误差较高。为此,提出一种基于Kinect的移动机器人实时局部路径规划方法。利用Kinect产生的RGB图像和3D图像实时获取移动机器人的周边动态环境信息,通过模糊逻辑和信息融合技术完成机器人的实时路径规划,从而实现机器人的目标跟踪与导航。实验结果表明,该方法具有较好的稳定性与实时性。Traditional path planning method exists the problem that the calculation is complex, efficiency is low, and has high error. In order to solve this problem, this paper proposes a real-time local path planning method for mobile robot based on Kinect. This paper uses RGB images and 3D images produced by Kinect to get the real-time peripheral dynamic environmental information of mobile robot, uses the fuzzy logic and information fusion technology to realize real-time path planning for the robot in dynamic environment, so as to solve the problem of robot target tracking and navigation. Experimental results show that this method has good stability and real-time.

关 键 词：Kinect传感器 模糊理论 路径规划 移动机器人 环境感知 视觉传感 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]