D-S证据理论在移动机器人信息融合中的应用  

Application of D-S Evidence Theory in Mobile Robotic Sensor Fusion

作　　者：余华[1] 吴文全[1] 刘忠[1] 

机构地区：[1]海军工程大学电子工程学院,武汉430033

出　　处：《计算机与数字工程》2009年第11期125-129,共5页Computer & Digital Engineering

基　　金：国家"八六三"项目"基于多智能体的传感器网络协同目标跟踪技术研究"(编号:2007ADA299)资助

摘　　要：移动机器人的自动能力中实时避障和导航是一个很关键的技术,研究中主要的问题是:机器人在运动时需要充分的环境信息,而且处理这些信息的速度要快,同时也要满足实时性的要求。详细介绍了将D-S证据理论应用于移动机器人对未知环境的探索、感知过程,并通过仿真结果对D-S证据融合方法的性能进行研究与改进,确定了D-S证据融合方案的具体实现步骤,并完成了一个简化的仿真算例,得出了相关结论。The key technology in the automatic ability of mobile robot is real-time obstacle avoidance and navigation. The main problem in research is that mobile-robot need plenty of environmental information when moving and the information should be processed with rapid speed to satisfy real-time request. The data fusion method based on Dempster- Sharer evidence theory to realize mobile robot＇s environmental recognition and navigation is specifically introduced. Algorithm＇s performance based on D-S evidence theory is studied and improved by simulation results. The concrete implementation process of D-S evidence data fusion method is determined and an simplified simulation is finished. The simulation results show the relational conclusion.

关 键 词：移动机器人 环境建模与导航 信息融合 DEMPSTER-SHAFER证据理论 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置]