Bayes理论在机器人信息融合中的应用  

Application of Bayesian Theory in Robotic Data 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12期4-9,共6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,研究的主要问题是: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。文章介绍了将Bayes经典推理理论应用于机器人对未知环境的探索、感知过程,确定了具体的实验方案和实现步骤,完成了一个简化的仿真算例,并通过仿真结果对该方法的有效性和性能进行了验证和评估。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 Bayesian theory to realize mobile robot＇s environmental recognition and navigation is introduced. Algorithm＇s performance based on is studied and improved by simulation results. The concrete implementation process of Bayesian theory 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 贝叶斯推理 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置]