针对粒子滤波固有的问题,结合在移动机器人蒙特卡罗定位中的最新应用成果,分别从建议分布的选择、重采样策略的改进、有效推理的执行、自适应机制的引入、与其他方法的集成等几个方面对其当前研究的关键技术进行了归纳总结,并对该研究领域需要解决的研究难点进行了分析,展望了进一步研究的方向。
Aimed at the inherent deficiency in particle filter and based on the up-to-date research about Monte Carlo localization for mobile robot, some key technologies in current research were respectively summarized from the aspect of the choice of proposal distribution, the improvement of resampling strategy, the implement of effective inference, the introduce of adaptive mechanism and the integration with other methods. At the same time, the main challenges that need to be solved in this field were analyzed and some future trends about the technology of these difficulties were also presented.