论文部分内容阅读
为了提高粒子滤波算法在机器人定位中的性能,在基本粒子滤波算法的基础上,引入概率回退的方法对机器人的初始状态进行估计,采用窗口滤波更新粒子集合,根据对机器人位置估计的情况动态更新粒子集合的大小,得到一种改进的粒子滤波算法——稳健的自适应粒子滤波算法。仿真结果表明:该算法充分利用了对机器人位置估计的有效信息,在显著提高算法稳健性的同时,降低了运算复杂度,较好地解决了机器人定位这一非线性非Gauss状态在线估计问题。
In order to improve the performance of particle filter algorithm in robot localization, based on the basic particle filter algorithm, the initial state of the robot is estimated by introducing the method of probability regression, and the particle set is updated by using window filter. According to the situation of robot position estimation By updating the size of the particle set, an improved particle filter algorithm - a robust adaptive particle filter algorithm is obtained. The simulation results show that this algorithm makes full use of the effective information of the robot position estimation, reduces the computational complexity while significantly improving the robustness of the algorithm, and solves the problem of online positioning of the robot in a nonlinear non-Gauss state.