万有引力优化的粒子滤波算法

针对经典粒子滤波中存在的粒子易退化、易丧失多样性以及滤波精度严重依赖于粒子数量的问题，提出一种万有引力优化的粒子滤波算法．通过万有引力算法优化粒子滤波中的粒子集来提高滤波精度．首先将每个粒子看做质量大小正比于粒子权值的点，粒子间的引力吸引着粒子向高似然区域移动，从而优化粒子集．然后利用精英粒子策略加快万有引力优化算法中粒子收敛速度，并避免粒子陷入局部最优; 引入感知模型防止过度收敛导致的粒子拥挤或重叠．仿真实验表明，该算法在粒子数较少的情况下与经典粒子滤波算法和粒子群优化粒子滤波算法相比，保持了更好的粒子滤波精度和速度．

Gravity optimized particle filter algorithm

As the traditional particle filter has problems of particle degeneracy and particle diversity loss and filter accuracy depends heavily on the particle number, a gravity optimized particle filter algorithm is proposed.The particle swarm is optimized by the gravity algorithm in the particle filter to improve the filtering accuracy. Each particle is regarded as a mass point and the mass is proportional to the particle weight.The gravity attracts particles moving toward the high likelihood region which optimizes the particle swarm.Then elite particle strategy is introduced to accelerate the particle convergence rate and avoid the local optimum in the gravity algorithm. The perceptual model is used to prevent particles from crowding or overlapping due to excessive convergence. Simulation results show that the proposed algorithm has a better filtering accuracy and speed in the case of few particles compared with the classical particle filter algorithm and particle swarm optimization particle filter algorithm.