论文部分内容阅读
错误的数据关联会降低SLAM算法的性能。为提高数据关联率,提出了基于人工鱼群算法的SLAM数据关联方法,利用启发式信息,根据状态转移概率和轮盘赌策略,建立鱼群状态量与所求解的对应关系,通过寻求最优人工鱼的状态从而获得最优解;同时使用混沌初始化鱼群,采用自适应的步长和拥挤度因子加快算法的收敛速度,在聚群和追尾行为后进行混沌优化,使人工鱼跳出局部极值点,从而获得全局最优解。最后针对无人机SLAM的数据关联问题,利用算法进行仿真试验,结果表明该方法是有效可行的。
Incorrect data association can degrade the performance of the SLAM algorithm. In order to improve the data association rate, an SLAM data association method based on artificial fish swarm algorithm is proposed. By using heuristic information, the state transition probability and roulette strategy are used to establish the corresponding relationship between the quantity of fish and the solution. Artificial fish state to obtain the optimal solution; At the same time using chaos to initialize the fish, using adaptive step and congestion factor to speed up the convergence rate of the algorithm, cluster and rear-end behavior of chaos optimization, artificial fish out of the local pole Value point, so as to obtain the global optimal solution. Finally, according to the data association problem of UAV SLAM, the algorithm is used to simulate the experiment. The results show that this method is effective and feasible.