具有状态约束的集员卡尔曼滤波器设计

Design of set-membership Kalman filter for systems with state constraints

针对状态约束问题,提出具有状态约束的集员卡尔曼滤波算法.采用最小迹椭球算法对状态向量的椭球域进行更新,同时分别在预测和滤波的两个阶段用投影的方法把没有约束的状态估计投影到有约束的状态估计表面处理约束问题.将所设计的集员卡尔曼滤波器应用到三维追踪实例中,实例仿真结果证明了所提方法的可行性和有效性.

The set- membership Kalman filtering is proposed for systems with state constraints. The algorithm of minimum trace ellipsoid is adopted to optimize the stage of time updating. At the step of prediction and filtering, the unconstrained set -membership Kalman filter is projected onto the state constraint surface respectively. The proposed algorithm is tested on a three - dimension tracking appli- cation. The simulation result shows that the method presented is available and effective.