基于多模态进化Rao-Blackwellized 粒子滤波器的 移动机器人航迹推算系统的故障诊断

针对一类移动机器人航迹推算系统的故障诊断问题, 提出一种多模态进化Rao-Blackwellized 粒子滤波
器(MERBPF) 算法. 为解决由粒子贫乏引起的不一致性问题, 采用交叉与变异种群策略优化, 根据粒子多样性加入扰
动因子. 利用专家规则判定机器人运动状态所对应的MERBPF, 构造复杂逻辑表述方法. 仿真实验结果表明: 在强过
程噪声下, MERBPF 仍具有较高的鲁棒性, 提高了诊断机器人航迹推算系统的准确率.

Fault diagnosis for mobile-robot dead reckoning system based on multimodality evolutionary Rao-Blackwellized particle filter

A multi-modality evolutionary Rao-Blackwellized particle filter(MERBPF) algorithm is proposed for mobilerobot
fault diagnosis of dead reckoning system. The inconsistency from particle degeneration problem is solved by integrating
swarms’ intercross and mutation strategy and adding disturbance factors accoding to diversity. Robot moving states are
determined by expert rules reasoning mechanism and monitored by each different ERBPF. Finally, the multi-modality
ERBPF is formed, which expresses complex logic clearly. The experimental results show that MERBPF maintains a strong
robustness even under the strong process noise, which improves the accuracy for the fault diagnosis of robot’s dead reckoning
investigation system.