Particle Swarm Optimization for Vehicle Positioning Based on Robust Cubature Kalman Filter

Abstract

This paper is concerned with the particle swarm optimization (PSO) based adaptive solution of a robust cubature Kalman filter (RCKF) for data fusion in land vehicle positioning. The cubature rule applied in the cubature Kalman filter is employed to solve the nonlinearity in system and measurement models. With the principle of bounded error covariance, a robust filtering solution is derived to provide tolerance to model uncertainties and the nonlinear approximation errors. On this basis, particle swarm optimization is adopted to assist the original RCKF algorithm and improve the estimation performance by adjusting the restraint coefficient, which is designed as a key parameter. Thus, a novel PSO-assisted robust Kalman filtering scheme is proposed for both the adaption and robustness performance. Simulation analysis and discussions are given to illustrate capabilities and advantages of the proposed filtering solution.

Swarm intelligence algorithm inspired by route choice behavior

“…Guidance information acquisition is dependent on market penetration of guidance information systems. The availability of guidance information systems overshadows guidance information accuracy, and traveler characteristics determine guidance 5 information acceptance. In RCBA, at each step, particles' choice of a solution is also probabilistic, analogous to route choice probabilistic behavior.…”

“…because of a particular fitness value for the solution, according to CPT. Considering the priority of the guidance solution, the probability of choosing the historical solution can be calculated using equation (5).…”

“…Other examples include the ant colony optimization (ACO) [2,3], the particle swarm optimization (PSO) [4][5][6][7][8], the artificial fish swarm algorithm (AFSA) [9], , the quantum multi-agent evolutionary algorithm（QMAEA） [10], the firefly algorithm (FA) [11], and the bacteria foraging optimization (BFO) [12]. Tao et al [13,14] proposed the idea of configurable intelligent optimization algorithms (CIOA), and a framework for CIOA have been studied and a series of algorithms have been developed based on the idea and framework, which are employed for addressing green material selection [15], dynamic migration of virtual machines [16], energy-aware cloud service scheduling [17], multi-objective service composition and optimal-selection [18][19][20], and so on.…”

Particle Smoother for Nonlinear Systems With One‐Step Randomly Delayed Measurements

“…Consider the following discrete‐time nonlinear stochastic system as shown by the state‐space model : and the one‐step randomly delayed measurement model where z k is the ideal (undelayed) measurement vector, y k is the actual (available) measurement vector, process noise n k and measurement noise v k are independent white processes with arbitrary PDFs. γ 1 = 0 and γ k ( k ⩾2) is the Bernoulli random variable taking the value of zero or one with known probability p ( γ k = 1) = p k ( k ⩾2), and p k denotes the latency probability and p k ∈[0,1].…”

Indoor Tracking by RFID Fusion with IMU Data

“…For example, Liu et al. proposed a data fusion method for land vehicle positioning in , where an adaptive solution of a robust cubature Kalman filter (RCKF) was given based on the particle swarm optimization (PSO). Urrea C et al.…”