Road network based vehicle navigation using an improved imm particle filter

This paper presents an improved interacting multiple model (IMM) algorithm for vehicle navigation using road network information. Incorporating extra information like a digital road map can significantly enhance the navigation performance of an intelligent vehicle especially when the standard positioning sensor losses accuracy due to obstruction. The proposed algorithm uses multiple models to associate the vehicle to different road sections, so that the corresponding information, such as road width, speed limits, can be taken into account as system constraints. An IMM filter that can deal with the model constraints is then developed based on the Bayesian framework. The mode transition governed by a state-dependent probability is also embedded in it. The derived Bayesian filter is implemented using a particle filter solution. Comparison results are included to show its performance against some existing algorithms for a vehicle travelling in an urban environment.