TITLE:
A Robust Hybrid Multisource Data Fusion Approach for Vehicle Localization
AUTHORS:
Adda Redouane Ahmed Bacha, Dominique Gruyer, Alain Lambert
KEYWORDS:
Localization; Mobile Robotic; Kalman Filter; EKF; Particle Swarm Optimization; PSO; Particle Filter; Data Fusion; Vehicle Positioning; Navigation; GPS
JOURNAL NAME:
Positioning,
Vol.4 No.4,
November
13,
2013
ABSTRACT:
In this paper, an innovative collaborative data
fusion approach to ego-vehicle localization is presented. This approach called Optimized Kalman
Swarm (OKS) is a data fusion and filtering method, fusing data from a low cost
GPS, an INS, an Odometer and a Steering wheel angle encoder. The OKS is
developed addressing the challenge of managing reactivity and robustness during a real time
ego-localization process. For ego-vehicle localization, especially for highly dynamic on-road maneuvers, a filter
needs to be robust and reactive at the same time. In these situations, the
balance between reactivity
and robustness concepts is crucial. The OKS filter represents an intelligent
cooperative-reactive localization algorithm inspired by dynamic Particle Swarm Optimization (PSO).
It combines advantages coming from two filters: Particle Filter (PF) and
Extended Kalman filter (EKF). The OKS is tested using real embedded sensors
data collected in the Satory’s test tracks. The OKS is also compared with both
the well-known EKF and the
Particle Filters (PF). The results show the efficiency of the OKS for a high
dynamic driving scenario with damaged and low quality GPS data.