Integrated recursive least square lattice and neuro-fuzzy modules for mobile multi-sensor data fusion

The last two decades have witnessed an increasing trend in integrating different navigation systems to overcome the limitations of the stand-alone operation of such systems. For instance, GPS is usually combined with Inertial Navigation System (INS) in several navigation applications. Most of the INS/GPS integration techniques relied on Kalman filtering (KF). Recently, artificial intelligence based techniques were also introduced to replace KF. In order to avoid some of the limitations of the present techniques, this paper introduces multi-sensor systems integration using Recursive Least Square Lattice (RLSL) filter along with an artificial intelligence technique based on Adaptive Neuro-Fuzzy Inference System (ANFIS). The proposed technique was examined with field test data conducted in a land vehicle using a tactical grade INS (Honeywell HG1700) integrated with Differential GPS measurements collected by a NovAtel OEM4 GPS receiver. The results indicate that the proposed RLSL/neuro-fuzzy system is robust in providing a reliable real-time INS/GPS integration module.