Implementation of Anfis for GPS-Aided Ins Uav Motion Sensing at Short Term GPS Outage

Abstract

The recent improvement in Micro-Electro-Mechanical System (MEMS) technology has enabled the evolvement of Inertial Navigation Unit (INU) to be built on top of a low cost, small size Integrated Circuit (IC) chip. Due to the nature of the MEMS INU, its outputs are normally corrupted by the resided stochastic noise. A common practice to regulate its measurements into usable motion data is by fusing the Global Positioning System (GPS) measurement data with the MEMS INU measurement data through Kalman filter for position, velocity and orientation estimations. Such integrated system is known as GPS-aided Inertial Navigation System (INS). Note that the robustness of the GPS-aided INS relies heavily on the availability of the GPS signals. In the event of no GPS signals, the overall system will solely depend on the INU to predict the position, velocity and orientation. The prediction results will eventually drift from its true value due to the INU's resided stochastic noise. In this study, a remedy system using Adaptive Neuro-Fuzzy Inference System (ANFIS) is developed to improve the performance of the GPS-aided INS during GPS outage condition. UAV motion sensing experiment was carried out and GPS outage conditions were imposed at several locations during the UAV navigation. The motion prediction dataduring GPS outages, with and without ANFIS implementation, were compared and the results clearly show that the GPS-aided INS with ANFIS implementation achieved better performance than the GPS-aided INS without ANFIS.

Hybrid Adaptive Computational Intelligence-based Multisensor Data Fusion applied to real-time UAV autonomous navigation

“…Additionally, [41,42] apply Fuzzy Inference Systems to perform the fusion. Finally, it is seen in [43] the use of ANFIS as a sub-remedy system to temporarily replace the GPS positioning estimation used as input to a Kalman filter during GPS outages. Although, according to the authors, the methodology implies an average performance improvement of not more than 40%, the great counterpoint to this work is that the employed methodology is subject to all the problems related to the use of the Kalman filter.…”