Intelligent methods for dynamic analysis and navigation of autonomous land vehicles


Tezin Türü: Doktora

Tezin Yürütüldüğü Kurum: Orta Doğu Teknik Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, Türkiye

Tezin Onay Tarihi: 2004

Öğrenci: HÜSEYİN BURAK KAYGISIZ

Eş Danışman: AYDAN MÜŞERREF ERKMEN, İSMET ERKMEN

Özet:

Autonomous land vehicles (ALVs) have received considerable attention after their introduction into military and commercial applications. ALVs still stand as a challenging research topic. One of the main problems arising in ALV operations is the navigation accuracy while the other is the dynamic effects of road irregularities which may prevent the vehicle and its cargo to function properly. In this thesis, we propose intelligent solutions to these two basic problems of ALV. First, an intelligent method is proposed to enhance the performance of a coupled global positioning/inertial navigation system (GPS/INS) for land navigation applications during the GPS signal loss. Our method is based on using an artificial neural network (ANN) to intelligently aid the GPS/INS coupled navigation system in the absence of GPS signals. The proposed enhanced GPS/INS is used in the dynamic environment of a tour of an autonomous van and we provide the results here. GPS/INS+ANN system performance is thus demonstrated with the land trials. Secondly, our work focuses on the identification and enlargement of the stability region of the ALV. In this thesis, the domain of attraction of the ALV is found to be patched by chaotic and regular regions with chaotic boundaries which are extracted using novel technique of cell mapping equipped with measures of fractal dimension and rough sets. All image cells in the cellular state space, with their individual fractal dimension are classified as being members of lower approximation (surely stable), upper approximation (possibly stable) or boundary region using rough set theory. The obtained rough set with fractal dimension as its attribute is used to model the uncertainty of the regular regions. This uncertainty is then smoothed by a reinforcement learning algorithm in order to enlarge regular regions that are used for chassis control, critical in ALV