B.Sc, Cum-Laude, Electrical and Electronics Engineering, SCE-Beer Sheva, ISRAEL, 2008.
M.Sc, Mechatroncis Engineering, Ben Gurion University of the Negev, 2014.
Thesis subject: Multisensory Data Fusion for Autonomous Vineyard Sprayer Robot Navigation (PDF).
This thesis deals with the localization of autonomous Vineyard Sprayer Robot as a part of a project addressing the lack of manpower problem to perform the vineyard spraying task and the exposure to hazardous pesticides during the spraying.
Within this thesis, we provided a set of tools and methodologies to design low cost navigation system with high precision of localization. A novel method for data fusion using LRT is proposed for localization that combine several methods for data fusion. Since each sensor has its own noise and error statistics, the pre filtering allow to treat separately each sensor. It uses a decision making technique for choosing the most probable solution. From surveying of data fusion algorithms it comes up that its accuracy depends on Gaussian noises which is not true in real applications. The algorithm propose in this thesis is general and can be applied in case on non-Gaussian noises. It has been illustrated how the proposed methodologies can be adapted to the vineyard sprayer platform. It can be adapted generally to any robot localization, whether it is on-road or off-road. This algorithm can also be used for many other applications where decision making is needed such as medicine; to calculate the probability of being diseased base on several parameters, economy; to select the best opportunity, safety instrumentation selectivity; select the best action to minimize the probability for risk occurring etc. This thesis is also a basis for further research especially in examination of the data fusion algorithm, its robustness and real-time implementation.