(1) "PLANNING COMPLEX PROCESSES FOR AUTONOMOUS VEHICLES BY MEANS OF GENETIC ALGORITHMS" This is a Master thesis, submitted to Computer Engineering Department, Faculty of Engineering, Cairo University at April 2008. And accordingly, a Master degree was granted to Nermeen Mohammed Ismail; the first author of the current paper. (2) NAME: Nermeen Mohammed Ismail PHYSICAL MAILING ADDRESS: 20 Masjed alfath aleslamy street. Begining of elharam street. EMAIL ADDRESS: nermeen.ismail@gmail.com PHONE NUMBER: +20106897723 NAME: Magda Bahaa Eldin Fayek PHYSICAL MAILING ADDRESS: Computer Engineering Department, Faculty of Engineering, Cairo University EMAIL ADDRESS: magdafayek@gmail.com PHONE NUMBER: +20101589411 NAME: Ashraf Hassan Abdel Wahab PHYSICAL MAILING ADDRESS: Electronics Research Institute, Computers & Systems Deparment EMAIL ADDRESS: awahab@mcit.gov.eg PHONE NUMBER: +20106087131 NAME: Nevin Mahmoud Darwish PHYSICAL MAILING ADDRESS: Computer Engineering Department, Faculty of Engineering, Cairo University EMAIL ADDRESS: ndarwish@ieee.org PHONE NUMBER: +20122247364 (3) Nermeen Mohammed Ismail (4) Autonomous robots are becoming an increasingly important tool for military, space exploration, and civilian applications. A key requirement for controlling mobile autonomous robots is the ability to express vehicle activity models as complex processes. This work presents PGen; a generative activity planner that translates intended state evolution to an action plan. PGen supports generative planning with complex processes via three main features. First, PGen goal plans and activity models are encoded using Reactive Model-based Programming Language (RMPL). Second, PGen represents goal plans, plan operators and plan candidates with a uniform representation called Temporal Plan Networks (TPN). Finally, PGen uses Genetic Algorithms as a novel approach for TPN-based planning. PGen has been successfully implemented and tested, simulation results are very promising. (5) {C, F, G} (6) Autonomous vehicles are turning out to be a progressively important tool for space investigation, army, and civilian applications. Model-based programming was developed to elevate programming to the specification of intended states. The specifics of achieving an intended state are delegated to what is called a model-based executive, such as Kirk. Kirk needs some inside component that is able to translate the intended states into an action plan. Spock generative planner was proposed. Spock uses an incomplete A* search algorithm to search for a suitable plan. We proposed PGen generative planner. PGen uses Genetic Algorithms as a novel approach for TPN-based planning. Actually we found that the usage of Genetic Algorithms improved the planner performance over the already existing compoenet (Spock). So we can say that the results obtained by PGen satisfy the following three of the eight criteria: (C) The result is equal to or better than a result that was placed into a database or archive of results maintained by an internationally recognized panel of scientific experts. (F) The result is equal to or better than a result that was considered an achievement in its field at the time it was first discovered. (G) The result solves a problem of indisputable difficulty in its field. (7) AUTHOR NAMES: Nermeen Mohammed Ismail, Magda Bahaa Eldin Fayek, Ashraf Hassan Abdel Wahab, Nevin Mahmoud Darwish PUBLICATION DATE: April 2008 THESIS NAME: "PLANNING COMPLEX PROCESSES FOR AUTONOMOUS VEHICLES BY MEANS OF GENETIC ALGORITHMS" PUBLISHER NAME: Computer Engineering Department, Faculty of Engineering, Cairo University. PUBLISHER CITY: Giza (8) "any prize money, if any, is to be divided equally among the co-authors" (9) Judges should consider this entry as "best" as it proposes better performance over Spock (the existing component) for a very essential component inside Kirk model-based executive. So, whenever this exeuctive is used in any planning problem (with PGen included), we ensure that this control system is so robust, and generates plans faster than before.