Autonomous Underwater Vehicle Control using Expert System based Building Blocks
|Betreuer:||Horst Hellbrück , Torsten Teubler|
In the context of the BOSS (Bionic Observation and Survey System) project we are developing an autonomous, intelligent, and cooperative behavior for AUV (Autonomous Underwater Vehicles). We implement the AUV's behavior using CLIPS, a so called "expert system". On the one hand, expert systems allow knowledge representation and reasoning and are a proven tool for implementing artificial intelligence applications. On the other hand, expert systems introduce a completely new programming paradigm which is hard to grasp for users of AUV's. With this work we will solve that issue by decomposing typical AUV tasks in expert system based building blocks allowing users to recombine them to build more complex tasks.
In this work typical tasks for AUV's will be investigated. It has to be examined if such tasks they can be decomposed in reusable and parameterized buidling blocks. If those buidling blocks exist they have to be implemented in the CLIPS expert system and the approach has to be evaluated by building at least three typical complex tasks based on the building blocks. The functionality of the approach has to be evaluated with a simulation. Details of the implementation are discussed with the supervisor during the thesis work.
- Investigation of typical expert system tasks for AUV control to identify building blocks of the system.
- Implementation of the identified building blocks.
- Implementation at least three complex tasks composed of expert system based building blocks.
- Evaluation of the approach using a simulation.
- Good knowledge of C/C++.
- Experience with expert systems (best CLIPS) or willingness to learn CLIPS.
- Very good skills in problem-abstraction.
- Good self-organized working skills.
- Knowledge of the English language.