<p>This master thesis investigates the principal capability of artificial evolution to produce tool use behavior in adaptive agents, excluding the application of life-time learning or adaptation mechanisms. Tool use is one aspect of complex behavior that is expected from autonomous agents acting in real-world environments. In order to achieve tool use behavior an agent needs to identify environmental objects as potential tools before it can use the tools in a problem-solving task. Up to now research in robotics has focused on life-time learning mechanisms in order to achieve this. However, these techniques impose great demands on resources, e.g. in terms of memory or computational power. All of them have shown limited results with respect to a general adaptivity. One might argue that even nature does not present any kind of omni-adaptive agent. While humans seem to be a good example of natural agents that master an impressive variety of life conditions and environments (at least from a human perspective, other examples are spectacular survivability observations of octopuses, scorpions or various viruses) even the most advanced engineering approaches can hardly compete with the simplest life-forms in terms of adaptation. This thesis tries to contribute to engineering approaches by promoting the application of artificial evolution as a complementing element with the presentation of successful pioneering experiments. The results of these experiments show that artificial evolution is indeed capable to render tool use behavior at different levels of complexity and shows that the application of artificial evolution might be a good complement to life-time approaches in order to create agents that are able to implicitly extract concepts and display tool use behavior. The author believes that off-loading at least parts of the concept retrieval process to artificial evolution will reduce resource efforts at life-time when creating autonomous agents with complex behavior such as tool use. This might be a first step towards the vision of a higher level of autonomy and adaptability. Moreover, it shows the demand for an experimental verification of commonly accepted limits between qualities of learned and evolved tool use capabilities.</p>

This master thesis investigates the principal capability of artificial evolution to produce tool use behavior in adaptive agents, excluding the application of life-time learning or adaptation mechanisms. Tool use is one aspect of complex behavior that is expected from autonomous agents acting in real-world environments. In order to achieve tool use behavior an agent needs to identify environmental objects as potential tools before it can use the tools in a problem-solving task. Up to now research in robotics has focused on life-time learning mechanisms in order to achieve this. However, these techniques impose great demands on resources, e.g. in terms of memory or computational power. All of them have shown limited results with respect to a general adaptivity. One might argue that even nature does not present any kind of omni-adaptive agent. While humans seem to be a good example of natural agents that master an impressive variety of life conditions and environments (at least from a human perspective, other examples are spectacular survivability observations of octopuses, scorpions or various viruses) even the most advanced engineering approaches can hardly compete with the simplest life-forms in terms of adaptation. This thesis tries to contribute to engineering approaches by promoting the application of artificial evolution as a complementing element with the presentation of successful pioneering experiments. The results of these experiments show that artificial evolution is indeed capable to render tool use behavior at different levels of complexity and shows that the application of artificial evolution might be a good complement to life-time approaches in order to create agents that are able to implicitly extract concepts and display tool use behavior. The author believes that off-loading at least parts of the concept retrieval process to artificial evolution will reduce resource efforts at life-time when creating autonomous agents with complex behavior such as tool use. This might be a first step towards the vision of a higher level of autonomy and adaptability. Moreover, it shows the demand for an experimental verification of commonly accepted limits between qualities of learned and evolved tool use capabilities.

This project attempts to research the manufacturing cost, with an emphasis on machining, of high performance flanges for Turbine Rear Structure (TRS) applications, as well as the tradeoffs with structural performance and weight. A combination of traditional cost modelling techniques from the literature, as well as, the non-conventional manufacturing complexity index, as cost indicator are implemented. A multidisciplinary study is carried out with the aid of ANSYS Workbench in the form of computer simulated experiments to investigate tradeoffs in flanges. It is concluded that multidisciplinary studies of cost, performance and weight lacked model robustness to draw sound conclusions about flange design. However, the manufacturing complexity index after partial validation with experienced engineers shows promising results, and could be a way forward to estimate final machining operation cost for flanges in the future. / Syftet för detta projekt är att undersöka tillverkningskostnaden, med tonvikt på bearbetning av högpresterande flänsar för turbinapplikationer (TRS), samt dess relation till strukturella prestanda och vikt. Traditionella kostnadsmodelleringstekniker kombineras med det ickekonventionella tillverkningskomplexitetsindexet och används som kostnadsindikator. En tvärvetenskaplig studie genomförs med hjälp av ANSYS Workbench i form av dator simulerade experiment för att undersöka flänsavvägningar. En slutsats av studien är att multidisciplinära modeller av kostnad, prestanda och vikt saknade robusthet för att kunna dra djupgående slutsatser om prestandan för en flänsdesign. Tillverkningskomplexitetsindexet visar dock, efter partiell validering med erfarna ingenjörer, lovande resultat och kan vara framgångsrikt ett sätt att uppskatta den slutliga bearbetningskostnaden för flänsar.