Cognitive optimization in the development of assistive living systems

This paper presents a preliminary exploration of the characteristics and structure of a cognitive architecture for control of assisted living systems. In this work the key aspects of the cognitive system considered are self-organization, communication, and the use of a priori knowledge. These aspects are used to explore a cognitive approach to optimization, which is considered to be a key aspect of a cognitive system. Test problems are examined in order to determine whether the cognitive structures proposed by psychologists can also perform optimization. The approach followed is to gift the cognitive optimization with a priori knowledge of how to solve optimization problems. This involves adapting and combining traditional optimization techniques, such as the bracketing, gradient search, and branch and bound, into a cognitive architecture. The algorithm is implemented as different processes that communicate and learn from each other by passing messages in order to organize around a solution. This approach is applied to four different problems with different levels of difficulty in order to gain insights into the structure and characteristics of cognitive optimization.