Exception handling for experience-based mobile cognitive systems in restaurant environments exemplified by guest detection

Recording and exploiting past experiences to handle an unforeseen situation is an important asset of human beings. However, in current robot architectures, experience-based learning has mainly been realized at sub-symbolic levels. In this paper, we present how to handle exception for an experience-based artificial cognitive system which is able to fulfill unforeseen situations in restaurant environments. Guest detection is employed to demonstrate the exception handling functionality. Experiments were executed to validate and evaluate the effectiveness of this artificial cognitive system.