Eyal Amir and Patrick Doyle
This paper presents a set of challenges for cognitive robotics in the context of a text-based adventure game. Games in this class have many challenging properties for cognitive robotics, including incompletely specified goals, an environment revealed only through exploration, actions whose preconditions and effects are not known a priori, and the need of commonsense knowledge for determining what actions are likely to be available or effective. These qualities require an agent that is able to use commonsense knowledge, make assumptions about unavailable knowledge, revise its beliefs, and learn what actions are appropriate. At the same time, more traditional robotics problems arise, including sensing, object classification, focusing on relevant features on a situation, reasoning within context, and decision-making, all within a large state space. In this paper we introduce the game and its environment, elaborate upon the properties of both as they pertain to cognitive robotics, and argue that this is a highly advantageous venue for exploring cognitive robotics issues.