Robots and Bananas: Exploring Deliberation in Cognitive Robots

Under what conditions should a cognitive robot act? How do we define “opportunities” for robot action? How can we characterize their properties? In this position paper, we offer an initial apparatus to formalize opportunities and to frame this discussion. A Robot-Banana Problem There is a physical object in our world, a banana, which can be either fresh, ripe, overripe or rotten. The banana changes state over time, from the first to the last. Maintaining a desirable world state includes that physical objects in the world, the banana, are in states that are desirable. It is desirable that the banana is fresh, ripe, or overripe, while a rotten banana is undesirable. Also, the banana should be eaten before it becomes rotten. Assume there is a mobile robot, capable of bringing a banana to a human for consumption. Assume also that the robot has a model representing the banana’s states and how long it takes to transition over them. How should the robot choose, among all possible intermediate states of the banana, when to act? Is it desirable that the robot immediately takes action as soon as there is a banana in the world, no matter what the states of the banana and the user are? The act of bringing the banana to the user for consumption achieves a desired state from the banana’s perspective — but what does this imply in terms of the world state? Not only should the banana be eaten in a favorable state, but the robot should not act intrusively against the user. For example, it would not be appropriate for the robot to force-feed the sleeping user just because the banana will soon be rotten! There are states in the world which are more suitable for taking a specific action than others — they offer opportunities for acting. For instance, the robot may offer the banana the next morning for breakfast. Consuming the banana before it is rotten and not intruding are desirable, and thereby contribute to the maintenance of a desirable world state. How do the desirable states of the banana affect whether we classify a state of the user as being suitable for robot action? When the banana is fresh, it is not necessary to act. ∗This work was funded by the EC Seventh Framework Programme (FP7/2007-2013) grant agreement no. 288899 Robot-Era. Copyright c © 2014, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. This may even result in an undesirable state of the user, therefore an undesirable world state. A ripe banana increases the necessity to act (we can predict that it will eventually become rotten), but we can afford to choose among few, well tailored states that are suitable for taking action. An overripe banana is closer to being rotten. This influences which states we now classify as suitable for taking action: this is a larger set, and potentially less perfectly tailored to acting. For all the desirable states of the banana in this simple example, the actions of the robot are always the same: bring the banana to the user for consumption. The banana’s desirable states do not differ in their influence on what the robot should do, rather when it should act. If the banana becomes rotten, the user’s state has no influence on which context the robot uses as a “trigger” to act. Also, the robot will act differently: instead of bringing the banana to the user, the robot will decide to dispose of it. In this paper we focus on characterizing the overall problem entailed by the example above. The attentive reader has certainly spotted that our hypothetical robot should be able to perform a wide range of cognitive tasks, which include perceiving, planning and acting. Studies in cognitive architectures, e.g., ACT-R (Anderson et al., 2004), lend support to the argument that diverse cognitive capabilities must be studied jointly. Similarly, the view proposed by Ghallab, Nau, and Traverso (2014) defines the deliberative capabilities that enable a robot to act appropriately. The view put forth in this paper agrees with these holistic perspectives, and is inspired by both cognitive architectures and planning as acting. Our starting point is an extremely simple example — the story of a robot, a banana and a thrifty human who does not like to waste food. The result is a preliminary formulation of opportunities that highlights the multi-faceted nature of this concept, and provides a language to state questions like the ones above. Formalizing Opportunity We consider a system Σ = 〈S,U, f〉, where S is a finite set of states, U is a finite set of external inputs (the robot’s actions), and f ⊆ S×U×S is a state transition relation. We assume discrete time, and that at each time t the system is in one state, denoted by st. The f relation models the system’s dynamics: f(st, ut, st+1) holds iff Σ can go from state st to st+1 when the input ut is applied. The free-run behavior AI and Robotics: Papers from the AAAI-14 Workshop