Legible Behavior

In this chapter, the discussion will focus on another type of interpretable behavior, namely legibility. The notion of legibility allows the robot to implicitly communicate information about its goals, plans (or model, in general) to a human observer. For instance, consider a human robot cohabitation scenario consisting of a multi-tasking robot with varied capabilities that is capable of performing a multitude of tasks in an environment. In such a scenario, it is crucial for the robot to aid the human’s goal or plan recognition process, as the human observer may not always know the robot’s intentions or objectives beforehand. Hence, in such cases, it may be useful for the robot to communicate information that the human is unaware of. As the better off the human is at identifying the robot’s goals or plans accurately, the better off is the overall team performance. However, explicit communication of objectives might not always be suitable. For instance, the what, when, and how of explicit communication may require additional thought. Further, several other aspects like cost of communication (in terms of resources or time), delay in communication (communications signals may take time to reach the human), feasibility of communication (broken or unavailable sensors), etc., may also need to be considered. On the other hand, the robot can simply synthesize a behavior that implicitly communicates the necessary information to the human observer.