Deceptive Actions to Improve the Attribution of Rationality to Playing Robotic Agents

Abstract

Play is a common activity, providing not only pleasure but also physical and cognitive development. In the quest for new playing experiences, there is an increasing tendency to develop robots playing with people. Making believable playing robots able to keep human players engaged and satisfied by the playing experience is the main challenge.In this work, we investigate the possibilities of a playful interaction between a human player and a mobile robot. In particular, this paper focuses on the applicability of deception as a means to support engagement and the attribution of rationality to playing robotic agents. By analyzing the interaction situation between the human and robot players, by identifying the need for deception, and by deciding whether and how to deceive, we aim at increasing self-reported engagement and fun, which are also related to the perception of the robotic opponent as smart enough to compete at an appropriate level.Experiments were conducted on a sample of 78 subjects facing two different deceptive behaviors and a basic behavior without any deception. All participants responded to a post-interaction questionnaire from which it was possible to observe a positive acceptance of the perception of the robot as a rational agent aimed at winning. In general, deception was perceived by most of the players as one of the robot's abilities, when actuated, and contributed to the reported fun.

A Pragmatic Approach to the Intentional Stance Semantic, Empirical and Ethical Considerations for the Design of Artificial Agents

“…In fact, some consider at least some forms of deception to be an intrinsic feature of robotics and AI, as they offer the best possibility of successfully developing socially integrated artificial agents. As such, deception is seen as an acceptable, even desirable phenomenon (Wagner & Arkin, 2011;Shim & Arkin, 2012;Isaac & Bridewell, 2017;de Oliveira et al, 2020). Indeed, one might argue that deception even lies at the foundation of the Turing test, the many versions of which share the assumption that, in order to pass the test, a machine must succeed in convincing a human jury that they are actually interacting with another human.…”

Communication in Human-Robot Interaction

“…The identification of these aspects, and consequent adaptation of the robot behavior to the specific situation, including the selection of the appropriate multimodal communicative actions, can be done by learning models of general attitudes, trying to classify the interlocutor from the interaction, to identify the type of the most appropriate modality, and to apply the learned model to generate the proper interaction. It has been observed both for verbal interaction (e.g., [73]) and for non-verbal interaction (e.g., in robotic games [74,75]) that robots matching the characteristics of the interacting people can have better performance.…”

Robot player adaptation to human opponents in physical, competitive robogames

“…In another version of the game (ADA2) [5], adaptation has been implemented by introducing feints among the possible robot behaviors. These are devised to deceive the player, and are randomly triggered in specific game situations, according to the evaluation of the situation.…”

“…This type of adaptation introduces surprising moments, which trigger curiosity, another important driver for engagement. In the experiments, we considered three implementations of the game, one without adaptation (fixed), and one with each type of deceptive behaviors, respectively static, where the speed of the robot was fixed and only the target was suddenly changed, and dynamic [5], where feints were further highlighted by speed changes.…”

“…• We present three different approaches to model aspects of the player from data acquired online within a single game, and results for self-reported fun during a real game (Robotower [5]). • We provide a discussion about two classes of adaptation (extrinsic and intrinsic) in the context of real humanrobot playing, physical interaction.…”