Using Markov Decision Process to Model Deception for Robotic and Interactive Game Applications

TL;DR

This paper models deception in robotic motion using a Markov Decision Process, proposing an adaptive strategy to deceive humans effectively over multiple interactions and introducing a new evaluation metric.

Contribution

It introduces a novel adaptive deceptive trajectory selection method for robots and a new metric to evaluate deception effectiveness.

Findings

The adaptive algorithm successfully deceives humans over multiple interactions.

The proposed method outperforms random strategy choices.

Deception effectiveness is quantitatively validated through user studies.

Abstract

This paper investigates deception in the context of motion using a simulated mobile robot. We analyze some previously designed deceptive strategies on a mobile robot simulator. We then present a novel approach to adaptively choose target-oriented deceptive trajectories to deceive humans for multiple interactions. Additionally, we propose a new metric to evaluate deception on data collected from the users when interacting with the mobile robot simulator. We performed a user study to test our proposed adaptive deceptive algorithm, which shows that our algorithm deceives humans even for multiple interactions and it is more effective than random choice of deceptive strategies.