A User-Centred Framework for Explainable Artificial Intelligence in\n Human-Robot Interaction

Abstract

State of the art Artificial Intelligence (AI) techniques have reached an\nimpressive complexity. Consequently, researchers are discovering more and more\nmethods to use them in real-world applications. However, the complexity of such\nsystems requires the introduction of methods that make those transparent to the\nhuman user. The AI community is trying to overcome the problem by introducing\nthe Explainable AI (XAI) field, which is tentative to make AI algorithms less\nopaque. However, in recent years, it became clearer that XAI is much more than\na computer science problem: since it is about communication, XAI is also a\nHuman-Agent Interaction problem. Moreover, AI came out of the laboratories to\nbe used in real life. This implies the need for XAI solutions tailored to\nnon-expert users. Hence, we propose a user-centred framework for XAI that\nfocuses on its social-interactive aspect taking inspiration from cognitive and\nsocial sciences' theories and findings. The framework aims to provide a\nstructure for interactive XAI solutions thought for non-expert users.\n