An Affective Robot Companion for Assisting the Elderly in a Cognitive Game Scenario
This addresses the challenge of improving engagement and enjoyment for elderly users in cognitive training through affective robotics, but it is incremental as it builds on existing emotion recognition and reinforcement learning methods.
The paper tackles the problem of enhancing human-robot interaction by using recognized emotions to actively modulate robot decision-making and dialogue, specifically in a cognitive training scenario like the 2048 Puzzle Game, aiming to make tasks more enjoyable for users.
Being able to recognize emotions in human users is considered a highly desirable trait in Human-Robot Interaction (HRI) scenarios. However, most contemporary approaches rarely attempt to apply recognized emotional features in an active manner to modulate robot decision-making and dialogue for the benefit of the user. In this position paper, we propose a method of incorporating recognized emotions into a Reinforcement Learning (RL) based dialogue management module that adapts its dialogue responses in order to attempt to make cognitive training tasks, like the 2048 Puzzle Game, more enjoyable for the users.