Engagement in Dialogue with Social Robots
It is becoming increasingly clear that social and interactive skills are necessary requirements in many application areas where robots interact, communicate and collaborate with humans or other connected devices. The social aspects of human-computer inter
- PDF / 87,855 Bytes
- 7 Pages / 439.37 x 666.142 pts Page_size
- 56 Downloads / 246 Views
Abstract It is becoming increasingly clear that social and interactive skills are necessary requirements in many application areas where robots interact, communicate and collaborate with humans or other connected devices. The social aspects of humancomputer interaction and the connection between humans and robots has recently received considerable attention in the fields of artificial intelligence, cognitive science, healthcare, companion technologies, and industrial/commercial robotics. This article addresses some dimensions of near-term future HRI, with focus on engagement detection for conversational efficiency. We present some findings from HRI research conducted at the Speech Communication Lab at Trinity College Dublin, report our experiences with a publicly exhibited conversational robot, and discuss some future research trends. Keywords Human-robot-interaction · Social engagement processing · Interactive speech-synthesis
· Functional dialogue
1 Introduction Researchers in the field of human-robot interaction (HRI) are typically addressing the question of how to make robots more ‘attractive’ to people interacting with them and are concerned with the motivation and engagement of users in their interactions with robots [1, 2]. There are several attempts to make robot speech sound more human and even to include laughter, turn-taking signals [3, 4] and extra-linguistic sounds to mimic natural human conversational interaction. However, given the ‘uncannyvalley effect’ [5] wherein too close a mimic can appear disturbing, our view is that L. Cerrato (B) · N. Campbell ADAPT Centre, Trinity College Dublin, Dublin, Ireland e-mail: [email protected] N. Campbell Speech Communication Lab, Trinity College Dublin, Dublin, Ireland e-mail: [email protected] © Springer Science+Business Media Singapore 2017 K. Jokinen and G. Wilcock (eds.), Dialogues with Social Robots, Lecture Notes in Electrical Engineering 427, DOI 10.1007/978-981-10-2585-3_25
313
314
L. Cerrato and N. Campbell
while robots should perhaps continue to sound somewhat robotic, they should at the same time be able to parse and interpret natural social human speech phenomena. We anticipate many situations where robots should be able to interpret a given utterance as a joke, for example, and even to make jokey or humorous responses to human utterances. It might be necessary to first define how we use the term robot in this context; and here we include many devices that might not normally come under the typical understanding of ‘robotics’. The fundamental defining characteristic of a robot as we see it is that it has multiple sensors and can autonomously effect changes in the real world as a result of different sensor inputs. Of course androids and humanoid devices come under this definition, but so too, we argue, does the iPhone, a Google car, and several present-day domestic appliances. We foresee a near-term future where, in some specific contexts, ubiquitous devices are highly interconnected and able to communicate with humans through speech, as well as being ab
Data Loading...
