Hybrid chat and task dialogue for more engaging HRI using reinforcement learning

Papaioannou, Ioannis; Dondrup, Christian; Novikova, Jekaterina; Lemon, Oliver

doi:10.1109/roman.2017.8172363

Cited by 27 publications

(22 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Having an embodied dialogue system such as a robot in HRI creates the need to be able to combine task execution and social chat as shown in previous work [11], [12]. Since robots are physical entities, executing a task might take time and/or several dialogue turns.…”

Section: Discussionmentioning

confidence: 99%

“…In addition to a requirement to support dialogue about multiple ongoing tasks, future plans, and ongoing task execution status, in recent years it has become recognised that "social chat" is also an important element of more engaging and usable dialogue interfaces, especially when having the option of an open domain dialogue with the user, like in the work presented in [5], [6]. As shown in [11], [12], adding social chat to a task-based agent not only has no negative impact on the system's task completion performance, but it is perceived as more pleasant and as meeting the users' expectations better than a purely task based system.…”

Section: Introductionmentioning

confidence: 99%

“…Addressing these issues and inspired by and building on the ability to manage multiple simultaneously executed tasks using Natural Language as introduced in previous work [9], we propose an extension to the premise of our recent experiment [11] by combining this ability of multi-threaded task management with a social dialogue component using the Alana open-domain conversational system presented in [10]. The proposed framework, therefore, improves upon the ideas presented in [9] by allowing the system to build rapport with the user through social interaction as shown in [11] and refines the system architecture by combining the two dialogue systems, i.e. task-based and social chat, into one overall dialogue management system as part of Alana [10], which allows for a more coherent interaction.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Human-Robot Interaction Requires More Than Slot Filling - Multi-Threaded Dialogue for Collaborative Tasks and Social Conversation

Dondrup¹,

Lemon²

2018

FAIM/ISCA Workshop on Artificial Intelligence for Multimodal Human Robot Interaction

Self Cite

View full text Add to dashboard Cite

Work on spoken dialogue systems (SDS) has largely been dominated by "slot filling" applications for the past decade or more, where information-gathering tasks such as restaurant search and flight booking have been the main focus of research. An important class of dialogues, about planning and executing tasks, has correspondingly been somewhat neglected. However, planning and execution dialogues become very important when we consider Human-Robot Interaction (HRI), as does the ability to carry out "social" open-domain conversation. This paper describes a new architecture that supports complex multi-threaded task planning and execution dialogues, interleaved with "social" dialogue with an opendomain chatbot.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Human-Robot Interaction Requires More Than Slot Filling - Multi-Threaded Dialogue for Collaborative Tasks and Social Conversation

Dondrup¹,

Lemon²

2018

FAIM/ISCA Workshop on Artificial Intelligence for Multimodal Human Robot Interaction

Self Cite

View full text Add to dashboard Cite

show abstract

“…In one of the most relevant examples [16] researchers investigated combining task and social dialogue in a robot intended for deployment as a guide in a shopping mall. Their evaluation showed that the hybrid task+chat system was rated significantly more pleasant and better met the users' expectations than a task-only version.…”

Section: Related Workmentioning

confidence: 99%

It's Good to Chat?

Gunson

Sieińska

Walsh

et al. 2020

Proceedings of the 20th ACM International Conference on Intelligent Virtual Agents

Self Cite

View full text Add to dashboard Cite

We present and evaluate a deployed conversational AI system that acts as a host of a working public building on a university campus. The system combines open-domain social chat with task-based conversation regarding navigation in the building, live resource updates (e.g. available computers), and events in the building. We investigated the impact of open-domain social chat on task completion and user preferences by comparing the combined system with a task-only version. We find that there is no significant difference in task completion or several aspects of user preference between the two systems, but that users would be significantly happier to talk to the task-only system in the future. This suggests that the łwalk-upž public setting and workplace nature of the environment creates a markedly different use case to the in-home, and more individual and private łcompanion/assistantž setting which is commonly assumed for systems like Alexa. We discuss the implications for the design of conversational systems in other public settings. CCS CONCEPTS • Human-centered computing → Natural language interfaces; Empirical studies in HCI; • Computing methodologies → Discourse, dialogue and pragmatics.

show abstract

“…We focus here on the selection of a shared visual perspective for providing route directions, but this work is part of an overall project that aims to implement and evaluate a complete system for the guiding task. This involves the development of a number of other components such as a human perception system [12], a human-aware reactive motion planner [13], a Human-Robot joint action supervision [14] and the associated dialogue [15].…”

Section: Introductionmentioning

confidence: 99%

Reasoning on Shared Visual Perspective to Improve Route Directions

Waldhart

Clodic

Alami

2019

2019 28th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)

View full text Add to dashboard Cite

We claim that the activity consisting in providing route directions can be best dealt with as a joint task involving the contribution not only of the robot as a direction provider but also of the human as listener. Moreover, we claim that in some cases, both the robot and the human should move to reach a different perspective of the environment which allows the explanations to be more efficient. As a first step toward implementing such a system, we propose the SVP (Shared Visual Perspective) planner which searches for the right placements both for the robot and the human to enable the visual perspective sharing needed for providing route direction and which makes the choice of the best landmark when several are available. The shared perspective is chosen taking into account not only the visibility of the landmarks, but the whole guiding task.

show abstract

Hybrid chat and task dialogue for more engaging HRI using reinforcement learning

Cited by 27 publications

References 13 publications

Human-Robot Interaction Requires More Than Slot Filling - Multi-Threaded Dialogue for Collaborative Tasks and Social Conversation

Human-Robot Interaction Requires More Than Slot Filling - Multi-Threaded Dialogue for Collaborative Tasks and Social Conversation

It's Good to Chat?

Reasoning on Shared Visual Perspective to Improve Route Directions

Contact Info

Product

Resources

About