Autonomous Robotic Dialogue System with Reinforcement Learning for Elderlies with Dementia

Magyar, Ján; Kobayashi, Masahiko; Nishio, S.; Sinčák, Peter; Ishiguro, Hiroshi

doi:10.1109/smc.2019.8914248

Cited by 12 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the teleoperated robot Telenoid has been trialled with five PwD in a care facility for 10 weeks, as a tool to promote conversation and improve behavioural and psychological symptoms of dementia [97]. In [98], the authors have further proposed an autonomous dialogue system integrated with Telenoid that triggers the next spoken action (including conversation topic) by estimating the senior's emotion and motivation based on non-verbal cues, through the use of external sensors to extract emotional features (e.g., facial emotion). Using a reinforcement learning approach, the adaptive robotic system would trigger one of three actions: short response (simple agreement, encouragement), long response (question), or topic change (a statement introducing a new topic), being able to maintain interactions with end-users for 20 min.…”

Section: B Small Affective Social Robotsmentioning

confidence: 99%

Conversational Affective Social Robots for Ageing and Dementia Support

Lima

Wairagkar

Gupta³

et al. 2022

IEEE Trans. Cogn. Dev. Syst.

View full text Add to dashboard Cite

Socially assistive robots (SAR) hold significant potential to assist older adults and people with dementia in human engagement and clinical contexts by supporting mental health and independence at home. While SAR research has recently experienced prolific growth, long-term trust, clinical translation and patient benefit remain immature. Affective human-robot interactions are unresolved and the deployment of robots with conversational abilities is fundamental for robustness and humanrobot engagement. In this paper, we review the state of the art within the past two decades, design trends, and current applications of conversational affective SAR for ageing and dementia support. A horizon scanning of AI voice technology for healthcare, including ubiquitous smart speakers, is further introduced to address current gaps inhibiting home use. We discuss the role of user-centred approaches in the design of voice systems, including the capacity to handle communication breakdowns for effective use by target populations. We summarise the state of development in interactions using speech and natural language processing, which forms a baseline for longitudinal health monitoring and cognitive assessment. Drawing from this foundation, we identify open challenges and propose future directions to advance conversational affective social robots for: 1) user engagement, 2) deployment in real-world settings, and 3) clinical translation.

show abstract

Section: B Small Affective Social Robotsmentioning

confidence: 99%

Conversational Affective Social Robots for Ageing and Dementia Support

Lima

Wairagkar

Gupta³

et al. 2022

IEEE Trans. Cogn. Dev. Syst.

View full text Add to dashboard Cite

show abstract

“…Our work attempts to build interactions above this basic knowledge layer, where utterance formulation, speech fluency and linguistic content, in a context-appropriate framework, are the learning objectives. For this purpose, adaptive dialogue systems have been proposed based on Reinforcement Learning frameworks [10] or Partially Observable Markov Decision Process (POMDP) [11].…”

Section: M Ethod and R Esearch Q Uestionmentioning

confidence: 99%

Adaptive Robot Discourse for Language Acquisition in Adulthood

Cumbal

2022

2022 17th ACM/IEEE International Conference on Human-Robot Interaction (HRI)

View full text Add to dashboard Cite

Acquiring a second language in adulthood differs considerably from the approach taken at younger ages. Learning rates tend to decrease during adolescence, and socio-emotional characteristics, like motivation and expectations, take a different perspective for adults. In particular, acquiring communicative competence is a stronger objective for older learners, as an appropriate use of language in social contexts ensures a better community immersion and well-being. This skill is best attained through interactions with proficient speakers, but if this option is not available, social robots present a good alternative for this purpose. However, to obtain optimal results, a robot companion should adapt to the learner's proficiency level and motivation continuously to encourage speech production and increase fluency. Our work attempts to achieve this goal by developing an adaptive robot that modifies its spoken dialogue strategy, and visual feedback, to reflect a student's knowledge, proficiency and engagement levels in situated interactions for long-term learning.

show abstract

“…The state space was defined as word-based features, and the action space included 35 dialogue actions in response to users’ intentions. In another study 30 of using RL to learn a conversation strategy for autonomous robotic dialogue system for PwDs, the authors designed state space as the robot’s internal motivation (closely associated with user’s motivation) and previously selected action. Their action space was represented by three types of robot’s action, including short response (simple agreement/encouragement), long response (question) and topic change.…”

Section: Introductionmentioning

confidence: 99%

A simulated experiment to explore robotic dialogue strategies for people with dementia

Yuan

Sadovnik

Zhang

et al. 2022

Journal of Rehabilitation and Assistive Technologies Engineerin

View full text Add to dashboard Cite

Introduction Persons with dementia (PwDs) often show symptoms of repetitive questioning, which brings great burdens on caregivers. Conversational robots hold promise of helping cope with PwDs’ repetitive behavior. This paper develops an adaptive conversation strategy to answer PwDs’ repetitive questions, follow up with new questions to distract PwDs from repetitive behavior, and stimulate their conversation and cognition. Methods We propose a general reinforcement learning model to interact with PwDs with repetitive questioning. Q-learning is exploited to learn adaptive conversation strategy (from the perspectives of rate and difficulty level of follow-up questions) for four simulated PwDs. A demonstration is presented using a humanoid robot. Results The designed Q-learning model performs better than random action selection model. The RL-based conversation strategy is adaptive to PwDs with different cognitive capabilities and engagement levels. In the demonstration, the robot can answer a user’s repetitive questions and further come up with a follow-up question to engage the user in continuous conversations. Conclusions The designed Q-learning model demonstrates noteworthy effectiveness in adaptive action selection. This may provide some insights towards developing conversational social robots to cope with repetitive questioning by PwDs and increase their quality of life.

show abstract

Autonomous Robotic Dialogue System with Reinforcement Learning for Elderlies with Dementia

Cited by 12 publications

References 10 publications

Conversational Affective Social Robots for Ageing and Dementia Support

Conversational Affective Social Robots for Ageing and Dementia Support

Adaptive Robot Discourse for Language Acquisition in Adulthood

A simulated experiment to explore robotic dialogue strategies for people with dementia

Contact Info

Product

Resources

About