Abstract
Social robots are intended to establish natural interactions with humans. In most cases, human-robot communication is predefined and results in monotonous interactions in the long term that lead the user to cease the interaction. In this paper, we propose a robotic application to generate verbal interactions dynamically. However, if the users do not perceive these dialogues as interesting, they will not engage in the interaction with the robot. To mitigate this problem, we propose generating verbal dialogues considering the user’s interests and preferences. To this end, we present a social robot application for conducting personalized conversations using data from social media accounts of interest for the user and large-language models to build the dialogue. After evaluating the proposed application, participants rated it very positively regarding its usability.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
The work described in this paper was conducted before the July 2023 update of the Twitter Terms of Service and Privacy Policy.
References
Andronas, D., Apostolopoulos, G., Fourtakas, N., Makris, S.: Multi-modal interfaces for natural Human-Robot Interaction. Procedia Manuf. 54, 197–202 (2021)
Asl, A.M., et al.: The usability and feasibility validation of the social robot MINI in people with dementia and mild cognitive impairment; a study protocol. BMC Psychiatry 22(1), 760 (2022)
Bangor, A., Kortum, P., Miller, J.: Determining what individual SUS scores mean: adding an adjective rating scale. J. Usability Stud. 4(3), 114–123 (2009)
Breazeal, C.: Designing Sociable Robots. MIT Press (2004)
Broadbent, E., Montgomery Walsh, R., Martini, N., Loveys, K., Sutherland, C.: Evaluating the usability of new software for medication management on a social robot. In: Companion of the 2020 ACM/IEEE International Conference on Human-robot Interaction, pp. 151–153 (2020)
Brooke, J.: SUS: a quick and dirty’usability. Usability Eval. Ind. 189(3), 189–194 (1996)
Cao, Y., Bi, W., Fang, M., Tao, D.: Pretrained language models for dialogue generation with multiple input sources. arXiv preprint arXiv:2010.07576 (2020)
Churamani, N., et al.: The impact of personalisation on human-robot interaction in learning scenarios. In: Proceedings of the 5th International Conference on Human Agent Interaction, pp. 171–180. HAI 2017, Association for Computing Machinery, New York, NY, USA (2017). https://doi.org/10.1145/3125739.3125756
Di Nuovo, A., et al.: Usability evaluation of a robotic system for cognitive testing. In: 2019 14th ACM/IEEE International Conference on Human-Robot Interaction (HRI), pp. 588–589 (2019). https://doi.org/10.1109/HRI.2019.8673187, ISSN: 2167-2148
Fernández-Rodicio, E., Castro-González, A., Alonso-Martín, F., Maroto-Gómez, M., Salichs, M.: Modelling multimodal dialogues for social robots using communicative acts. Sensors 20(12) (2020). https://doi.org/10.3390/s20123440, https://www.mdpi.com/1424-8220/20/12/3440
Fronemann, N., Pollmann, K., Loh, W.: Should my robot know what’s best for me? Human-robot interaction between user experience and ethical design. AI Soc. 37(2), 517–533 (2022)
Hellou, M., Gasteiger, N., Lim, J.Y., Jang, M., Ahn, H.S.: Personalization and localization in human-robot interaction: a review of technical methods. Robotics 10(4), 120 (2021)
John, N.E., Rossi, A., Rossi, S.: Personalized human-robot interaction with a robot bartender. In: Adjunct Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization, pp. 155–159 (2022)
Jung, M., Lazaro, M.J.S., Yun, M.H.: Evaluation of methodologies and measures on the usability of social robots: a systematic review. Appl. Sci. 11(4), 1388 (2021)
Kenton, J.D.M.W.C., Toutanova, L.K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of naacL-HLT, vol. 1, pp. 2 (2019)
Lee, M.K., Forlizzi, J., Kiesler, S., Rybski, P., Antanitis, J., Savetsila, S.: Personalization in HRI: a longitudinal field experiment. In: Proceedings of the Seventh Annual ACM/IEEE International Conference on Human-Robot Interaction, pp. 319–326 (2012)
Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461 (2019)
Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)
Louie, W.Y.G., Nejat, G.: A social robot learning to facilitate an assistive group-based activity from non-expert caregivers. Int. J. Soc. Robot. 12(5), 1159–1176 (2020)
Keizer, O., et al.: Using socially assistive robots for monitoring and preventing frailty among older adults: a study on usability and user experience challenges. Health Technol. 9(4), 595–605 (2019). https://doi.org/10.1007/s12553-019-00320-9
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730–27744 (2022)
Salichs, M.A., et al.: Mini: a new social robot for the elderly. Int. J. Soc. Robot. 12(6), 1231–1249 (2020). https://doi.org/10.1007/s12369-020-00687-0
Xue, L., et al.: mT5: a massively multilingual pre-trained text-to-text transformer. arXiv preprint arXiv:2010.11934 (2020)
Zhao, X., Wu, W., Xu, C., Tao, C., Zhao, D., Yan, R.: Knowledge-grounded dialogue generation with pre-trained language models. arXiv preprint arXiv:2010.08824 (2020)
Acknowledgments
This work has been supported by the Madrid Government (Comunidad de Madrid-Spain) under the Multiannual Agreement with UC3M (“Fostering Young Doctors Research”, SMM4HRI-CM-UC3M), and in the context of the V PRICIT (Research and Technological Innovation Regional Programme). This work has been partially supported by the project“Robots sociales para mitigar la soledad y el aislamiento en mayores (SOROLI)”, funded by Agencia Estatal de Investigación (AEI), Spanish Ministerio de Ciencia e Innovación (PID2021-123941OA-I00), and the project sense2MakeSense, funded by the Spanish State Agency of Research (PID2019-109388GB-I00).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Onorati, T., Castro-González, Á., del Valle, J.C., Díaz, P., Castillo, J.C. (2023). Creating Personalized Verbal Human-Robot Interactions Using LLM with the Robot Mini. In: Bravo, J., Urzáiz, G. (eds) Proceedings of the 15th International Conference on Ubiquitous Computing & Ambient Intelligence (UCAmI 2023). UCAmI 2023. Lecture Notes in Networks and Systems, vol 835. Springer, Cham. https://doi.org/10.1007/978-3-031-48306-6_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-48306-6_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-48305-9
Online ISBN: 978-3-031-48306-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)