Abstract
The growing deployment of social robots requires the ability to adapt to the dynamic changes occurring in the real environments. These reactive behaviors, however, are often incapable of reasoning and predicting the effects of their actions in the next future. Therefore, they must be accompanied by forms of deliberative semantic/causal reasoning. The combination of the reactive and deliberative forms of reasoning, which resembles the dual process theory, raises the problem of entrusting tasks to the corresponding modules. Just as happens in biological systems, the tendency to assign activities, as much as possible, towards the lower abstraction layers, equips the systems with more responsive capabilities at the cost of making the reactive layers more difficult to implement. In this document, we will introduce an architecture that, inspired by the classic three-tier architecture, combines slow and fast forms of reasoning, allowing social robots to achieve complex and dynamic behaviors. Since entrusting tasks to the more reactive components complicates their implementation (e.g., it requires the definition of formal rules which may not adequately generalize to unforeseen scenarios), we aim to reduce the technicalities and, consequently, to facilitate to the developers the implementation of the reactive behaviors. By relying on recent achievements in natural language translation, we will describe our recent efforts to adopt Transformer-based architectures, allowing the replacement of formal rules with easier to write “stories”, defined through sequences of perceived events and actions, entrusting the system with the task of learning behaviors by generalizing from them.
This research was funded by the “SI-Robotics: Social robotics for active and healthy ageing” project (Italian M.I.U.R., PON—Ricerca e Innovazione 2014–2020—G.A. ARS01 01120).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
References
Beraldo, G., et al.: Shared autonomy for telepresence robots based on people-aware navigation. In: Ang Jr., M.H., Asama, H., Lin, W., Foong, S. (eds.) IAS 2021. LNNS, vol. 412, pp. 109–122. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-95892-3_9
Bonnefon, J.F., Rahwan, I.: Machine thinking, fast and slow. Trends Cogn. Sci. 24(12), 1019–1027 (2020). http://publications.ut-capitole.fr/41996/
Bunk, T., Varshneya, D., Vlasov, V., Nichol, A.: DIET: lightweight language understanding for dialogue systems. CoRR abs/2004.09936 (2020), https://arxiv.org/abs/2004.09936
Cesta, A., Cortellessa, G., Fracasso, F., Orlandini, A., Turno, M.: User needs and preferences on AAL systems that support older adults and their carers. J. Ambient Intell. Smart Environ. 10(1), 49–70 (2018)
De Benedictis, R., Cesta, A.: Lifted Heuristics for Timeline-based Planning. In: ECAI-2020, 24th European Conference on Artificial Intelligence, pp. 498–2337. Santiago de Compostela, Spain (2020)
De Benedictis, R., Tagliaferri, C., Cortellessa, G., Cesta, A.: Tailoring a forward looking vocal assistant to older adults. In: Bettelli, A., Monteriù, A., Gamberini, L. (eds.) Ambient Assisted Living, pp. 3–17. Springer International Publishing, Cham (2022)
De Benedictis, R., Umbrico, A., Fracasso, F., Cortellessa, G., Orlandini, A., Cesta, A.: A two-layered approach to adaptive dialogues for robotic assistance. In: 2020 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), pp. 82–89 (2020). https://doi.org/10.1109/RO-MAN47096.2020.9223605
Dean, T.L., Wellman, M.P.: Planning and Control. Morgan Kaufmann Publishers Inc. (1991)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). pp. 4171–4186. Association for Computational Linguistics, Minneapolis, Minnesota (Jun 2019). https://doi.org/10.18653/v1/N19-1423, https://aclanthology.org/N19-1423
Gat, E.: On Three-Layer Architectures. In: Artificial Intelligence and Mobile Robots, pp. 195–210. AAAI Press (1997)
Isabet, B., Pino, M., Lewis, M., Benveniste, S., Rigaud, A.S.: Social Telepresence Robots: A Narrative Review of Experiments Involving Older Adults before and during the COVID-19 Pandemic. Int. J. Environ. Res. Public Health 18(7), 3597 (2021)
Jackson, P.: Introduction to Expert Systems, 2nd edn. Addison-Wesley Longman Publishing Co., Inc, USA (1990)
Kahneman, D.: Thinking, fast and slow. Macmillan (2011)
Laniel, S., Létourneau, D., Grondin, F., Labbé, M., Ferland, F., Michaud, F.: Toward enhancing the autonomy of a telepresence mobile robot for remote home care assistance. Paladyn, J. Behav. Robot. 12(1), 214–237 (2021)
Orlandini, A.: ExCITE Project: a review of forty-two months of robotic telepresence technology evolution. Presence 25(3), 204–221 (2016)
Sarker, M.K., Zhou, L., Eberhart, A., Hitzler, P.: Neuro-symbolic artificial intelligence. AI Commun. 34(3), 197–209 (jan 2021). https://doi.org/10.3233/AIC-210084, https://doi.org/10.3233/AIC-210084
Susskind, Z., Arden, B., John, L.K., Stockton, P., John, E.B.: Neuro-symbolic AI: an emerging class of AI workloads and their characterization. CoRR abs/2109.06133 (2021), https://arxiv.org/abs/2109.06133
Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems. vol. 30. Curran Associates, Inc. (2017), https://proceedings.neurips.cc/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf
Vlasov, V., Mosig, J.E.M., Nichol, A.: Dialogue transformers (2019). 10.48550/ARXIV.1910.00486, https://arxiv.org/abs/1910.00486
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
De Benedictis, R., Beraldo, G., Cortellessa, G., Fracasso, F., Cesta, A. (2022). A Transformer-Based Approach for Choosing Actions in Social Robotics. In: Cavallo, F., et al. Social Robotics. ICSR 2022. Lecture Notes in Computer Science(), vol 13817. Springer, Cham. https://doi.org/10.1007/978-3-031-24667-8_18
Download citation
DOI: https://doi.org/10.1007/978-3-031-24667-8_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-24666-1
Online ISBN: 978-3-031-24667-8
eBook Packages: Computer ScienceComputer Science (R0)