Abstract
This work presents a model for improving transparency during robot learning tasks in Human-Robot Interaction scenarios. Our model puts the human in the learning loop by using two categories of robot’s emotional/behavioural reactions, one associated with the learning process of the robot and another elicited as a response to the feedback provided by the user. Preliminary results from a between-subjects study show that people empathized more with a robot expressing its emotions in both the above categories. We noticed a slight increase in the transparency of the robot while it expressed emotions during the learning process and as a response to the user. These findings highlight the importance of emotional behaviours for improving the transparency in the learning systems, which are fundamental for social learning scenarios in future humanoid robotic applications.
This work has been supported by the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 955778, and CHIST-ERA IV COHERENT project “COllaborative HiErarchical Robotic ExplaNaTions”, and Italian PON R &I 2014-2020 - REACT-EU (CUP E65F21002920003).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Arghode, V., Yalvac, B., Liew, J.: Teacher empathy and science education: a collective case study. Eurasia J. Math. Sci. Technol. Educ. 9(2), 89–99 (2013)
Baron-Cohen, S.: The essential difference: the male and female brain. In: Phi Kappa Phi Forum, vol. 85, pp. 23–26 (2005)
Breazeal, C.: Designing sociable machines. In: Socially Intelligent Agents, pp. 149–156. Springer, Heidelberg (2002). https://doi.org/10.1007/0-306-47373-9_18
Broekens, J., Chetouani, M.: Towards transparent robot learning through tdrl-based emotional expressions. IEEE Trans. Affect. Comput. 12(2), 352–362 (2019)
Chvátal, V.: Mastermind. Combinatorica 3(3), 325–329 (1983)
Davis, M.H.: Measuring individual differences in empathy: evidence for a multidimensional approach. J. Pers. Soc. Psychol. 44(1), 113 (1983)
Hindemith, L., Bruns, O., Noller, A.M., Hemion, N., Schneider, S., Vollmer, A.L.: Interactive robot task learning: Human teaching proficiency with different feedback approaches. IEEE Trans. Cogn. Dev. Syst. (2022)
Kwak, S.S., Kim, Y., Kim, E., Shin, C., Cho, K.: What makes people empathize with an emotional robot?: the impact of agency and physical embodiment on human empathy for a robot. In: 2013 IEEE RO-MAN, pp. 180–185. IEEE (2013)
Lin, J., Zhang, Q., Gomez, R., Nakamura, K., He, B., Li, G.: Human social feedback for efficient interactive reinforcement agent learning. In: 2020 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), pp. 706–712. IEEE (2020)
Löffler, D., Schmidt, N., Tscharn, R.: Multimodal expression of artificial emotion in social robots using color, motion and sound. In: 2018 13th ACM/IEEE International Conference on Human-Robot Interaction (HRI), pp. 334–343. IEEE (2018)
Matarese, M., Sciutti, A., Rea, F., Rossi, S.: Toward robots’ behavioral transparency of temporal difference reinforcement learning with a human teacher. IEEE Trans. Hum.-Mach. Syst. 51(6), 578–589 (2021)
McAllister, G., Irvine, J.J.: The role of empathy in teaching culturally diverse students: a qualitative study of teachers’ beliefs. J. Teach. Educ. 53(5), 433–443 (2002)
Pekrun, R.: Emotions and learning. Educ. Pract. Ser. 24(1), 1–31 (2014)
Rossi, A., Dautenhahn, K., Lee Koay, K., Walters, M.L.: How social robots influence people’s trust in critical situations. In: RO-MAN 2020, pp. 1020–1025 (2020)
Rossi, A., Scheunemann, M.M., L’Arco, G., Rossi, S.: Evaluation of a humanoid robot’s emotional gestures for transparent interaction. In: Li, H., et al. (eds.) ICSR 2021. LNCS (LNAI), vol. 13086, pp. 397–407. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-90525-5_34
Suay, H.B., Chernova, S.: Effect of human guidance and state space size on interactive reinforcement learning. In: 2011 Ro-Man, pp. 1–6. IEEE (2011)
Thomaz, A.L., Hoffman, G., Breazeal, C.: Real-time interactive reinforcement learning for robots. In: AAAI 2005 Workshop on Human Comprehensible Machine Learning, pp. 9–13 (2005)
Tiedens, L.Z., Linton, S.: Judgment under emotional certainty and uncertainty: the effects of specific emotions on information processing. J. Pers. Social Psychol. 81(6), 973 (2001)
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
Angelopoulos, G., Rossi, A., L’Arco, G., Rossi, S. (2022). Transparent Interactive Reinforcement Learning Using Emotional Behaviours. 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_27
Download citation
DOI: https://doi.org/10.1007/978-3-031-24667-8_27
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)