ABSTRACT
Robots designed to collaborate with human partners should be able to implicitly anticipate and adapt to their needs. To do so, robots need a framework supporting cognition and mutual understanding in social settings. We posit that even basic cognitive processes, such as learning, could benefit from considering the social and affective dimensions. In this direction, we propose a recently developed scenario, based on a competitive game, as a tool to steer the development of socially-aware competitive reinforcement learning (RL).
- Pablo Barros, Alessandra Sciutti, Anne C Bloem, Inge M Hootsmans, Lena M Opheij, Romain HA Toebosch, and Emilia Barakova. 2021. It’s Food Fight! Designing the Chef’s Hat Card Game for Affective-Aware HRI. In Comp. 2021 ACM/IEEE International Conference on Human-Robot Interaction. 524–528.Google Scholar
- Pablo Barros, Ana Tanevska, Francisco Cruz, and Alessandra Sciutti. 2020. Moody Learners-Explaining Competitive Behaviour of Reinforcement Learning Agents. In 2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob). IEEE, 1–8.Google Scholar
- Pablo Barros, Ana Tanevska, Ozge Yalcin, and Alessandra Sciutti. 2020. Incorporating Rivalry in reinforcement learning for a competitive game.Google Scholar
- Nikhil Churamani, Matthias Kerzel, Erik Strahl, Pablo Barros, and Stefan Wermter. 2017. Teaching emotion expressions to a human companion robot using deep neural architectures. In 2017 International Joint Conference on Neural Networks (IJCNN). IEEE, 627–634.Google ScholarCross Ref
- Yiannis Demiris and Matthew Johnson. 2003. Distributed, predictive perception of actions: A biologically inspired robotics architecture for imitation and learning. Connection Science (2003). https://doi.org/10.1080/09540090310001655129Google Scholar
- Yuan Gao, Fangkai Yang, Martin Frisk, Daniel Hemandez, Christopher Peters, and Ginevra Castellano. 2019. Learning Socially Appropriate Robot Approaching Behavior Toward Groups using Deep Reinforcement Learning. In 2019 28th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN). IEEE, 1–8.Google ScholarDigital Library
- Riitta Hari, Linda Henriksson, Sanna Malinen, and Lauri Parkkonen. 2015. Centrality of Social Interaction in Human Brain Function. Neuron 88, 1 (2015), 181–193. https://doi.org/10.1016/j.neuron.2015.09.022Google ScholarCross Ref
- Gavin J Kilduff. 2014. Driven to win: Rivalry, motivation, and performance. Social Psychological and Personality Science 5, 8 (2014), 944–952.Google ScholarCross Ref
- Iuliia Kotseruba and John K. Tsotsos. 2020. 40 years of cognitive architectures: core cognitive abilities and practical applications. Artificial Intelligence Review(2020). https://doi.org/10.1007/s10462-018-9646-yGoogle Scholar
- Jennifer S. Lerner, Ye Li, Piercarlo Valdesolo, and Karim S. Kassam. 2015. Emotion and decision making. Annual Review of Psychology(2015). https://doi.org/10.1146/annurev-psych-010213-115043Google Scholar
- Antonio Lieto. 2021. Cognitive Design for Artificial Minds. Routledge.Google Scholar
- Antonio Lieto, William G Kennedy, Christian Lebiere, Oscar J Romero, Niels Taatgen, and Robert L West. 2018. Higher-level knowledge, rational and social levels constraints of the common model of the mind. Procedia computer science 145 (2018), 757–764.Google Scholar
- Zimo Liu, Jingya Wang, Shaogang Gong, Huchuan Lu, and Dacheng Tao. 2019. Deep reinforcement active learning for human-in-the-loop person re-identification. In Proceedings of the IEEE International Conference on Computer Vision. 6122–6131.Google ScholarCross Ref
- Federico Manzi, Angela Sorgente, Davide Massaro, Daniela Villani, Daniele Di Lernia, Clelia Malighetti, Andrea Gaggioli, Domenico Rossignoli, Giulio Sandini, Alessandra Sciutti, Francesco Rea, Mario A. Maggioni, Antonella Marchetti, and Giuseppe Riva. 2021. Emerging Adults’ Expectations About the Next Generation of Robots: Exploring Robotic Needs Through a Latent Profile Analysis. Cyberpsychology, Behavior, and Social Networking (2021). https://doi.org/10.1089/cyber.2020.0161Google Scholar
- Carlo Mazzola, Alexander Mois Aroyo, Francesco Rea, and Alessandra Sciutti. 2020. Interacting with a social robot affects visual perception of space. In ACM/IEEE International Conference on Human-Robot Interaction. https://doi.org/10.1145/3319502.3374819Google ScholarDigital Library
- Hamidreza Modares, Isura Ranatunga, Frank L Lewis, and Dan O Popa. 2015. Optimized assistive human–robot interaction using reinforcement learning. IEEE transactions on cybernetics 46, 3 (2015), 655–667.Google Scholar
- Ioannis Papaioannou and Oliver Lemon. 2017. Combining chat and task-based multimodal dialogue for more engaging HRI: A scalable method using reinforcement learning. In Proceedings of the Companion of the 2017 ACM/IEEE International Conference on Human-Robot Interaction. 365–366.Google ScholarDigital Library
- Giulio Sandini, Alessandra Sciutti, and David Vernon. 2021 (submitted). Cognitive Robots. In Encyclopedia of Robotics. Springer.Google Scholar
- Damian A. Stanley and Ralph Adolphs. 2013. Toward a neural basis for social behavior. https://doi.org/10.1016/j.neuron.2013.10.038Google Scholar
- A. Tanevska, F. Rea, G. Sandini, L. Cañamero, and A. Sciutti. 2020. A Socially Adaptable Framework for Human-Robot Interaction. Frontiers in Robotics and AI 7 (2020). https://doi.org/10.3389/frobt.2020.00121Google Scholar
- Nguyen Tan Viet Tuyen, Sungmoon Jeong, and Nak Young Chong. 2018. Emotional Bodily Expressions for Culturally Competent Robots through Long Term Human-Robot Interaction. In 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2008–2013.Google ScholarCross Ref
- Greet Van de Perre, Hoang-Long Cao, Albert De Beir, Pablo Gómez Esteban, Dirk Lefeber, and Bram Vanderborght. 2018. Generic method for generating blended gestures and affective functional behaviors for social robots. Autonomous Robots 42, 3 (2018), 569–580.Google ScholarDigital Library
- David Vernon. 2014. Artificial cognitive systems: A primer. MIT Press.Google Scholar
- David Vernon, Claes von Hofsten, and Luciano Fadiga. 2016. Desiderata for developmental cognitive architectures. Biologically Inspired Cognitive Architectures 18 (2016), 116–127.Google ScholarCross Ref
- Alessia Vignolo, Nicoletta Noceti, Francesco Rea, Alessandra Sciutti, Francesca Odone, and Giulio Sandini. 2017. Detecting biological motion for human–robot interaction: A link between perception and action. Frontiers in Robotics and AI 4 (2017), 14.Google ScholarCross Ref
- Oriol Vinyals, Igor Babuschkin, Wojciech M Czarnecki, Michaël Mathieu, Andrew Dudzik, Junyoung Chung, David H Choi, Richard Powell, Timo Ewalds, Petko Georgiev, 2019. Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575, 7782 (2019), 350–354.Google Scholar
Index Terms
- Affect-Aware Learning for Social Robots
Recommendations
Intrinsically motivated model learning for developing curious robots
Reinforcement Learning (RL) agents are typically deployed to learn a specific, concrete task based on a pre-defined reward function. However, in some cases an agent may be able to gain experience in the domain prior to being given a task. In such cases, ...
Emotion and reinforcement: affective facial expressions facilitate robot learning
ICMI'06/IJCAI'07: Proceedings of the ICMI 2006 and IJCAI 2007 international conference on Artifical intelligence for human computingComputer models can be used to investigate the role of emotion in learning. Here we present EARL, our framework for the systematic study of the relation between emotion, adaptation and reinforcement learning (RL). EARL enables the study of, among other ...
Effects of form and motion on judgments of social robots' animacy, likability, trustworthiness and unpleasantness
One of robot designers' main goals is to make robots as sociable as possible. Aside from improving robots' actual social functions, a great deal of effort is devoted to making them appear lifelike. This is often achieved by endowing the robot with an ...
Comments