Staff member


Jordi-Ysard Puigbò Llobet

PhD Student
Synthetic, Perceptive, Emotive and Cognitive Systems (SPECS)
jysard@ibecbarcelona.eu

Staff member publications

Fischer, Tobias, Puigbò, Jordi-Ysard, Camilleri, Daniel, Nguyen, Phuong D. H., Moulin-Frier, Clément, Lallée, Stéphane, Metta, Giorgio, Prescott, Tony J., Demiris, Yiannis, Verschure, P., (2018). iCub-HRI: A software framework for complex human-robot interaction scenarios on the iCub humanoid robot Frontiers in Robotics and AI , 5, (22), Article 22

Generating complex, human-like behaviour in a humanoid robot like the iCub requires the integration of a wide range of open source components and a scalable cognitive architecture. Hence, we present the iCub-HRI library which provides convenience wrappers for components related to perception (object recognition, agent tracking, speech recognition, touch detection), object manipulation (basic and complex motor actions) and social interaction (speech synthesis, joint attention) exposed as a C++ library with bindings for Java (allowing to use iCub-HRI within Matlab) and Python. In addition to previously integrated components, the library allows for simple extension to new components and rapid prototyping by adapting to changes in interfaces between components. We also provide a set of modules which make use of the library, such as a high-level knowledge acquisition module and an action recognition module. The proposed architecture has been successfully employed for a complex human-robot interaction scenario involving the acquisition of language capabilities, execution of goal-oriented behaviour and expression of a verbal narrative of the robot's experience in the world. Accompanying this paper is a tutorial which allows a subset of this interaction to be reproduced. The architecture is aimed at researchers familiarising themselves with the iCub ecosystem, as well as expert users, and we expect the library to be widely used in the iCub community.

Keywords: Robotics, iCub Humanoid, YARP, Software architecture, C++, Python, Java, Human-robot interaction


Puigbò, J. Y., Maffei, G., Herreros, I., Ceresa, M., González Ballester, M. A., Verschure, P. F. M. J., (2018). Cholinergic behavior state-dependent mechanisms of neocortical gain control: A neurocomputational study Molecular Neurobiology , 55, (1), 249-257

The embodied mammalian brain evolved to adapt to an only partially known and knowable world. The adaptive labeling of the world is critically dependent on the neocortex which in turn is modulated by a range of subcortical systems such as the thalamus, ventral striatum, and the amygdala. A particular case in point is the learning paradigm of classical conditioning where acquired representations of states of the world such as sounds and visual features are associated with predefined discrete behavioral responses such as eye blinks and freezing. Learning progresses in a very specific order, where the animal first identifies the features of the task that are predictive of a motivational state and then forms the association of the current sensory state with a particular action and shapes this action to the specific contingency. This adaptive feature selection has both attentional and memory components, i.e., a behaviorally relevant state must be detected while its representation must be stabilized to allow its interfacing to output systems. Here, we present a computational model of the neocortical systems that underlie this feature detection process and its state-dependent modulation mediated by the amygdala and its downstream target the nucleus basalis of Meynert. In particular, we analyze the role of different populations of inhibitory interneurons in the regulation of cortical activity and their state-dependent gating of sensory signals. In our model, we show that the neuromodulator acetylcholine (ACh), which is in turn under control of the amygdala, plays a distinct role in the dynamics of each population and their associated gating function serving the detection of novel sensory features not captured in the state of the network, facilitating the adjustment of cortical sensory representations and regulating the switching between modes of attention and learning.

Keywords: Acetylcholine, Inhibitory network, Neocortical circuits, Neuromodulation


Moulin-Frier, C., Puigbò, J. Y., Arsiwalla, X. D., Sanchez-Fibla, M., Verschure, P., (2018). Embodied artificial intelligence through distributed adaptive control: An integrated framework ICDL-EpiRob 2017 7th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics , IEEE (Lisbon, Portugal) , 324-330

In this paper, we argue that the future of Artificial Intelligence research resides in two keywords: integration and embodiment. We support this claim by analyzing the recent advances in the field. Regarding integration, we note that the most impactful recent contributions have been made possible through the integration of recent Machine Learning methods (based in particular on Deep Learning and Recurrent Neural Networks) with more traditional ones (e.g. Monte-Carlo tree search, goal babbling exploration or addressable memory systems). Regarding embodiment, we note that the traditional benchmark tasks (e.g. visual classification or board games) are becoming obsolete as state-of-the-art learning algorithms approach or even surpass human performance in most of them, having recently encouraged the development of first-person 3D game platforms embedding realistic physics. Building on this analysis, we first propose an embodied cognitive architecture integrating heterogeneous subfields of Artificial Intelligence into a unified framework. We demonstrate the utility of our approach by showing how major contributions of the field can be expressed within the proposed framework. We then claim that benchmarking environments need to reproduce ecologically-valid conditions for bootstrapping the acquisition of increasingly complex cognitive skills through the concept of a cognitive arms race between embodied agents.

Keywords: Cognitive Architectures, Embodied Artificial Intelligence, Evolutionary Arms Race, Unified Theories of Cognition


Puigbò, J. Y., Arsiwalla, X. D., Verschure, P., (2018). Challenges of machine learning for living machines Biomimetic and Biohybrid Systems 7th International Conference, Living Machines 2018 (Lecture Notes in Computer Science) , Springer International Publishing (Paris, France) 10928, 382-386

Machine Learning algorithms (and in particular Reinforcement Learning (RL)) have proved very successful in recent years. These have managed to achieve super-human performance in many different tasks, from video-games to board-games and complex cognitive tasks such as path-planning or Theory of Mind (ToM) on artificial agents. Nonetheless, this super-human performance is also super-artificial. Despite some metrics are better than what a human can achieve (i.e. cumulative reward), in less common metrics (i.e. time to learning asymptote) the performance is significantly worse. Moreover, the means by which those are achieved fail to extend our understanding of the human or mammal brain. Moreover, most approaches used are based on black-box optimization, making any comparison beyond performance (e.g. at the architectural level) difficult. In this position paper, we review the origins of reinforcement learning and propose its extension with models of learning derived from fear and avoidance behaviors. We argue that avoidance-based mechanisms are required when training on embodied, situated systems to ensure fast and safe convergence and potentially overcome some of the current limitations of the RL paradigm.

Keywords: Avoidance, Neural networks, Reinforcement learning


Freire, I. T., Arsiwalla, X. D., Puigbò, J. Y., Verschure, P., (2018). Limits of multi-agent predictive models in the formation of social conventions Frontiers in Artificial Intelligence and Applications (ed. Falomir, Z., Gibert, K., Plaza, E.), IOS Press (Amsterdam, The Netherlands) Volume 308: Artificial Intelligence Research and Development, 297-301

A major challenge in cognitive science and AI is to understand how intelligent agents might be able to predict mental states of other agents during complex social interactions. What are the computational principles of such a Theory of Mind (ToM)? In previous work, we have investigated hypotheses of how the human brain might realize a ToM of other agents in a multi-agent social scenario. In particular, we have proposed control-based cognitive architectures to predict the model of other agents in a game-theoretic task (Battle of the Exes). Our multi-layer architecture implements top-down predictions from adaptive to reactive layers of control and bottom-up error feedback from reactive to adaptive layers. We tested cooperative and competitive strategies among different multi-agent models, demonstrating that while pure RL leads to reasonable efficiency and fairness in social interactions, there are other architectures that can perform better in specific circumstances. However, we found that even the best predictive models fall short of human data in terms of stability of social convention formation. In order to explain this gap between humans and predictive AI agents, in this work we propose introducing the notion of trust in the form of mutual agreements between agents that might enhance stability in the formation of conventions such as turn-taking.

Keywords: Cognitive Architectures, Game Theory, Multi-Agent Models, Reinforcement Learning, Theory of Mind


Moulin-Frier, C., Puigbò, J.-Y., Arsiwalla, Xerxes D., Martì Sanchez-Fibla, M., Verschure, Paul F. M. J., (2017). Embodied artificial intelligence through distributed adaptive control: An integrated framework 7th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-Epirob 2017) , IEEE (Lisbon, Portugal) , 1-8

In this paper, we argue that the future of Artificial Intelligence research resides in two keywords: integration and embodiment. We support this claim by analyzing the recent advances of the field. Regarding integration, we note that the most impactful recent contributions have been made possible through the integration of recent Machine Learning methods (based in particular on Deep Learning and Recurrent Neural Networks) with more traditional ones (e.g. Monte-Carlo tree search, goal babbling exploration or addressable memory systems). Regarding embodiment, we note that the traditional benchmark tasks (e.g. visual classification or board games) are becoming obsolete as state-of-the-art learning algorithms approach or even surpass human performance in most of them, having recently encouraged the development of first-person 3D game platforms embedding realistic physics. Building upon this analysis, we first propose an embodied cognitive architecture integrating heterogenous sub-fields of Artificial Intelligence into a unified framework. We demonstrate the utility of our approach by showing how major contributions of the field can be expressed within the proposed framework. We then claim that benchmarking environments need to reproduce ecologically-valid conditions for bootstrapping the acquisition of increasingly complex cognitive skills through the concept of a cognitive arms race between embodied agents.

Keywords: Cognitive Architectures, Embodied Artificial Intelligence, Evolutionary Arms Race, Unified Theories of Cognition


Puigbò, Jordi-Ysard, Gonzalez-Ballester, Miguel Ángel, Verschure, Paul , (2017). Behavior-state dependent modulation of perception based on a model of conditioning Biomimetic and Biohybrid Systems 6th International Conference, Living Machines 2017 (Lecture Notes in Computer Science) , Springer International Publishing (Standfor, USA) 10384, 387-393

The embodied mammalian brain evolved to adapt to an only partially known and knowable world. The adaptive labeling of the world is critically dependent on the neocortex which in turn is modulated by a range of subcortical systems such as the thalamus, ventral striatum and the amygdala. A particular case in point is the learning paradigm of classical conditioning where acquired representations of states of the world such as sounds and visual features are associated with predefined discrete behavioral responses such as eye blinks and freezing. Learning progresses in a very specific order, where the animal first identifies the features of the task that are predictive of a motivational state and then forms the association of the current sensory state with a particular action and shapes this action to the specific contingency. This adaptive feature selection has both attentional and memory components, i.e. a behaviorally relevant state must be detected while its representation must be stabilized to allow its interfacing to output systems. Here we present a computational model of the neocortical systems that underlie this feature detection process and its state dependent modulation mediated by the amygdala and its downstream target, the nucleus basalis of Meynert. Specifically, we analyze how amygdala driven cholinergic modulation these mechanisms through computational modeling and present a framework for rapid learning of behaviorally relevant perceptual representations.