Towards Open and Expandable Cognitive AI Architectures for Large-Scale Multi-Agent Human-Robot Collaborative Learning

Abstract

Learning from Demonstration (LfD) constitutes one of the most robust methodologies for constructing efficient cognitive robotic systems. Despite the large body of research works already reported, current key technological challenges include those of multi-agent learning and long-term autonomy. Towards this direction, a novel cognitive architecture for multi-agent LfD robotic learning is introduced in this paper, targeting to enable the reliable deployment of open, scalable and expandable robotic systems in large-scale and complex environments. In particular, the designed architecture capitalizes on the recent advances in the Artificial Intelligence (AI) (and especially the Deep Learning (DL)) field, by establishing a Federated Learning (FL)-based framework for incarnating a multi-human multi-robot collaborative learning environment. The fundamental conceptualization relies on employing multiple AI-empowered cognitive processes (implementing various robotic tasks) that operate at the edge nodes of a network of robotic platforms, while global AI models (underpinning the aforementioned robotic tasks) are collectively created and shared among the network, by elegantly combining information from a large number of human-robot interaction instances. Regarding pivotal novelties, the designed cognitive architecture a) introduces a new FL-based formalism that extends the conventional LfD learning paradigm to support large-scale multi-agent operational settings, b) elaborates previous FL-based self-learning robotic schemes so as to incorporate the human in the learning loop and c) consolidates the fundamental principles of FL with additional sophisticated AI-enabled learning methodologies for modelling the multi-level inter-dependencies among the robotic tasks. The applicability of the proposed framework is explained using an example of a realworld industrial case study (subject to ongoing research activities) for agile production-based Critical Raw Materials (CRM) recovery. INDEX TERMSLearning from demonstration, human-robot interaction, artificial intelligence, federated learning VOLUME XX, XXXX This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication.

Exploring cognitive reflection for decision-making in robots: Insights and implications

“… Validation Against Human Cognitive Processes: A fundamental challenge lies in aligning robotic cognitive reflection with human cognitive processes. This requires not only the development of sophisticated models that accurately emulate human thought but also interdisciplinary efforts to validate these models against the nuances of human cognition [68][69][70].…”

Aplicación de algoritmos de aprendizaje automático a sistemas robóticos multiagente para la programación y control de operaciones productivas y logísticas: una revisión de la literatura reciente

“…Se han utilizado para actividades complejas y repetitivas. Estos sistemas electromecánicos inicialmente fueron controlados por un computador o circuitos eléctricos específicos (Papadopoulos et al, 2021).…”

Simulation of Creative Manifestation by Functional Ensembles of Intellectual Agents Based on Live Information in Various Spheres of Life Activity

“…In recent years, cognitive systems with functional self-organization technologies have appeared (Banerjee, 2020;Papadopoulos, Antona, & Stephanidis, 2021;Chacón, Ponsa, & Angulo, 2020;Wang, 2020;Zhang, Zeng, Pan, Shi, & Lu, 2021;Sugali, Sprunger, & Venkata, 2021;Babulak, 2021;Bryndin, 2021c). A fundamental step in describing such systems was taken by a Danish scientist who worked in America for many years, Per Buck in the theory of self-organized criticality (Buck, 2013).…”