Cognitive architectures for autonomous robots: Towards human-level autonomy and beyond.

Morayo Ogunsina 1, *, Christianah Pelumi Efunniyi 2, Olajide Soji Osundare 3, Samuel Olaoluwa Folorunsho 4 and Lucy Anthony Akwawa 5

1 Independent Researcher, Arizona, USA.
2 One Advanced, UK.
3 Nigeria Inter-bank Settlement System Plc (NIBSS), Nigeria.
4 Independent Researcher, London, UK.
5 Information Systems - Business Analytics, Eastern Michigan University, Ypsilanti, Michigan, USA. 
 
Review
International Journal of Frontline Research in Engineering and Technology, 2024, 02(01), 041–050.
Article DOI: 10.56355/ijfret.2024.2.1.0021
Publication history: 
Received on 17 July 2024; revised on 26 August 2024; accepted on 29 August 2024
 
Abstract: 
Achieving human-level autonomy in robots is a complex and multifaceted challenge that requires the development of advanced cognitive architectures. This paper proposes a comprehensive cognitive architecture designed to integrate perception, memory, and decision-making processes, thereby enhancing the adaptability and intelligence of autonomous robots. The proposed architecture is critically examined in terms of its ability to address limitations in existing models, particularly in industrial and social applications. Through a detailed analysis, the paper explores the innovative features of this architecture, such as multimodal perception and continuous learning. It discusses its scalability and flexibility across various domains. The paper also takes a look at the ethical and societal implications of achieving human-level autonomy, emphasizing the need for robust safety protocols and thoughtful integration into human environments. Finally, the paper outlines the ongoing challenges in the field and suggests future research directions to advance the development of autonomous systems further.
 
Keywords: 
Cognitive architecture; Human-level autonomy; Autonomous robots; Perception and decision-making; Continuous learning; Ethical robotics
 
Full text article in PDF: 
 
Copyright information: 
Copyright © 2024 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0