Cognitive Architectures in Autonomous Robotics: A Systematic Review of Behavior Generation Approaches and Evaluation Strategies

Cognitive architectures are an essential component in the development of intelligent autonomous robots, enabling planning, learning, and adaptation to dynamic environments. This paper presents a systematic review of the literature focused on cognitive architectures applied to behavior generation in autonomous robotics. A structured search and selection process was conducted using multiple scientific databases, applying explicit inclusion, exclusion, and quality assessment criteria. From an initial set of 502 studies, 22 publications (2018–mid-2025) were selected for in-depth analysis. The review identifies a growing trend toward hybrid architectures that integrate symbolic reasoning with data-driven methods, such as neural networks and behavior trees. The types of architectures, tools used (such as symbolic planners, neural networks, and behavior trees), middleware employed (with a predominance of Robot Operating System), as well as the methods and metrics used in their evaluation, are analyzed. This review provides a detailed overview of the state of the art and highlights the technologies and approaches currently most widely used in the design of cognitive robotic systems.