Cognitive architectures and autonomy: Commentary and Response (original) (raw)

Cognitive Architectures and Autonomy: A Comparative Review

Journal of Artificial General Intelligence, 2012

One of the original goals of artificial intelligence (AI) research was to create machines with very general cognitive capabilities and a relatively high level of autonomy. It has taken the field longer than many had expected to achieve even a fraction of this goal; the community has focused on building specific, targeted cognitive processes in isolation, and as of yet no system exists that integrates a broad range of capabilities or presents a general solution to autonomous acquisition of a large set of skills. Among the reasons for this are the highly limited machine learning and adaptation techniques available, and the inherent complexity of integrating numerous cognitive and learning capabilities in a coherent architecture. In this paper we review selected systems and architectures built expressly to address integrated skills. We highlight principles and features of these systems that seem promising for creating generally intelligent systems with some level of autonomy, and discuss them in the context of the development of future cognitive architectures. Autonomy is a key property for any system to be considered generally intelligent, in our view; we use this concept as an organizing principle for comparing the reviewed systems. Features that remain largely unaddressed in present research, but seem nevertheless necessary for such efforts to succeed, are also discussed.

Generic Cognitive Architecture for Real-Time, Embedded Cognitive Systems

Context. The problem of integrated cognition belongs to a multidisciplinary area of cognitive engineering. The multidisciplinary focusing on cognitive models and real-time embedded systems, such as mobile robots, helps to reveal a broader and deeper understanding of robotics as part of everyday life and society. Over the past decades many cognitive architectures have been proposed and steadily developed, based on different approaches and methodologies, but still current cognitive architectures are far from the goal of covering the requirements for general intelligence. Recent research in the area of evolutionary algorithms and genetic programming is used in this study as an inspiration for developing the new version of integrated cognitive architecture, and the knowledge of human brain structure and functions is applied to the architecture as well. Objectives. In this study a survey of cognitive architectures is performed, a version of biologically inspired hybrid cognitive architecture is developed. This architecture is influenced by a contemporary research in evolutionary algorithms and genetic programming. Some modules of the architecture are applied to a mobile robot in a simulated environment. Methods. Several different research methods are used in the thesis, such as literature study, case study and simulated experimentations. The source of the literature, used for the literature study, is Internet and the e-library's resources, freely available for the students. The selection criteria are rely on a trusted-review strategy, that means a review of a subject area published by trusted sources, such as highly ranked journals. The relevance is evaluated by fitness with a purpose of the study. Case study is conducted by investigating the characteristics and abilities of a simple mobile robot in an experimental environment. Experiments of robot's navigating in different environments with some modules of integrated cognitive architecture implemented are conducted in a simulated environment. Robot's wall following behaviour is analysed applying two different genetic programming methods and three different fitness functions. Robot's learning abilities are analysed using different training environments and comparing the navigation output afterwards. Results. The statistical information is gathered during the experiments in order to analyze the performance of a robot's behaviour. For each generation of an evolutionary run average and best population fitness values, complexity of the chromosomes, the number of robot's collisions with other objects and the value of population entropy are stored. Conclusions. The results indicate that the proposed integrated cognitive architecture is plausible and can be implemented successfully to a mobile robot. The implementation of the two modules is described in this thesis, while developing and implementation of other modules is indicated as a future work of the author. For robot control, the results indicate that genetic programming methods can be successfully integrated with a subsumption architecture and used as a learning mechanism. Different fitness functions, from the other side, can be used for designing relevant navigation behaviour, such as wall following and others. Both genetic programming methods and fitness functions are influencing the quality of robot navigation behaviour. The interaction of these two factors also has an influence on the navigation performance. The results of learning experiments highlight the influence of specific training environments on the future navigational performance.

The Soar of Cognitive Architectures

this paper presents a review of "How AI, cognitive science and DM are combined to develop intelligent agents", and how the paradigm first shifted from AI to Data mining and then towards combination of data mining and artificial intelligence. The paper will also provide a state-of-the-art account of the cognitive architectures. It also gives a detailed comparative study of all the architectures discussed in the paper. All the survey of data mining and cognitive architecture is done w.r.t Multi agent systems. Therefore, paper will also provide a bird eye view of MAS/ ABMS.

The Role of Cognitive Architectures in General Artificial Intelligence

2017

The term " Cognitive Architectures " indicates both abstract models of cognition, in natural and artificial agents, and the software instantiations of such models which are then employed in the field of Artificial Intelligence (AI). The main role of Cognitive Architectures in AI is that one of enabling the realization of artificial systems able to exhibit intelligent behavior in a general setting through a detailed analogy with the constitutive and developmental functioning and mechanisms underlying human cognition. We provide a brief overview of the status quo and of the potential role that Cognitive Architectures may serve in the fields of Computational Cognitive Science and Artificial Intelligence (AI) research.

Towards a Robust Cognitive Architecture for Autonomous Mobile Robots

2000

, and for the others who kindly helped when necessary. Special thanks to my parents, Gul and Mehmet Kose, for their motivation, kindness and help during this study, and for the rest of my life. This thesis is dedicated to Aliye Kanbur, who was always a good friend, more than just being a grand mother.

Architectures for Cognitive Systems

There has been increased interest recently in cognitive and behavior-based agent architectures and cognitive models of human behavior. This interest results in part from advances in agent technology, cognitive neuroscience and emotion research that make such models possible, and in part from maturing applications that require, or benefit from, the inclusion of different emotion-related aspects (e.g., adaptive human-computer interfaces, social and expressive robots, autonomous agents, decision support systems, etc). The objective of this paper is to present an architecture within which a large variety of modules/mechanisms are decomposed by function and structure and are interconnected by situated recomposition methods. The result of such recomposition is different types of perceptions, cognitive methods and behaviours. Another aspect is also presented which has not been commonly addressed in most architectures of this type: the distinction between cognition as a control structure fo...

Cognitive architectures: Research issues and challenges Action editor: Ron Sun

In this paper, we examine the motivations for research on cognitive architectures and review some candidates that have been explored in the literature. After this, we consider the capabilities that a cognitive architecture should support, some properties that it should exhibit related to representation, organization, performance, and learning, and some criteria for evaluating such architectures at the systems level. In closing, we discuss some open issues that should drive future research in this important area.

Cognitive Architectures: Where do we go from here?

Artificial Intelligence and Applications, 2008

Abstract. Cognitive architectures play a vital role in providing blueprints for building future intelligent systems supporting a broad ,range of capabilities similar to ,those of humans. ,How useful are existing architectures for creating artificial general intelligence? A critical survey of the state of the art in cognitive architectures is presented ,providing a useful insight into the possible frameworks ,for general

AFRANCI : multi-layer architecture for cognitive agents

2012

The development of Autonomous and Intelligent agents, capable of accomplishing goals and survive in complex, dynamic and unpredictable environments is a highly complex task. In this context, intelligence, is regarded as an adaptive and a fast behaviour that agents use to survive in the environments.

Cognitive architectures: Research issues and challenges

Cognitive Systems Research, 2009

In this paper, we examine the motivations for research on cognitive architectures and review some candidates that have been explored in the literature. After this, we consider the capabilities that a cognitive architecture should support, some properties that it should exhibit related to representation, organization, performance, and learning, and some criteria for evaluating such architectures at the systems level. In