An Immune Learning Classifier Network for Autonomous Navigation

Vargas, Patrícia A.; Castro, Leandro Nunes de; Michelan, Roberto; Zuben, Fernando J. Von

doi:10.1007/978-3-540-45192-1_7

Cited by 24 publications

(22 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, [7] uses activation A(x i ), defined as the product of the global strength of match T g (x i ) and the concentration; see (9). This method of assessing fitness is adopted here as it incorporates both the AIS and RL aspects of the hybrid system…”

Section: A Equations Used To Model the Networkmentioning

confidence: 99%

Idiotypic Immune Networks in Mobile-Robot Control

Whitbrook

Aickelin

Garibaldi

2007

IEEE Trans. Syst., Man, Cybern. B

View full text Add to dashboard Cite

Abstract-Jerne's idiotypic-network theory postulates that the immune response involves interantibody stimulation and suppression, as well as matching to antigens. The theory has proved the most popular artificial immune system (AIS) model for incorporation into behavior-based robotics, but guidelines for implementing idiotypic selection are scarce. Furthermore, the direct effects of employing the technique have not been demonstrated in the form of a comparison with nonidiotypic systems. This paper aims to address these issues. A method for integrating an idiotypic AIS network with a reinforcement-learning (RL)-based control system is described, and the mechanisms underlying antibody stimulation and suppression are explained in detail. Some hypotheses that account for the network advantage are put forward and tested using three systems with increasing idiotypic complexity. The basic RL, a simplified hybrid AIS-RL that implements idiotypic selection independently of derived concentration levels, and a full hybrid AIS-RL scheme are examined. The test bed takes the form of a simulated Pioneer robot that is required to navigate through maze worlds detecting and tracking door markers.Index Terms-Artificial immune system (AIS), behavior arbitration mechanism, idiotypic-network theory, reinforcement learning (RL).

show abstract

Section: A Equations Used To Model the Networkmentioning

confidence: 99%

Idiotypic Immune Networks in Mobile-Robot Control

Whitbrook

Aickelin

Garibaldi

2007

IEEE Trans. Syst., Man, Cybern. B

View full text Add to dashboard Cite

show abstract

“…Vergas et al [39] devised a combined system named as CLARINET. CLARINET is an immune network of classifiers which works on automated movement by amalgamating the advantages of classifier systems based on learning process, evolutionary algorithms, and a modular structure named as immune network model.…”

Section: International Journal Of Computer Applications (0975 -8887) mentioning

confidence: 99%

Artificial Immune System: State of the Art Approach

Mishra¹,

Bhusry²

2015

IJCA

View full text Add to dashboard Cite

The inspiration of framing the artificially developed immune system (AIS) is done through the biological immune system which compromise of signified information processing and self-adapting system. Since it originated in the 1990s, the branch of AIS gets a significant success in the field of Computational Intelligence. Present paper insights major works in the area of AIS and explore current advancements in applied system since past years. It has been observed that the particular research focused on three major considerable algorithms of AIS: (1) clonal selection algorithms (2) negative selection algorithm (3) artificial immune networks. However, computer scientists and engineers are motivated by the biological immune system to evolve new models and problem solving approaches. Developed AIS applications in extensive amount have received a lot of researcher's attention who were planning to establish models based on immune system and techniques in order to provide solutions for complicated problems of engineering. This paper presents a survey of current models of AIS and its algorithms.

show abstract

“…However, the sets of possible behaviours and preconditions are fixed; the GA works simply by mixing and evolving different combinations with various parameters for the idiotope. Michelan and Von Zuben (2002) and Vargas et al (2003) also use GAs to evolve the antibodies, but again only the idiotypic-network connections are derived. Krautmacher and Dilger (2004) apply the idiotypic method to robot navigation, but their emphasis is on the use of a variable set of antigens; they do not change or develop the initial set of handcrafted antibodies, as only the network links are evolved.…”

Section: Background and Motivationmentioning

confidence: 99%

Genetic-Algorithm Seeding of Idiotypic Networks for Mobile-Robot Navigation

Whitbrook

Aickelin

Garibaldi

2008

Proceedings of the Fifth International Conference on Informatics in Control, Automation and Robotics Service

View full text Add to dashboard Cite

Abstract:Robot-control designers have begun to exploit the properties of the human immune system in order to produce dynamic systems that can adapt to complex, varying, real-world tasks. Jerne's idiotypic-network theory has proved the most popular artificial-immune-system (AIS) method for incorporation into behaviour-based robotics, since idiotypic selection produces highly adaptive responses. However, previous efforts have mostly focused on evolving the network connections and have often worked with a single, preengineered set of behaviours, limiting variability. This paper describes a method for encoding behaviours as a variable set of attributes, and shows that when the encoding is used with a genetic algorithm (GA), multiple sets of diverse behaviours can develop naturally and rapidly, providing much greater scope for flexible behaviour-selection. The algorithm is tested extensively with a simulated e-puck robot that navigates around a maze by tracking colour. Results show that highly successful behaviour sets can be generated within about 25 minutes, and that much greater diversity can be obtained when multiple autonomous populations are used, rather than a single one.

show abstract

An Immune Learning Classifier Network for Autonomous Navigation

Cited by 24 publications

References 7 publications

Idiotypic Immune Networks in Mobile-Robot Control

Idiotypic Immune Networks in Mobile-Robot Control

Artificial Immune System: State of the Art Approach

Genetic-Algorithm Seeding of Idiotypic Networks for Mobile-Robot Navigation

Contact Info

Product

Resources

About