Autonomous Mobile Robot Navigation using Artificial Immune System

Authors:
Kunal Shrivastava;Shashi Shekhar Jha;Shivashankar B. Nair
Affiliations:
Department of Computer Science & Engineering IIT, Guwahati, India;Department of Computer Science & Engineering IIT, Guwahati, India;Department of Computer Science & Engineering IIT, Guwahati, India
Venue:
Proceedings of Conference on Advances In Robotics
Year:
2013

Citing 7
Cited 0

The immune system, adaptation, and machine learning

Physica D
Artficial Immune Systems and Their Applications

Artficial Immune Systems and Their Applications
Artificial Immune Systems: A New Computational Intelligence Paradigm

Artificial Immune Systems: A New Computational Intelligence Paradigm
A 3-level autonomous mobile robot navigation system designed by using reasoning/search approaches

Robotics and Autonomous Systems
Decentralized control system for autonomous navigation based on an evolved artificial immune network

CEC '02 Proceedings of the Evolutionary Computation on 2002. CEC '02. Proceedings of the 2002 Congress - Volume 02
Review Article: Recent Advances in Artificial Immune Systems: Models and Applications

Applied Soft Computing
Learning and optimization using the clonal selection principle

IEEE Transactions on Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

The principles of the Artificial Immune System (AIS) have been applied to a wide range of applications including that of robotics. Most of the research carried out so far has been based on either of the two prominent AIS models viz. the Clonal selection model and the Idiotypic model. In this paper we present an AIS based mechanism for the navigation of an autonomous mobile robot by blending both these models. This hybrid mechanism was tested on a real robot situated in an unknown environment comprising obstacles and unfavourable conditions. The main objective of the robot was to discover safe zones within the environment. An inherent pain is generated within the robot as and when it encounters unfavorable situation. The AIS within the robot uses the values reported by the on-board sensors as an antigen and the reduction in pain as a reward to generate a repertoire of antibodies or actions using the Clonal Selection model. These learned antibodies form an Idiotypic network which triggers the appropriate antibodies on-demand to facilitate navigation towards the goal. The results obtained in different test cases suggest that the proposed model is viable and able to cope up with different environmental conditions.