Q-Learning Elicited Disaster Management System Using Intelligent Mapping Approach

Artificial Intelligence (AI) is one of the thought provoking areas of exploration within the research community. In this area, reinforcement learning and computer vision techniques are coming under the focus. Research in AI focuses on the development and analysis of algorithms that perform intelligent behavior with minimal human intervention. Moreover, from several literatures it has been observed that enormous investigations have also been performed in robotics. In this paper, initially an attempt has been made to design an intelligent system triggered by improved Q-learning algorithm which can map in any unknown disaster environments and perform in a proficient fashion. Thereafter, the concept of robotics has been amalgamated to test the enhanced performance of the proposed system in real time. Thereafter, the performance of the proposed system has also been studied under different environments like constrained and unconstrained.

[1]  Robert H. Cannon,et al.  Utilizing human vision and computer vision to direct a robot in a semi-structured environment via task-level commands , 1995, Proceedings 1995 IEEE/RSJ International Conference on Intelligent Robots and Systems. Human Robot Interaction and Cooperative Robots.

[2]  P. V. Lange,et al.  The psychology of social dilemmas: A review. , 2013 .

[3]  Kao-Shing Hwang,et al.  Gait Balance and Acceleration of a Biped Robot Based on Q-Learning , 2016, IEEE Access.

[4]  Christopher M. Kreucher,et al.  LANA: a lane extraction algorithm that uses frequency domain features , 1999, IEEE Trans. Robotics Autom..

[5]  Hector Muñoz-Avila,et al.  Adaptive Goal Driven Autonomy , 2018, ICCBR.

[6]  Gert Kootstra,et al.  Active exploration and keypoint clustering for object recognition , 2008, 2008 IEEE International Conference on Robotics and Automation.

[7]  Minjie Zhang,et al.  Emotional Multiagent Reinforcement Learning in Spatial Social Dilemmas , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[8]  Alois Knoll,et al.  Orthogonal Image Features for Visual Servoing of a 6-DOF Manipulator With Uncalibrated Stereo Cameras , 2016, IEEE Transactions on Robotics.

[9]  Y.F. Li,et al.  Automatic sensor placement for model-based robot vision , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[10]  Jan Peters,et al.  Computational Intelligence: Principles, Techniques and Applications , 2007, Comput. J..

[11]  Pietro Perona,et al.  Evaluation of Features Detectors and Descriptors based on 3D Objects , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[12]  David W. Aha,et al.  Bounded Expectations for Discrepancy Detection in Goal-Driven Autonomy , 2014, AAAI 2014.