An agent-based model for navigation simulation in a heterogeneous environment

Teresa A Shanklin, Purdue University

Abstract

Complex navigation (e.g. indoor and outdoor environments) can be studied as a system-of-systems problem. The model is made up of disparate systems that can aid a user in navigating from one location to another, utilizing whatever sensor system or information is available. By using intelligent navigation sensors and techniques (e.g. RFID, Wifi, GPS, embedded sensors on a mobile device, IMU, etc.) and adaptive techniques to switch between them, brings the possibility of an end-to-end navigational multi-agent system-of-systems (MaSoS). Indoor location-based applications have a broad appeal for development in navigation, robotics, gaming, asset tracking, networking, and more. GPS technologies have been successfully leveraged for outdoor navigation, but often lose effectiveness indoors due to a more constrained environment, possible loss of signal, lack of elevation information and need for better accuracy. Increasingly complex problems in navigation allow for the development of a framework for a system-of-systems. Individual systems contain distributed and heterogeneous components that are disparate in nature. Multiple prototypes and a framework for a multi-agent system-of-systems are presented. The purpose of the model is to overcome the limitations of a single technology navigation system. The system creates a classic system-of-systems utilizing existing and developing localization services. The system provides point-to-point path planning and navigation regardless of the transportation medium, location of the user or current environment.

Degree

Ph.D.

Advisors

Matson, Purdue University.

Subject Area

Information Technology|Artificial intelligence

Off-Campus Purdue Users:
To access this dissertation, please log in to our
proxy server
.

Share

COinS