An Edge-detection and HPF Based Intelligent Space - A Network Based Integrated Navigation System.

Abstract

Intelligent space (iSpace) is a large scale mechatronics system. It is a multidisciplinary effort whose aim is to produce a network structure and components that are capable of integrating sensors, actuators, DSP, communication, and control algorithms in a manner that suits time-sensitive applications including real-time navigation and/or obstacle avoidance. There are many challenges that must be overcome in order to put such a distributed, heterogeneous system together. The research presented here deals with one of these issues, i.e. the adverse effect of processing delays on the system. Here a novel structure for a delay-resistant sensory-motor module to navigate a differential drive unmanned ground vehicle (UGV) in a cluttered environment is suggested. The module consists of an early vision edge detection stage, a harmonic potential field (HPF) planner; a network based quadratic curve fitting controller and gain schedule middleware (GSM). The structure of this module and its components are described. Thorough experimental results along with performance assessment comparing to the previous implementation are also provided.