퍼지 규칙과 신경망을 이용한 센서 네트워크 기반 이동 로봇의 냄새 검출 및 추적

Abstract

This thesis represents a mobile robot, which can recognize chemical odor, measure concentration, and track its source indoors. The mobile robot has the function of smell that can sort several gases in experiment such as ammonia, ethanol, and their mixture with neural network algorithm and measure each gas concentration with fuzzy rules. In addition, it can not only navigate to the desired position with vision system by avoiding obstacles but also transmit odor information and warning messages earned from its own operations to other nodes by multi-hop communication in wireless sensor network. We suggest the way of odor sorting, concentration measurement, and source tracking for a mobile robot in wireless sensor network using a new algorithm with vision system and gas sensors. The experimental studies prove that the efficiency of the proposed algorithm for odor recognition, concentration measurement, and source tracking is superior to the existing one.