Path Planning of the Fire Escaping System Using Active Detection Module

Ying Yao Ting, Huan Sheng Wang, Kuo Lan Su


This article proposes a security system which detects the fire events and plans the moving route. Each robot with several modules owns the shape of cylinder and height, weight and diameter is 18cm, 1.5kg and 8cm. A main controller (STC12C5A60S2) equips robots as a microprocessor. Each robot has the capability to escape from the fire scene. Whenever detecting fires and obstacles using image sensor and reflective IR sensors, robots send the ID code, orientation, and position to the centralized computer and other robots. After other robots have confirmed the fire events, the centralized computer uses the Gaussian probability function to calculate the danger values of the surrounding points near the fire source. And Bayesian estimation method is applied to compute the total estimated value of each point in platform. Furthermore, the total weighted values of all points are shown in a platform and its aim is to enlarge the difference between danger and safety without ambiguity. A* algorithm is used in the escaping routes are planned by a centralized computer. The mobile robot follows the leading of the supervised computer autonomously to escape from dangerous areas. The air-fuel ratio and the rate of increasing in temperature with distance are directly proportional to the danger value. Associating the increasing temperature rate with three-fire sources, it is verified to be an efficient system.


A* algorithm; Air-fuel mass ratio; Path planning

Full Text:




  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

IAES International Journal of Robotics and Automation (IJRA)
ISSN 2089-4856, e-ISSN 2722-2586
This journal is published by the Institute of Advanced Engineering and Science (IAES) in collaboration with Intelektual Pustaka Media Utama (IPMU).

Web Analytics Made Easy - Statcounter IJRA Visitor Statistics