3 April 2023 in IEEE Access
Automated Guided Vehicle (AGV) have received a lot of attention in recent years in terms of both hardware and software research. Nowadays, the AGV offer more adaptable and effective industrial and transportation system solutions. An AGV navigation techniques is essential to its operation. The decision to use AGV navigation is not simple, though to be suite to the application and sufficient. This paper survey the navigation approaches applied in AGV in the past five years of published academic research. In doing so, this work responds to three related questions: (1) is the AGV classical navigation techniques still relevant to the current application area; (2) is the heuristic navigation techniques itself able to optimize AGV movement in term of guide and strategy; (3) is the use of Artificial Intelligence (AI) in AGV navigation techniques able to increase system performance. As a result, numerous techniques for the AGV navigation have been developed globally. On the other hand, the most popular navigation approaches are provided below for more research.
1 December 2023 in IEEE Transactions on Instrumentation and Measurement
Automated guided vehicles (AGVs) have recently acquired a lot of interest in the academic research field and industry applications due to a variety of advantages, including increased mobility and improved safety. AGVs are designed to maneuver following a predetermined path; however, if the path is blocked, how can the AGV avoid or pass through it by selecting the new path with the safest behavior? This article discovered a number of recent advanced methods that are widely employed in AGV operation with the aim of avoiding dynamic obstacles and being able to function in a complex environment. The most recent techniques for obstacle avoidance utilized with AGV have been evaluated in scholarly research that has been published in the last five years. In doing so, this review responds to three related questions: are the fundamental approaches for avoiding obstacles in AGV robot systems still applicable? 2) which is the most recent sensor technology used by the AGV robot to sense its surroundings? and 3) does the artificial intelligence (AI) method improve the AGV robot’s ability to make decisions and function autonomously? As a result, various fundamental and recent advances in methods are covered. This study is done to make it easier for researchers or engineers to comprehend and conduct more research.
6 April 2023 in IEEE Access
Global path planning techniques have been widely employed in solving path planning problems, however they have been found to be unsuitable for unknown environments. Contrarily, the traditional Q-learning method, which is a common reinforcement learning approach for local path planning, is unable to complete the task for multiple targets. To address these limitations, this paper proposes a modified Q-learning method, called Vector Field Histogram based Q-learning (VFH-QL) utilized the VFH information in state space representation and reward function, based on a 2D LiDAR sensor. We compared the performance of our proposed method with the classical Q-learning method (CQL) through training experiments that were conducted in a simulated environment with a size of 400 square pixels, representing a 20-meter square map. The environment contained static obstacles and a single mobile robot. Two experiments were conducted: experiment A involved path planning for a single target, while experiment B involved path planning for multiple targets. The results of experiment A showed that VFH-QL method had 87.06% less training time and 99.98% better obstacle avoidance compared to CQL. In experiment B, VFH-QL method was found to have an average training time that was 95.69% less than that of the CQL method and 83.99% better path quality. The VFH-QL method was then evaluated using a benchmark dataset. The results indicated that the VFH-QL exhibited superior path quality, with efficiency of 94.89% and improvements of 96.91% and 96.69% over CQL and SARSA in the task of path planning for multiple targets in unknown environments.
1 September 2020 in IOP Conference Series: Materials Science and Engineering
A confined space has a limited space for entry and exit but it is large enough for workers to enter and perform work inside. It is not designed for continuous occupancy because it can contribute atmospheric hazards accidents that threaten the worker safety and industry progress. In this work, we reported the testing an instrument to assist workers for atmosphere testing during pre-entry. An electronic nose (e-nose) using specific sensor arrays is the integration between hardware and software that able to sense different concentrations of gases in an air sample using pattern recognition techniques. The instrument utilizes multivariate statistical analysis which is Principal Component Analysis (PCA) for discriminate the different concentrations of gases and the Support Vector Machine (SVM) to classify the acquired data from the air sample. The instrument was successfully tested using diesel, gasoline, petrol and thinner. The results show that the instrument able to discriminate an air sample using PCA with total variation for 99.94%, while the classifier success rate for SVM indicates at 98.21% for train performance and 95.83% for test performance. This will contribute significantly to acquiring a new and alternative method of using the instrument for monitoring the atmospheric hazards in confined space to ensure the safety of workers during work progress in a confined space.
1 November 2021 in Journal of Physics: Conference Series
The presence of explosive or flammable gases in confined space may contribute towards accidents that threaten the workers safety and industrial progress. Conventionally, the existing instrument for gas detection in confined space is manually carried by humans whereby the workers or competence person itself were exposed directly to the gases. This project is aim to develop a prototype system to detect the presence of gases leak where the robotic system replaces humans to carry gas sensors. Users only need to maneuver the robot using a mobile phone to monitor the specific area that may have an explosive or flammable gas leak which includes Liquefied Petroleum Gas (LPG) and methane gases. The sensors will detect if a change in the gas concentration has exceeded a safety limit and will activate the alarm as an alert signal. The readings of gases as input signals were sent wirelessly to the Personal Computer (PC) as a user device for monitoring purposes. This prototype is successfully developed, tested and calibrated using the samples of LPG gas, methane, smoke and environment temperature. The result proved that the developed system is able to detect an air sample using selected gas sensors and display the data in graph form with live monitoring. This will contribute significantly to acquiring a new and alternative method using the system for detecting the presence of gases in confined space application.