Muslikhin Muslikhin

Automated guided vehicles (AGVs) have become prevalent over the last decade. However, numerous challenges remain, including path planning, security, and the capacity to operate safely in unstructured environments. This study proposes an obstacle avoidance system that leverages deep action learning (DAL) to address these challenges and meet the requirements of Industry 4.0 for AGVs, such as speed, accuracy, and robustness. In the proposed approach, the DAL is integrated into an AGV platform to enhance its visual navigation, object recognition, localization, and decision-making capabilities. Then DAL itself was introduced to combine the work of You Only Look Once (YOLOv4), speeded-up robust features (SURF), and k-nearest neighbor (kNN) and AGV control in indoor visual navigation. The DAL system triggers SURF to differentiate two navigation images, and kNN is used to verify visual distance in real time to avoid obstacles on the floor while searching for the home position. The testing findings show that the suggested system is reliable and fits the needs of advanced AGV operations.

Sliding mode controller (SMC) has become a popular traditional control method in industries due to the most effective control strategies employing nonlinear control and the ability to reject disturbances, particularly for line trajectory control. However, this control method has chattering problems due to high-frequency switching. To cope with the shortcoming, an artificial intelligence (AI) method is utilized in the traditional SMC to eliminate or reduce this chattering problem. This paper investigates an adaptive fuzzy logic system combined with SMC algorithm to alleviate the problem. Fuzzy logic is chosen due to its advantages in tackling nonlinear properties using if-then thinking, whereas SMC method can be applied due to its ability to reject disturbance control. The inverted pendulum is selected as a controlled object and simulated using MATLAB/Simulink to investigate this control method. By combining the fuzzy logic system and the SMC approach, the chattering problems can be adaptively reduced on the line trajectory tracking signal. The adaptive fuzzy SMC achieved better performance with fast response compared with previous literature algorithms for similar plants.

Detecting troop camouflage on the battlefield is crucial to beat or decide in critical situations to survive. This paper proposed a hybrid model based on deep action learning for camouflage recognition and detection. To involve deep action learning in this proposed system, deep learning based on you only look once (YOLOv3) with SquezeeNet and the fourth steps on action learning were engaged. Following the successful formulation of the learning cycle, an instrument examines the environment and performance in action learning with qualitative weightings; specific target detection experiments with view angle, target localization, and the firing point procedure were performed. For each deep action learning cycle, the complete process is divided into planning, acting, observing, and reflecting. If the results do not meet the minimal passing grade after the first cycle, the cycle will be repeated until the system succeeds in the firing point. Furthermore, this study found that deep action learning could enhance intelligence over earlier camouflage detection methods, while maintaining acceptable error rates. As a result, deep action learning could be used in armament systems if the environment is properly identified.

Robotic grasping for cluttered tasks and heterogeneous targets is not satisfied by the deep learning that has been developed in the last decade. The main problem lies in intelligence, which is stagnant, even though it has a high accuracy rate in usual environment; however, the cluttered grasping environment is very irregular. In this paper, an action learning for robotic grasping using eye-in-hand coordination is developed to grasp the cluttered and wide range of various objects using 6 degree-of-freedom (DOF) robotic manipulator equipped with a three-finger gripper. To involve action learning in this system, k-Nearest Neighbor (kNN), Disparity Map (DM), and You Only Look Once (YOLO) were needed. After successfully formulating the learning cycle, an instrument assesses the robot’s environment and performance with qualitative weightings. Some experiments of measuring the depth of the target, localization of target variations, target detection, and the gripping process itself were conducted. The entire process is spread out in plan, act, observe, and reflect for each action learning cycle. If the first cycle does not suffice the results according to the minimum pass standard, the cycle will renew until the robot succeeds in picking and placing. Furthermore, this study demonstrated that the action learning-based object manipulation system with stereo-like vision and eye-in-hand calibration can improve intelligence over previous errors with acceptable errors. Thus, action learning might be applicable to other object manipulation systems without having to define the environment first.

To achieve Industry 4.0 solutions for the networking of mechatronic components in production plants, the use of Internet of Things (IoT) technology is the optimal way for goods transportation in the cyber-physical system (CPS). As a result, automated guided vehicles (AGVs) are networked to all other participants in the production system to accept and execute transport jobs. Accurately tracking the planned paths of AGVs is therefore essential. The omnidirectional mobile vehicle has shown its excellent characteristics in crowded environments and narrow aisle spaces. However, the slip problem of the omnidirectional mobile vehicle is more serious than that of the general wheeled mobile vehicle. This paper proposes a slip estimation and compensation control method for an omnidirectional Mecanum-wheeled automated guided vehicle (OMWAGV) and implements a control system. Based on the slip estimation and compensation control of the general wheeled mobile platform, a Microchip dsPIC30F6010A microcontroller-based system uses an MPU-9250 multi-axis accelerometer sensor to derive the longitudinal speed, transverse speed, and steering angle of the omnidirectional wheel platform. These data are then compared with those from the motor encoders. A linear regression with a recursive least squares (RLS) method is utilized to estimate real-time slip ratio variations of four driving wheels and conduct the corresponding compensation and control. As a result, the driving speeds of the four omnidirectional wheels are dynamically adjusted so that the OMWAGV can accurately follow the predetermined motion trajectory. The experimental results of diagonally moving and cross-walking motions without and with slip estimation and compensation control showed that, without calculating the errors occurred during travel, the distances between the original starting position to the stopping position are dramatically reduced from 1.52 m to 0.03 m and from 1.56 m to 0.03 m, respectively. The higher tracking accuracy of the proposed method verifies its effectiveness and validness.

The penetration of Industry 4.0 in the convenience store is increasingly visible. The combination of Artificial Intelligence (AI), the Internet of Things (IoT), and robotic were always under evaluation, including applied AI in the whole system that is demanded robust when integrated with online shop. Meanwhile, the problem of speed detection and precision is still a challenge in AI. In this study data-driven deep learning was developed to improve the speed and maximize localization of consumer products. After the selected data-driven received from the online shop platform then triggers deep learning and activates a modified YOLOv2 in parallel. Thus, each detector per product is needed. Our system performance is proven by experiments to meet expectations in evaluating speed, precision, and performance in recognition and localization.

According to the data from Alzheimer’s Disease International (ADI) in 2018, it is estimated that 10 million new dementia patients will be added worldwide, and the global dementia population is estimated to be 50 million. Due to a decline in the birth rate and the development and great progress of medical technology, the proportion of elderly people has risen annually in Taiwan. In fact, Taiwan has become one of the fastest-growing aged countries in the world. Consequently, problems related to aging societies will emerge. Dementia is one of most prevailing aging-related diseases, with a great influence on daily life and a great economic burden. Dementia is not a single disease, but a combination of symptoms. There is currently no medicine that can cure dementia. Finding preventive measures for dementia has become a public concern. Older people should actively increase brain-protective factors and reduce risk factors in their lives to reduce the risk of dementia and even prevent the occurrence of dementia. Studies have shown that engaging in mental or creative activities that stimulate brain function has a relative risk reduction of nearly 50%. Elderly people should develop the habit of life-long learning to strengthen effective neural bonds between brain cells and preserve brain cognitive functions. Playing chess is one of the suggested activities. This paper aimed to develop a Chinese robotic chess system for the elderly. It mainly uses a camera to capture the contour of the Chinese chessman, recognizes the character and location of the chessman, and then transmits this information to the robotic arm, which will grab and place the chessman in the appropriate position on the chessboard. The camera image is transmitted to MATLAB for image recognition. The character of the chessman is recognized by convolutional neural networks (CNNs). Forward and inverse kinematics are used to manipulate the robotic arm. Even if the chessmen are arbitrarily placed, the experiment showed that their coordinates can be found through the camera as long as they are located within the working scope of the camera and the robotic arm. For black chessmen, no matter how many degrees they are rotated, they can be recognized correctly, while the red ones can be recognized 100% of the time within 90° of rotation and 98.7% with more than a 90° rotation.

This paper develops a hybrid algorithm of adaptive network-based fuzzy inference system (ANFIS) and regions with convolutional neural network (R-CNN) for stereo vision-based object recognition and manipulation. The stereo camera at an eye-to-hand configuration firstly captures the image of the target object. Then, the shape, features, and centroid of the object are estimated. Similar pixels are segmented by the image segmentation method, and similar regions are merged through selective search. The eye-to-hand calibration is based on ANFIS to reduce computing burden. A six-degree-of-freedom (6-DOF) robot arm with a gripper will conduct experiments to demonstrate the effectiveness of the proposed system.

Estimating the position of a homogeneous object from an image for XY position is quite simple because it has the same dimensions XY. However, determining the XYZ position requires a unique approach. Generally, for estimating 3D position, stereo camera or expensive cameras are used with complicated computer vision algorithms. In this paper, we classify the position of an object using a mono camera. The image is divided into 3185 classes and five layers as a machine learning algorithm references. The k-nearest neighbors (kNN) approach usually is to find the closest point of the centroids to the closest class. Thus, this approach can be used as a three-axis prediction method that can afford the best performance solution.

This study aims to utilize the FIS matlab converter (fuzzy inference system) into the C arduino programming language with the aim of simplifying the fuzzy logic model that can be applied immediately with control hardware such as Arduino. In this study, an example of fuzzy logic is used with two sensor inputs, namely temperature and smoke sensors as inputs and two outputs in the form of buzzers and pump motors. The method used is sugeno in matlab. Then the formation of input variables modeled mapping scale is formed 0 - 100 and scale output 0 - 2. Converter. Fis fuzzy inference system can be applied to the design of fuzzy logic systems with the results of the .ino format conversion program template that can be set output results as arduino triger directly . This setting is enough to do with the reading of the g_fisOutput [] variable with IF-ELSE.