Abstract— This paper presents an EMG (electromyogram)-based input interface using machine learning for people with physical disabilities of the extremities. We have developed a virtual hand that can be operated in virtual environment using EMG signals. In this paper, we performed a lifting object task and box and block test task with the virtual hand. From the experimental results of the lifting object tasks, it was confirmed that six wrist joint movements were classified, and that an experimental subject appropriately lifted objects with the virtual hand in the virtual space. In the box and block tests task, it was confirmed that he moved block(s) to the opposite side of the box 9 times within 60 sec.Keywords—EMG Signal; Machine Learning; Myoelectric Prosthesis
Abstract:Previous studies have demonstrated that emotional arousal is evoked by visual feedback of a selfie. This selfie was subjectively evaluated as having a good face and a good psychological state. However, the causality between emotional arousal due to feedback from a selfie and facial features recognized by the human eye was not revealed. The objective of the present study was factor clarification of the emotional arousal. The study evaluates the kind of facial information the human eye recognizes when the human distinguishes the type of selfie. For this, a model was developed using machine learning to automatically classify if a photographed selfie can favorably affect the emotional state. As a result, the type of selfie was distinguished at 83.3% correctness, and it was suggested that the whole face was recognized when the human eye evaluated a selfie as a selfie that can have a favorable effect on the emotional state. In other words, when evaluating the face, it was suggested that evaluating the whole, not the part, would be a cause of emotional arousal.
Abstract: Dynamic multi-object recognition based on machine vision is a very important research direction in the field of pattern recognition. In this paper, the multi-object identification of robotic fishes in water is studied and A HSV color space model is proposed. By re-modeling the original color space, the main light interference in the image can be effectively removed, and the shadow of the robotic fish can be removed, making the background segmentation more accurate. The improved algorithm has stronger robustness than the original matching tracking algorithm
Keywords: Robotic fish, target recognition, machine vision, HSV, deep learning
Abstract: UAV is defined as Unmanned Aerial Vehicle with some greater or lesser degree of ‘automatic intelligence’ part of an unmanned aircraft systems. Although all UAV systems have many elements other than the air vehicles, UAVs are usually categorized by the capability or size of the air vehicle that is required to carry out the mission. However, it is possible that one system may employ more than one type of air vehicle to cover different types of missions, and that may pose a problem in its designation. However, these definitions are constantly being changed as technology advances, allowing a smaller system to take on the roles of the one above. The boundaries, therefore, are often blurred so that the following definitions can only be approximate and subject to change. The main challenge in design and making any system for integration into the main research system, such as robot or UAV, requires careful attention on the interaction of each electric and electrical unit or component on the circuit board. This paper highlights the fabrication and the evaluation of the Inshore Fishing UAV gripper, the acrylic board, and the wireless communication module. The communication transmission distance between the UAV on shore and UAV over the sea is about 1 kilometer with stable flight.
Keywords: UAV; UAS; Gripper; Drone; Seashore; twe-litle.
Abstract: An in-process hole inspection subsystem was integrated with the drilling robotic system, which is based on the line laser scanner installed near the end-effector. The proposed inspection approach is based on the image processing of 3D (three dimension) point cloud obtained from laser scanner driven by the robotic manipulator. The normal of measuring surface was detected from the 3D point data on the hole edge, which determines the feedback signal to the hardware to adjust the direction of laser beam. By normal adjusting algorithm, the laser scanner is driven by the robotic manipulator to achieve the normal direction of the measuring hole. Then, based on 2D (two dimension) point data, the least square ellipse fitting method was applied to compute the hole parameters, such as diameter, circularity and positioning of the hole. The designed approach was tested for its accuracy and robust in an example of through hole automatic inspection
Keywords: line laser scanner, drilling robot, hole inspection, normal adjusting
Abstract: This paper design a new vehicle system that has a function of storing path data. The main control chip of the intelligent vehicles system is STM32F103ZET6. The current position and direction of the vehicle are determined by means of path memory and position recognition. This system is rarely affected by the ground condition, so there is no need for any ground signs.
Keywords: intellectual vehicles system, path memory, position recognition, STM32F103ZET6
Abstract: In order to reduce the torsional moment of the motor in Axis-2, the drive compensation devices can be used for the joint of industrial robots. The static balance compensation range of conventional balance cylinders is limited. Since of lacking in autonomy, continuity, and dynamics, balance cylinders cannot be used for compensation when load is various. The dynamic cylinder based on series elastic actuator (SEA) devices is designed to realize the automatic response of industrial robots when load is various, to obtain continuous dynamic compensation of the inertia moment and to achieve the optimum balance. Because SEA devices have features of dynamic adjustment and energy amplification, they can be used to realize balance compensation and reduce effectively the power requirement for the joint drive motor or even replace a motor of Axis-2. Thus, a new kind of flexible balance-drive device is constructed. In this paper, theoretical and experimental analyses of the dynamic model are conducted. The experimental results prove that the devices combine the effects of balancing cylinders and motors of Axis-2, as well as increasing load capacity and flexibility.
Keywords: Industrial robot; Balance mechanism; Series elastic actuator; Distributed actuator
Abstract: A new type of the anti-theft electronic lock with the lock bolt structure is designed, which can realize the function of locking and unlocking of the bicycle safely. The hardware system includes the STC-12C5A microcontroller, RFID card, data read/write module and mechanical lock structure. The system combined the non-contact RFID card reader and the lock structure. And the static mechanical property is analyzed to meet various situations. A number of actual test results showed that the electronic lock system is safe and reliable.
Abstract: This paper highlights the importance of combining intensity and feature based localization systems in autonomous driving. The intensity based localization system is represented by calculating cross correlation between LIDAR and map images. The feature based system is integrated by extracting the lateral edges from the LIDAR and map images with respect to the heading angle. An edge matching technique is then applied to estimate the lateral position based on the common extracted features. The experimental results have verified that the estimation of the lateral and longitudinal positions has been improved against the changes of weather and environmental conditions by combining the image and edge matching results.
Abstract: This paper initiates and describes the development of an inshore fishing UAV at the seashore, where the UAV can communicate with its controller by sending all the information during its flight in real time to the base station. The operation distance of the UAV from the seashore is to the fishing point will be between 500 m to 1km. The navigation method is under investigation, which is to guide the UAV from the seashore to fishing points along a predefined path planning by avoiding sudden obstacles it may face.
Abstract: This paper presents the concept of a highly-sophisticated network system using unmanned aerial vehicles, further named drones, and wireless networks for enhancing safety against natural disasters. The system consists of several drones and ground vehicles. Each vehicle has a wireless network unit, which employs the dual-mode Wireless Access in Vehicular Environment (WAVE) in the 700 MHz or 5 GHz band, with the goal of creating a multi-hop (more than three hops) ad hoc network. These features enable the system to facilitate rescue and relief operations in the event of a serious disaster. The proposed system represents an innovation in the field of mesh network systems, being based on a combination of ubiquitous drones and ground vehicles.
Abstract: Object classification is an important technique for autonomous vehicles to identify surrounding dynamic objects and execute safe path planning. In this paper, a multi-class object classification method is proposed to classify objects around the vehicle into car, pedestrian bicyclist, and background using a LIDAR sensor. The various effective features of each object are computed using 3D point clouds, and Real AdaBoost algorithm is applied for multi-class classification. In addition, class probabilities are calculated and updated in a time series framework for tracking objects. Classification is evaluated using a dataset that includes long-range objects over 50m. The overall accuracy of the clusters for each frame is 92.7% and for tracking objects is 95.5%. Moreover, processing time for object classification is 0.07ms. Thus, this method can be used in real time for autonomous driving on urban roads.
Abstract: The development and impact of technology on our everyday lives cannot be compared with the world our ancestors lived in several decades ago. This is described as the world of technology (WoT). But despite all the advancements in technologies, understanding of the mechanisms of nature and the damages caused via natural disasters, such as earthquakes, landslides, and flooding to mention only a few, are still very far away. In the effort of saving lives during natural disasters, such as earthquakes, this study introduces a rapid human body detection technology using image processing from UAV camera. The skin color from a female student is first extracted in RGB then converted to HSV. Next, opening and closing morphological operations are performed eight times each to remove all noise present in the image. Experimental tests were performed both indoor and outdoor, where the female student presented an object close and far to the camera to check the detection capability in both cases. The experiment results show that close or far, the camera can clearly detect both a human body and any part of a human body. The results of the experiment proves the merit of the proposed method.
Abstract: Automated driving is an emerging technology in which a car performs the tasks of recognition, decision making, and control. Recognizing surrounding vehicles is vital in generating the trajectory of an ego-vehicle. This paper focuses on detecting a turn signal information as one of the driver’s intention for surrounding vehicles. This information helps to predict the driver’s behavior in advance especially as instances of lane change and turns at an intersection. Using their intension, the automated vehicle is able to generate a safety trajectory before the driver’s behavior changes. The proposed method recognizes the turn signal of the target vehicle using a mono-camera. It detects the lighting state using Convolutional Neural Network, and then calculates a flashing frequency using Fast Fourier Transform.
Abstract: An assistive robotic arm for people with severe disabilities is presented in this paper. Its user interface using eye movements consists of a Web camera, computer, and microcontroller with display unit. Using the robotic arm system, we performed two experiments: (1) transferring water task and (2) eating soup task. It was found from the experimental results that the assistive robotic arm system could stably and appropriately transfer more than 82 % of water and 86 % of soup to the respective positions.