FPGA, Embedded System, PCB Layout, Robotics and More

Văn hóa và Hoạt động

Energy-Efficient Unmanned Aerial Vehicle (UAV) Surveillance Utilizing Artificial Intelligence (AI)

Recently, unmanned aerial vehicles (UAVs) enhance connectivity and accessibility for civilian and military applications. A group of UAVs with onboard cameras usually monitors or collects information about designated areas. The UAVs can build a distributed network to share/exchange and process collected sensing data before sending it to a data processing center. A huge data transmission among them may cause latency and high-energy consumption. This paper deploys artificial intelligent (AI) techniques to process the video data streaming among the UAVs. Thus, each distributed UAV only needs to send the certain required information to each other. Each UAV processes data utilizing AI and only sends the data that matters to the others. The UAVs, formed as a connected network, communicate within a short communication range and share their own data with each other. The convolution neural network (CNN) technique extracts feature from images automatically that the UAVs only send the moving objects instead of the whole frames. This significantly reduces redundant information for either each UAV or the whole network and saves a huge energy consumption for the network. The UAVs can also save energy for their motion in the sensing field. In addition, a flocking control algorithm is deployed to lead the group of UAVs in the working fields and to avoid obstacles if needed. Simulation and experimental results are provided to verify the proposed algorithms in either AIbased data processing or controlling the UAVs. The results show promising points to save energy for the networks.

Chi tiết

Design Of A Robotic System To Assist In The Treatment Of Severe COVID-19 Patients

Abstract— This paper presents the design and construction of an intelligent mobile robot system to assist in patient treatment for severe covid-19 patients. The robot will talk to the patient and report the situation outside, and transport food, drinks, and consumables into the isolation room. The robot can move to the destination in two modes: autonomous and online control. The hardware is built on a mobile robot system that is connected to the Internet via 4G mobile network. The system uses a client-server software architecture, in which the data exchanged between the client and the server is transmitted over different transport protocols. Autonomous operating mechanisms such as obstacle avoidance positioning, safe destination navigation, and feedback display for remote robot control are simulated experimentally in an active treatment room.

Chi tiết

Preparation of Papers in Two Column Format for the ICSES Transactions and Conferences

Today, airports are quickly deploying self-service technologies as a generalship to improve passenger experience by reducing service times at all stages of check-in. Whereby, one of the important problems in airport area is the ability of allowance of a large number of passengers over the airport counters. There are many solutions have been proposed, including the application of self check-in kiosks that allow passengers to check-in by themselves without having to go to the counter. In this paper, we present a kiosk design that includes hardware devices and graphical user interface (GUI) of self-service check-in software based on the analysis of the features and the functions of similar solutions available on the market and a self check-in software design methodology using web crawling for collecting data from airline’s website that can be applied to many airlines without too much cost or technical challenge in order to decrease the load check-in counters. Our research aim is to propose a low cost solution that offers new features without providing other solutions, with a focus on improving the efficiency of the check-in process of passengers at the airport. Keywords— Self check-in, kiosk, airport service, booking, graphic user interface, web crawling.

Chi tiết

Robot Navigation Using FPGA Based Moving Object Tracking System

The paper describes an object tracking robot system implemented on FPGA. The system collects real-time object images from the OV7670 camera, the images are passed through the median filter step to enhance image quality. Based on the color (red) the object is separated from the background, proceed to filter the object by mathematical morphological method to remove noise around the object. The (new) coordinates of the object are determined, thereby giving control signals to the robot. Embedded system on FPGA includes MicroBlaze soft processor, hardware IP cores: median filter, color separation, morphological filter. These cores are capable of High-speed pipeline computation and data communication through the DMA Controller enables high data rates whether faster. The entire system was executed in realtime on Xilinx's Spartan-6 FPGA KIT. Keywords—Robot Chasing Objects, FPGAs, Embedded System, Median Filter, Homomorphic Filter, MicroBlaze.

Chi tiết

Trajectory Tracking Control of the Nonholonomic Mobile Robot using Torque Method and Neural Network

This paper deals with the problem of tracking control of the mobile robot with non-holonomic constraints. A controller with two control loops is designed. The inner loop generates control laws for the tangent and angular velocities to control the robot to follow the target trajectory. It is derived based on the robot kinematics and the Lyapunov theory. The outer loop employs the torque method to control the robot dynamics. A neural network is implemented to compensate for the uncertainties caused by the dynamics model. The asymptotic stabilization of the whole system is proven by the direct Lyapunov stabilization theory. Simulations in MATLAB confirmed the validity of the proposed method. Keywords - Trajectory tracking, mobile robot, torque control, neural networks, Lyapunov theory.

Chi tiết


Giải pháp tích hợp máy xét nghiệm y tế vào hệ thống phần mềm quản lý bệnh viện là giải pháp kết nối, truyền tải dữ liệu nhờ thiết bị kết nối phần cứng và phần mềm kết nối giữa thiết kế tương thích. giữa quá trình đọc dữ liệu từ máy xét nghiệm và chuyển vào cơ sở dữ liệu trên máy chủ của hệ thống phần mềm quản lý bệnh viện.

Chi tiết

A Novel Platform for Internet-based Mobile Robot Systems

In this paper, we introduce a software and hardware structure for online mobile robotic systems. The hardware mainly consists of a Multi-Sensor Smart Robot connected to the Internet through the 3G mobile network. The system employs a client-server software architecture in which the exchanged data between the client and the server is transmitted through different transport protocols. Autonomous mechanisms such as obstacle avoidance and safe-point achievement are implemented to ensure robot safety. This architecture is put into operation on the real Internet and the preliminary result is promising. By adopting this structure, it will be very easy to construct an experimental platform for the research on diverse teleoperation topics such as remote control algorithms, interface designs, network protocols, applications, etc.

Chi tiết

Định vị bằng Camera nhận diện các điểm đánh dấu Marker

Ước tính vị trí có tầm quan trọng lớn trong nhiều ứng dụng thị giác máy tính: định vị Robot, thực tế ảo và nhiều ứng dụng khác. Quá trình này dựa trên việc tìm kiếm sự tương ứng giữa các điểm trong môi trường thực và phép chiếu hình ảnh 2D của chúng. Đây thường là một bước khó, và do đó, người ta thường sử dụng các điểm đánh dấu tổng hợp hoặc fiducial để làm cho nó dễ dàng hơn.

Chi tiết

Nền tảng mới lạ cho hệ thống rô bốt di động dựa trên Internet

Trong bài báo này, chúng tôi giới thiệu cấu trúc phần mềm và phần cứng cho các hệ thống rô bốt di động trực tuyến. Phần cứng chủ yếu bao gồm một Robot thông minh đa cảm biến được kết nối với Internet thông qua mạng di động 3G. Hệ thống sử dụng kiến trúc phần mềm máy khách-máy chủ, trong đó dữ liệu được trao đổi giữa máy khách và máy chủ được truyền qua các giao thức truyền tải khác nhau. Các cơ chế tự chủ như tránh chướng ngại vật và đạt được điểm an toàn được thực hiện để đảm bảo an toàn cho robot. Kiến trúc này được đưa vào hoạt động trên Internet thực và kết quả sơ bộ đầy hứa hẹn. Bằng cách áp dụng cấu trúc này, sẽ rất dễ dàng để xây dựng một nền tảng thử nghiệm cho nghiên cứu về các chủ đề viễn thông đa dạng như thuật toán điều khiển từ xa, thiết kế giao diện, giao thức mạng và ứng dụng, v.v.

Chi tiết

A calibrated distance prediction method from image sensor to human face

In a system based on human-computer interaction, predicting the distance by computer vision between the camera and human face is an important operation. To calculate the distance between the camera and the face, an estimation method based on the geometric similarity of two triangles is proposed in this paper, the face recognition image processing technique will also be used description. Accordingly, taking the midpoint of the face vertex in the image, an algorithm with calibration is introduced to determine the distance from the camera to the face. The architecture for the face detection process based on Stacked Convolutional Neural Network (MTCNN) to detect face position in the image will be presented. Python's implementation uses the Intel OpenCV image processing library to reduce system overhead. Experiments and experimental applications show that the distance prediction algorithm based on face recognition and the proposed estimation method show high accuracy and fast calculation speed. Keywords: Fuzzy logic; Convolutional Neural Networks; computer vision and prediction distance adjustment

Chi tiết