D4 Teknologi Rekayasa Robotika

Permanent URI for this collectionhttps://repository.polibatam.ac.id/handle/PL029/1765

Browse

Now showing 1 - 4 of 4

Application of Object Detection and Face Recognition with Customize Dataset on Service Robot
(2024-09-18) Saputra, Wiki; Wijaya, Ryan Satria
Computer vision technology is currently gaining traction in all industries, including manufacturing, agriculture, healthcare, and services. Computer vision technology now incorporates robotics technology, making it very dynamic and flexible. Computer vision, like a service robot, is used in a variety of applications, including safety, analysis, and service. One of the skills of service robots is the ability to recognize its users through the use of computer vision. So that by recognizing the user, the robot can be commanded according to the user's wishes. Computer vision on service robots is trained using a special dataset that includes the object of a user's face. The computer will be trained by recognizing its users through digital images and annotating their faces, followed by training using the yolov5 architecture and applying the resulting data to the robot.
Implementasi Pemetaan Robot Roda Mecanum Otonom Berbasis LIDAR dengan SLAM
(2024-09-18) sahidan,diki; prayoga,senandung
Jurnal ini mengulas tentang autonomous mobile robot roda mekanum menggunakan lokalisasi dan pemetaan menggunakan lidar Robot beroda mekanik adalah robot yang dapat bergerak dari titik A ke titik B secara mandiri. Tujuan dari penelitian ini adalah untuk mengevaluasi ketepatan dan akurasi pemetaan. dan ketepatan dalam pemetaan untuk memastikan robot dapat beroperasi dengan efisien serta membangun kemampuan untuk melakukan pemetaan lingkungan sekitar secara real-time menggunakan data yang diperoleh dari sensor Lidar A2M12 dan mengimplementasikan algoritma SLAM (Simultaneous Localization and Mapping) untuk menentukan posisi dan orientasi robot secara simultan saat melakukan pemetaan. Untuk bergerak secara mandiri, robot harus menyadari lingkungannya dan posisinya dalam lingkungan tersebut. Metode yang digunakan adalah lokalisasi dan pemetaan simultan dengan menggunakan sensor RPLidar A2M12 dan ROS (Robot Operating System). berdasarkan hasil pengujian gmapping SLAM sebesar 3,34%, error pengukuran jarak dan sudut sensor sebesar 1,16%, Secara keseluruhan, robot otonom ini dapat digunakan bahkan di area terbuka dan rintangan sederhana.
Implementation of path planning with obstacle avoidence using SLAM in Services Robot
(2024-09-18) Tarigan Wahyudi,Dikki; Wijaya Satria,Ryan
Obstacle avoidance is an important aspect in service robot navigation. This research proposes an approach that integrates Lidar sensors with Simultaneous Localization and Mapping (SLAM) methods to improve the robot's ability to identify, understand, and avoid obstacles in dynamic environments. This data is then processed using SLAM algorithms to create a real-time map of the environment while estimating the robot's position within it. In this research, lidar is used to detect obstacles to be encountered by the robot. Dynamic environment mapping allows the robot to detect changes and adjust its path plan on the fly. An obstacle avoidance algorithm is designed to interact with SLAM data, so that the robot can adaptively change its movement path to avoid newly appearing or moving obstacles In robotic path planning, Dijkstra's algorithm can be applied to generate the shortest, most efficient route from the robot's current location to a target location. The algorithm operates on a predefined map or a dynamically updated map (as in SLAM), considering obstacles and the cost associated with traversing different parts of the environment. Dijkstra algorithm is chosen to determine the path to be traveled by the robot.Djikstra algorithm is chosen to determine the path to be traveled by the robot. The djikstra algorithm takes the robot through the obstacle barrier well from the starting position to the destination point with excellent.Combining SLAM with Lidar obstacle avoidance improves the robot's robustness in complex and rapidly changing environmental situations. Simulation experiments and field testing show that this approach is effective in improving the robot's performance in dealing with obstacles and optimizing its autonomous navigation. By utilizing Lidar and SLAM technologies, this research contributes to the development of reliable robot navigation systems in various application contexts.
Path Planning Application using Dijkstra Algorithm on Service Robot
(2024-09-18) Mahendra, Arya; Wijaya, Ryan Satria
The advancement of robot technology in mobile robots is quickly evolving and being utilized in various sectors such as industries, military, medicine, and public services. Challenges consist of perception, localization, motion control, and path planning. The aim of Dijkstra's algorithm, which is a greedy algorithm, is to optimize path planning to improve movement efficiency. Dijkstra's algorithm is a useful method in graph theory to find the shortest path between two nodes in a weighted graph, utilizing an iterative approach to compute the distance. The algorithm being suggested speeds up the initial process by simultaneously determining the shortest route from the starting point to all other points, utilizing various paths or continuing on the same path to reach additional nodes. Nonetheless, it begins at the central node, utilizing data that is not influenced by the route taken. The author experimented with Dijkstra's algorithm using a Service Robot, successfully navigating past three obstacles without any collisions. The robot demonstrated success in finding the shortest and fastest path by maintaining an average speed of 0.23 m/s and average errors of 0.021 metres on the x-axis and 0.017 metres on the y-axis.