3 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 3 / 3
Yayın Microsoft Kinect Sensörü kullanarak zemin düzlemi algılama(IEEE, 2013-06-13) Kırcalı, Doğan; Tek, Faik Boray; İyidir, İbrahim KamilGörüntü işleme tabanlı mobil robotların başarılı navigasyonu için zemin düzlemi algılama esastır. Bu bildiride Kinect derinlik sensöründen elde edilen derinlik bilgisine dayalı yeni ve gürbüz bir zemin düzlemi algılama algoritması önerilmektedir. Literatürdeki benzer yöntemlerin aksine, zemin düzleminin sahnedeki en büyük alan olduğunu varsayılmamaktadır. Yöntemimiz sensörün yeri görüş açısının sabit olduğu veya değişken olabileceği iki farklı durum için iki değişik algoritma halinde sunulmaktadır. Yaptığımız deneylerde her iki durum için önerdiğimiz algoritmaların oldukça başarılı olduğu gösterilmektedir.Yayın Adaptive visual obstacle detection for mobile robots using monocular camera and ultrasonic sensor(Springer-Verlag, 2012-10-07) İyidir, İbrahim Kamil; Tek, Faik Boray; Kırcalı, DoğanThis paper presents a novel vision based obstacle detection algorithm that is adapted from a powerful background subtraction algorithm: ViBe (VIsual Background Extractor). We describe an adaptive obstacle detection method using monocular color vision and an ultrasonic distance sensor. Our approach assumes an obstacle free region in front of the robot in the initial frame. However, the method dynamically adapts to its environment in the succeeding frames. The adaptation is performed using a model update rule based on using ultrasonic distance sensor reading. Our detailed experiments validate the proposed concept and ultrasonic sensor based model update.Yayın A new local path planning approach by synthesis of PRM and RRT* algorithms for an autonomous mobile robot(Springer, 2025-02) Göktaş, Anıl Gökhan; Sezer, SemihMany research efforts have been and continue to be carried out to make human life easier through the use of new technologies. The ability to shift labor to non-humans and reduce the workforce demonstrates the scope of innovation. In this investigation, a new approach is proposed to address several shortcomings of the PRM and RRT algorithms used for path planning in mobile robots. The proposed approach differs by building markers around it, avoiding dynamic obstacles and providing a shorter path. Simulation studies of the PRM and RRT* algorithms, along with the Circular Nodes (CN) approach, were conducted in real and virtual environments. Meanwhile, experimental studies for the CN approach were carried out in a real environment, with obstacles. When compared to other methods, the proposed approach has demonstrated an increase in node efficiency by up to five times. Moreover, implementing node points that are approximately 10% of those used in the PRM and RRT* algorithms has resulted in a shorter path. The reduction in the number of nodes and path length leads to a reduction in energy consumption and processing power.
