Citation Number
1
Views
31
Downloands
4
İnsan müdahalesi olmadan kendi kendine hareket edebilen araçlar sürücüsüz araç olarak adlandırılmaktadır. Sürücüsüz araçlar son yirmi yılda; askeri, lojistik ve endüstriyel üretimdeki potansiyel uygulamaları ile hem akademiden, hem de endüstriden büyük ilgi görmeye başlamıştır. Sürücüsüz araçların kullanılması günümüz trafiğinin çevresel etkilerini azaltmak ve trafik kazalarını önlemek gibi birçok konuda toplumsal fayda sağlamaktadır. Sürücüsüz araçlarda navigasyon için GPS, çarpışmaları önlemek için sensör ve nesneleri tespit etmek için kamera gibi çeşitli teknolojiler kullanılmaktadır. Bu teknolojilerin hepsi ya da birkaçı kullanılarak Derin Öğrenme tabanlı ve PID kontrol ile otonom sürüş yapılabilmektedir. Bu çalışmada Derin Öğrenme Tabanlı model eğitimi ve otonom sürüş testleri sürüş simülatöründe gerçekleştirilmiştir. Sürüş simülatöründen aracın direksiyon açısı, hız bilgisi ve ön camına monte edilen üç kameradan (sağ, sol ve orta) görüntü bilgisi alınmıştır. Aracın otonom hareketi Derin Öğrenme tabanlı model eğitimi gerçekleştirilerek ve PID kontrol ile sağlanmıştır. Bu çalışmada Derin Öğrenme ile eğitilen modelin sürüş performansı ile PID kontrol ile gerçekleştirilen sürüş performansı sürüş simülatöründe bir tam turda karşılaştırılmıştır. Aracın sürüş parkurundaki bir tam turda gerçek zamanlı olarak özerk hareketi kaydedilmiş ve başarım değerlendirmesi gerçekleştirilmiştir. Sürüş simülatöründe gerçekleştirilen testler sonucunda PID kontrol tabanlı sürüşte de başarılı sonuçlar elde edilmiş olmasına rağmen, Derin Öğrenme tabanlı modelin performansının daha iyi olduğu belirlenmiştir.
Vehicles that can move by themselves without human intervention are called driverless vehicles. In the last twenty years, unmanned vehicles have begun to see great interest from both the academy and the industry with their potential applications in military, logistics and industrial production. The use of driverless vehicles provides social benefits in many aspects, including reducing the environmental impacts of today’s traffic and preventing traffic accidents. A variety of technologies, such as GPS for navigation in unmanned vehicles, sensors and cameras, are used to detect objects to prevent collisions. All or a few of these technologies can be used for deep learning-based and autonomous driving with PID control. In this study, deep learning-based model training and autonomous driving tests were carried out in the driving simulator. From the driving simulator, the vehicle’s driving angle, speed information and image information were taken from the three cameras (right, left and middle) installed on the front window. The autonomous movement of the vehicle is provided by deep learning-based model training and PID control. In this study, the driving performance of the model trained with Deep Learning with PID control was compared in a full round in the driving simulator. In a full round of the vehicle's driving track, the self-movement was recorded in real time and the success assessment was carried out. Though the tests on the driving simulator have achieved successful results in PID-based driving, the Deep Learning-based model has been shown to have better performance.
Vehicles that can move on their own without human intervention are called autonomous vehicles. Over the last two decades, autonomous vehicles have been receiving considerable interest from both academia and industry, with potential applications in military, logistics and industrial production. The development of autonomous vehicles provides social benefits in many aspects, such as reducing the number of deaths and reducing the environmental impact of today's traffic. Autonomous vehicles use various technologies such as GPS for navigation, sensors to avoid collisions, and cameras for object detection. Autonomous driving can be performed with Deep Learning and PID control. In this study, Deep Learning Based model training and autonomous driving tests were carried out in the driving simulator. Steering angle, speed information from the driving simulator and image information from three cameras (right, left and middle) mounted on the windshield were obtained. Autonomous movement of the vehicle was provided by performing Deep Learning based model training and PID control. In this study, the driving performance of the model trained with Deep Learning and the driving performance performed by PID control were compared in one full tour in the driving simulator. Autonomous movement of the vehicle was recorded in real time during one full lap on the driving track and performance evaluation was carried out. As a result of the tests carried out in the driving simulator, although successful results were obtained in PID control-based driving, it was determined that the performance of the Deep Learning based model was better.
Field : Mimarlık, Planlama ve Tasarım; Mühendislik
Journal Type : Uluslararası
Article Detail 
Citation Owners
Similar Articles
Download PDF
Journal Information
Listen Paper
Print This Page
Share
Mendeley
