Training a Remote-Control Car to Autonomously Lane-Follow using End-to-End Neural Networks
| Autor: | Bryce Simmons, Huong Pham, Yazeed Alhuthaifi, Pasham Adwani, Artur Wolek |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
050210 logistics & transportation
Finite-state machine Artificial neural network Computer science business.industry 05 social sciences 02 engineering and technology Stop sign Convolutional neural network law.invention End-to-end principle law 0502 economics and business 0202 electrical engineering electronic engineering information engineering Software design 020201 artificial intelligence & image processing Computer vision Artificial intelligence business Monocular vision Remote control |
| Zdroj: | CISS |
| DOI: | 10.1109/ciss.2019.8692851 |
| Popis: | This paper describes the implementation of an end-to-end learning approach that enables a small, low-cost, remote-control car to lane-follow in a simple indoor environment. A deep neural network (DNN) and a convolutional neural network (CNN) were trained to map raw images from a forward-looking camera to steering and speed commands (right, left, forward, reverse). The mechanical, electrical, and software design of the autonomous car is presented and the architectures of the DNN and CNN are discussed. The accuracy and loss of both types of neural networks is compared to two existing models VGG16 and DenseNet. A finite state machine is used to control the behavior of the car as it transitions between lane-following and stopped states during experimental demonstrations. The car enters the stopped state when either a stop sign is detected (using a Haar classifier and monocular vision) or an ultrasonic sensor indicates the presence of an obstacle. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|