Autonomous Vehicle Control System Using Convolutional Neural Network (original) (raw)

Understanding of Convolutional Neural Network (CNN): A Review

International Journal of Robotics and Control Systems, 2022

The application of deep learning technology has increased rapidly in recent years. Technologies in deep learning increasingly emulate natural human abilities, such as knowledge learning, problem-solving, and decision-making. In general, deep learning can carry out self-training without repetitive programming by humans. Convolutional neural networks (CNNs) are deep learning algorithms commonly used in wide applications. CNN is often used for image classification, segmentation, object detection, video processing, natural language processing, and speech recognition. CNN has four layers: convolution layer, pooling layer, fully connected layer, and non-linear layer. The convolutional layer uses kernel filters to calculate the convolution of the input image by extracting the fundamental features. The pooling layer combines two successive convolutional layers. The third layer is the fully connected layer, commonly called the convolutional output layer. The activation function defines the output of a neural network, such as 'yes' or 'no'. The most common and popular CNN activation functions are Sigmoid, Tanh, ReLU, Leaky ReLU, Noisy ReLU, and Parametric Linear Units. The organization and function of the visual cortex greatly influence CNN architecture because it is designed to resemble the neuronal connections in the human brain. Some of the popular CNN architectures are LeNet, AlexNet and VGGNet.

Use of CNN(YOLO) in Self Driving vehicles

The field of autonomous automation is of interest to researchers, and much has been accomplished in this area, of which this paper presents a detailed chronology. This paper can help one understand the trends in autonomous vehicle technology for the past, present, and future. We see a drastic change in autonomous vehicle technology since 1920s, when the first radio controlled vehicles were designed. In the subsequent decades, we see fairly autonomous electric cars powered by embedded circuits in the roads. By 1960s, autonomous cars having similar electronic guide systems came into picture. 1980s saw vision guided autonomous vehicles, which was a major milestone in technology and till date we use similar or modified forms of vision and radio guided technologies. Various semi-autonomous features introduced in modern cars such as lane keeping, automatic braking and adaptive cruise control are based on such systems. Extensive network guided systems in conjunction with vision guided features is the future of autonomous vehicles. It is predicted that most companies will launch fully autonomous vehicles by the advent of next decade. The future of autonomous vehicles is an ambitious era of safe and comfortable transportation. Background An autonomous car is a vehicle capable of sensing its environment and operating without human involvement. A human passenger is not required to take control of the vehicle at any time, nor is a human passenger required to be present in the vehicle at all. An autonomous car can go anywhere a traditional car goes and do everything that an experienced human driver does.The Society of Automotive Engineers (SAE) currently defines 6 levels of driving automation ranging from Level 0 (fully manual) to Level 5 (fully autonomous). These levels have been adopted by the U.S. Department of Transportation.

An Experimental Analysis on Self Driving Car Using CNN

IRJET, 2022

For the past decade, there has been a surge of interest in self-driving cars. This can be because of breakthroughs within the field of deep learning wherever deep neural networks square measure trained to perform tasks that generally need human intervention. CNN’s apply models to spot patterns and options in pictures, creating them helpful within the field of pc Vision. Samples of these square measure object detection, image classification, image captioning, etc. during this project, we've trained a CNN victimization pictures captured by a simulated automotive to drive the automotive autonomously. The CNN learns distinctive options from the pictures and generates steering predictions permitting the automotive to drive while not somebody's. For testing functions and getting ready the dataset the Unity based mostly machine provided by Udacity was used

Use of Machine Learning in Automobile Industry to Improve Safety Using CNN

IJRASET, 2021

Vision-based vehicle steering system cars can have three main roles: 1) road access; 2) an obstacle to find; and 3) signal recognition. The first two have already been taught many years and there have been many positive results, but a sign of traffic recognition is a less readable field. Road signs provide drivers with the most important information on the road, to do driving is safe and easy. We think road signs should play the same role of private cars. The color and shape are very different from the natural environment. The algorithm described in this paper uses this feature. It has two main parts. The first, to find, uses color range to separate image analysis and shapes to get symptoms. The second, in stages, uses the neural network. Some effects from natural forums are shown. On the other hand, the algorithm works to detect other types of marks can tell a moving robot to perform a specific task that place.

Development of a Vehicle for Driving with Convolutional Neural Network

International Journal of Advanced Computer Science and Applications

The aim of this paper is the design, simulation, construction and programming of the autonomous vehicle, capable of obstacle avoidance, object tracking also image and video processing. The vehicle will use a built-in camera for evaluating and navigating the terrain, a six-axis accelerometer and gyro for calculating angular velocities and accelerations, Arduino for interfacing with motors as well as with Raspberry Pi which is the main on-board computer. The design of the vehicle is performed in Autodesk Fusion 360. Most of the mechanical parts have been 3D printed. In order to control the chassis of the vehicle through the microcontrollers, the development of the PCB was required. On top of this, a camera has been added to the vehicle, in order to achieve obstacle avoidance and perform object tracking. The video processing required to achieve these goals is done by using OpenCV and Convolutional Neural Network. Among other objectives of this paper is the detection of traffic signs. The application of the Convolutional Neural Network algorithm after some of the examinations made has shown greater precision in recognizing STOP traffic sign of different positions and occlusion ratios, and finding the path for the fastest time.

A Model Based on Convolutional Neural Network (CNN) for Vehicle Classification

IEEE, 2021

The Convolutional Neural Network (CNN) is a form of artificial neural network that has become very popular in computer vision. We proposed a convolutional neural network for classifying common types of vehicles in our country in this paper. Vehicle classification is essential in many applications, including surveillance protection systems and traffic control systems. We raised these concerns and set a goal to find a way to eliminate traffic-related road accidents. The most challenging aspect of computer vision is achieving effective outcomes in order to execute a device due to variations of data shapes and colors. We used three learning methods to identify the vehicle: MobileNetV2, DenseNet, and VGG 19, and demonstrated the methods detection accuracy. Convolutional neural networks are capable of performing all three approaches with grace. The system performs impressively on a real-time standard dataset-the Nepal dataset, which contains 4800 photographs of vehicles. DenseNet has a training accuracy of 94.32 % and a validation accuracy of 95.37%. Furthermore, the VGG 19 has a training accuracy of 91.94 % and a validation accuracy of 92.68 %. The MobileNetV2 architecture has the best accuracy, with a training accuracy of 97.01% and validation accuracy of 98.10%.

A Convolutional Neural Network Approach Towards Self-Driving Cars

2019 IEEE 16th India Council International Conference (INDICON), 2019

A convolutional neural network (CNN) approach is used to implement a level 2 autonomous vehicle by mapping pixels from the camera input to the steering commands. The network automatically learns the maximum variable features from the camera input, hence requires minimal human intervention. Given realistic frames as input, the driving policy trained on the dataset by NVIDIA and Udacity can adapt to real-world driving in a controlled environment. The CNN is tested on the CARLA open-source driving simulator. Details of a beta-testing platform are also presented, which consists of an ultrasonic sensor for obstacle detection and an RGBD camera for real-time position monitoring at 10Hz. RRT*-Connect algorithm is used for path planning. Arduino Mega and Raspberry Pi are used for motor control and processing respectively to output the steering angle, which is converted to angular velocity for steering.

IJERT-A Study on Neural Networks From Pixels to Actions: Learning to Drive A Car

International Journal of Engineering Research and Technology (IJERT), 2019

https://www.ijert.org/A-Study-on-Neural-Networks-From-Pixels-to-Actions:-Learning-to-Drive-A-Car https://www.ijert.org/research/A-Study-on-Neural-Networks-From-Pixels-to-Actions-Learning-to-Drive-A-Car-IJERTCONV7IS08075.pdf Self-driving cars offer many advantages. They have the ability to outperform human drivers in some circumstances and can be safer, as computers don't get tired nor lose focus. They offer great economic advantages as they remove the need for drivers. An end-to-end neural network to predict a car's steering actions on a highway is being analyzed. The inputs of the network are images from a single car-mounted camera. Neural networks have gained a lot of popularity from their successes in large-scale image classification benchmarks. They have since been applied in many different areas, often resulting in substantial improvements. The performance of a self-driving car system is crucial because errors can result in the death of a human being. The first aspect is the format of the input data. The second aspect is related to the temporal dependencies between consecutive inputs. A stacked frames approach which increases the performance of this network is being used. Training and testing of data is done on real-life datasets and qualitatively shown the importance of recovery cases as well as demonstrate that the standard metrics that are used to evaluate networks that are trained on datasets-accuracy, MCA, MAE, MSE do not necessarily accurately reflect a system's driving behaviour.

Image Recognition by Using a Convolutional Neural Network to Identify Objects for Driverless Car

International Journal for Research in Applied Science & Engineering Technology (IJRASET), 2022

The concept of the paper was inspired by the recent surge in the automated car industry. The designed car was capable of detecting the road signals and taking the right and left turns accordingly. Object detection is a key ability required by most computer used in automated vehicles. The latest research in this area has been making great progress in many directions. Object detection and tracking has a variety of uses, our paper explain how to use convolutional neural network for object detection in autonomous vehicles. Automatic car always has the potential to solve traffic problems with the help of Convolution Neural Network (CNN). However, in the current scenario complete autonomy is still to be achieved. Although today's CNN have brought us closer to autonomy than ever before. CNN contain artificial neurons which are trained using preset rules and these rules determine whether it will provide an output or not when given a set of inputs. CNN will analyze various road footages, which include various scenarios such as collisions, empty roads, traffic, etc. CNN will analyze and send appropriate instructions to the car such as brake, accelerate, slow down, etc.

Convolutional Neural Network (CNN): The architecture and applications

Applied Journal of Physical Science Volume 4(4), pages 42-50, December 2022 Article Number: 1378CAD82 ISSN: 2756-6684 https://doi.org/10.31248/AJPS2022.085 https://integrityresjournals.org/journal/AJPS, 2022

The human brain is made up of several hundreds of billions of interconnected neurons that process information in parallel. Researchers in the field of artificial intelligence have successfully demonstrated a considerable level of intelligence on chips and this has been termed Neural Networks (NNs). Neural networks, also known as artificial neural networks (ANNs) or simulated neural networks (SNNs), are a subset of machine learning (ML) and they are at the heart of deep learning algorithms. These subsets of ML have their names and structures derived from the human brain and the way that biological neurons signal to one another. A class of NNs that are often used in processing digital data images is the Convolutional Neural Network (CNN or ConvNet). The human brain processes a huge amount of information with each neuron having its own receptive field connected to other neurons in a way that they cover the entire visual field. Mimicking the biological technique, where the neurons only respond to stimuli in the restricted region of the visual field referred to as the receptive field, each neuron in the CNN processes data only in its receptive field. In this review paper, the architecture and application of CNN are presented. Its evolution, concepts, and approaches to solving problems related to digital images, computer vision and are also examined.