Navigating Self-Driving Vehicles Using Convolutional Neural Network

Duong, Minh-Thien; Do, Truong-Dong; Le, My-Ha

doi:10.1109/gtsd.2018.8595533

Cited by 36 publications

(8 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…De manera similar, la investigación presentada en (Thieng, Dong, & Ha, 2018) introduce un entorno de simulación que también utiliza un único carril. En este caso la red no solamente predice el ángulo de dirección, sino que también la velocidad, lo que resulta útil para la navegación durante las curvas.…”

Section: Discussionunclassified

Predicción del ángulo de giro para un auto: Implementación de dos áreas de interés

Martínez-Hernández,

Arias-Aguilar,

Macías-García

et al. 2024

ICBI

View full text Add to dashboard Cite

La predicción del ángulo de dirección en vehículos inteligentes es un tema ampliamente estudiado en la literatura. Sin embargo, se requiere la intervención de un usuario para operar al vehículo, limitando el grado de autonomía. Este trabajo propone algoritmos basados en redes neuronales artificiales para determinar el ángulo de giro de un vehículo en movimiento, con aplicaciones en tiempo real para vehículos a escala en una pista de dos carriles. Utilizando una cámara frontal centrada en el vehículo se determinan dos áreas de interés: la imagen original y una versión rectificada mediante un cambio de perspectiva. Posteriormente, se emplea la tupla de imágenes para construir dos bases de datos etiquetadas con el ángulo deseado de giro, las cuales, son empleadas para entrenar dos redes neuronales convolucionales. Una vez entrenadas, ambos modelos son implementados en tiempo real para guiar un vehículo a escala en una pista libre de obstáculos, permitiendo su navegación autónoma dentro del carril designado y observando el comportamiento en cada caso.

show abstract

Section: Discussionunclassified

Predicción del ángulo de giro para un auto: Implementación de dos áreas de interés

Martínez-Hernández,

Arias-Aguilar,

Macías-García

et al. 2024

ICBI

View full text Add to dashboard Cite

show abstract

“…For selfdriving vehicles, deep learning has been widely used. Obstacle detection, scene recognition, and lane recognition are all major issues in self-driving cars that must be solved [23].…”

Section: Figure 1: Self-driving Carmentioning

confidence: 99%

Deep Learning Control for Autonomous Robot

Farkh¹,

Alhuwaimel²,

Alzahrani³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Several applications of machine learning and artificial intelligence, have acquired importance and come to the fore as a result of recent advances and improvements in these approaches. Autonomous cars are one such application. This is expected to have a significant and revolutionary influence on society. Integration with smart cities, new infrastructure and urban planning with sophisticated cyber-security are some of the current ramifications of self-driving automobiles. The autonomous automobile, often known as selfdriving systems or driverless vehicles, is a vehicle that can perceive its surroundings and navigate predetermined routes without human involvement. Cars are on the verge of evolving into autonomous robots, thanks to significant breakthroughs in artificial intelligence and related technologies, and this will have a wide range of socio-economic implications. However, in order for these automobiles to become a reality, they must be endowed with the perception and cognition necessary to deal with high-pressure real-life events and make proper judgments and take appropriate action. The majority of self-driving car technologies are based on computer systems that automate vehicle control parts. From forward-collision warning and antilock brakes to lane-keeping and adaptive drive control, to fully automated driving, these technological components have a wide range of capabilities. A self-driving car combines a wide range of sensors, actuators, and cameras. Recent researches on computer vision and deep learning are used to control autonomous driving systems. For self-driving automobiles, lane-keeping is crucial. This study presents a deep learning approach to obtain the proper steering angle to maintain the robot in the lane. We propose an advanced control for a selfdriving robot by using two controllers simultaneously. Convolutional neural networks (CNNs) are employed, to predict the car' and a proportionalintegral-derivative (PID) controller is designed for speed and steering control. This study uses a Raspberry PI based camera to control the robot car.

show abstract

“…Lately, many architectures of CNN have been proposed by researchers for steering angle prediction [24][25][26][27][28][29]. By analysis of available literature regarding the imitation-learning-based steering angle prediction, it was observed that the performance of a neural network architecture proposed in one research cannot be compared with an architecture proposed in another research.…”

Section: Related Workmentioning

confidence: 99%

Optimizing Steering Angle Predictive Convolutional Neural Network for Autonomous Car

Saleem¹,

Riaz²,

Shaikh³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Deep learning techniques, particularly convolutional neural networks (CNNs), have exhibited remarkable performance in solving visionrelated problems, especially in unpredictable, dynamic, and challenging environments. In autonomous vehicles, imitation-learning-based steering angle prediction is viable due to the visual imagery comprehension of CNNs. In this regard, globally, researchers are currently focusing on the architectural design and optimization of the hyperparameters of CNNs to achieve the best results. Literature has proven the superiority of metaheuristic algorithms over the manual-tuning of CNNs. However, to the best of our knowledge, these techniques are yet to be applied to address the problem of imitationlearning-based steering angle prediction. Thus, in this study, we examine the application of the bat algorithm and particle swarm optimization algorithm for the optimization of the CNN model and its hyperparameters, which are employed to solve the steering angle prediction problem. To validate the performance of each hyperparameters' set and architectural parameters' set, we utilized the Udacity steering angle dataset and obtained the best results at the following hyperparameter set: optimizer, Adagrad; learning rate, 0.0052; and nonlinear activation function, exponential linear unit. As per our findings, we determined that the deep learning models show better results but require more training epochs and time as compared to shallower ones. Results show the superiority of our approach in optimizing CNNs through metaheuristic algorithms as compared with the manual-tuning approach. Infield testing was also performed using the model trained with the optimal architecture, which we developed using our approach.

show abstract

Navigating Self-Driving Vehicles Using Convolutional Neural Network

Cited by 36 publications

References 7 publications

Predicción del ángulo de giro para un auto: Implementación de dos áreas de interés

Predicción del ángulo de giro para un auto: Implementación de dos áreas de interés

Deep Learning Control for Autonomous Robot

Optimizing Steering Angle Predictive Convolutional Neural Network for Autonomous Car

Contact Info

Product

Resources

About