Lane centering is a significant feature in the automotive industry and an important feature for advanced or autonomous vehicles, providing assistance to help drivers stay in their lane. The objective of this work is to utilize camera images which are processed by a lane-centering algorithm to make steering decisions. A model with a convolutional neural network (CNN) algorithm is used and simulated datasets are trained and tested. The goal is to make the program learn how to steer the vehicle autonomously and achieve end-to-end learning for steering command generation. The CNN can map raw pixels from cameras directly to steering commands without any intermediate feature engineering. A model is utilized which is created by NVIDIA researchers called the NVIDIA PilotNet. This network comprises five convolutional layers for feature extraction, followed by three fully connected layers for predicting the steering commands. The model is trained using two different sets of data to see how well the model performs with different types of data. The first set comes from Udacity’s Self-Driving Car Nanodegree Program, which uses their open-source Vehicle Simulation. Secondly, a dataset from the Mississippi State University Autonomous Vehicular Simulator (MAVS) is used. The training process involves reducing the error between predicted steering angles and the actual steering commands logged by the car. After the model has been trained, it is implemented for testing the car’s autonomous capabilities within the Self Driving Car Nanodegree Program Simulation. In this mode, the car demonstrates the ability to effectively track and navigate along the road lanes.
We integrate advanced computer vision and Vehicle-to-Infrastructure (V2I) communication systems for effective intersection navigation. In the first phase, the YOLOv8 deep learning model is employed to accurately detect traffic lights, with specialized training on the S2TLD Dataset for precision. Then we establish seamless V2I communication in MAVS Simulation, allowing vehicles to receive Signal Phase and Timing (SPaT) messages from traffic lights, enabling autonomous adjustment of speed and behavior. Simulating the scenarios in a high-fidelity automotive simulator demonstrates accurate traffic light detection and timely phase information, promising safer and more efficient intersection navigation for autonomous vehicles.
Adaptive Cruise Control (ACC) is one of the common advanced driving features that aims to assist the driver from fatigue. A lot of models for ACC are available, such as Proportional, Integral, and Derivative (PID), Model Predictive Control (MPC), and reinforcement learning (RL). Recently a deep RL technique called deep deterministic policy gradient (DDPG) has been widely used for velocity control. DDPG is a mixture of deep learning (DL) and RL method, that uses neural networks (NN) to estimate its action. In this work, we utilize an attention DDPG model. The attention mechanism in DDPG increases the overall effectiveness of the model by reducing focus on the less important features. The network structure consists of one hidden layer with 30 neurons, which has been deployed in our previous work. The reward function has been designed to concentrate on overall safety and comfort. In this paper, we introduce a new criterion of weather conditions, which has not been used before in the literature. We trained our model with a publicly available dataset. For testing, we created simulated sensor data created in the Mississippi State University Autonomous Vehicular Simulator (MAVS). We introduced various scenarios within the simulation environment with differing weather conditions to assess the performance of the ACC model. In many cases, the sensors are weather-sensitive, which can affect the performance of the ACC system. The primary objective of this study is to evaluate the performance of the Attention DDPG-based ACC model under varying weather conditions. The results show that the agent can maintain safety across a range of weather conditions.
For autonomous driving, pedestrian and road signs detection are key elements. There is much existing literature available addressing this issue successfully. However, the autonomous system requires a large and diverse set of training samples and labeling in real-world environments. Manual annotation of these samples is somewhat challenging and time-consuming. In this paper, our goal is to get better detection accuracy with minimal training data. For this, we have employed the active learning algorithm. Active learning is a useful method that selects only the effective portion of the dataset for training and reduces annotation costs. Though it uses only a small amount of the training data, it provides a high detection accuracy. In this work, we have chosen the deep active learning model for object detection via the probabilistic model of Choi et al. and modified the depth scale of different layers in the backbone. As real-world data may contain noise, motion, or other disruptions, we modified the original model to obtain improved detection results. In this experiment, we create a customized dataset that contains pedestrians, road signs, traffic lights, and zebra (or pedestrian) crossings to deploy the active learning algorithm. The experimental results show that the active learning model can produce good detection outcomes by accurately detecting and classifying pedestrians, road signs, traffic light, and zebra (or pedestrian) crossings.
KEYWORDS: Signal attenuation, Neural networks, Fourier transforms, Data processing, Data conversion, Cell phones, Neurons, Mobile devices, Received signal strength, Computer engineering
Mobile devices have distinct RF fingerprints, which are reflected by changes in the frequency of transmitted signals. The Short-Time Fourier Transform (STFT) is a suitable technique for evaluating this frequency content and thus identifying them. In this paper, we take advantage of STFT processing and perform roomlevel location classification. The raw in-phase and quadrature (IQ) signals and channel state information (CSI) frames have been collected using seven different cell phones. The data collection process has been performed in eight different locations on the same floor of our engineering building, which contains indoor hallways and rooms of different sizes. Three software-defined radios (SDRs) are placed in three different locations to receive signals simultaneously but separately. The IQ and CSI frames have been concatenated together for training a neural network. A Multi-Layer Perception (MLP) network has been used to train the concatenated signals as input and their corresponding locations as labels. A challenging aspect is that our dataset does not contain the same number of samples per location. Moreover, several locations have insufficient training data due to signal attenuation. An imbalanced learning method has been implemented in this dataset to overcome this limitation and improve the classification accuracy. The classification strategy involves binary classification like individual location vs. other. Using this approach, we obtain a mean accuracy of around 95%.
Navigating through an unknown environment is one of the key capabilities of the autonomous ground vehicle (AGV). It is relatively easier to traverse through an on-road environment, but moving through an off-road environment is challenging because of the inadequate driving path, obstacles, surface roughness, slope, dense vegetation, poor soil conditions, lack of road signs, etc. This complexity requires simulation of the AGV through many environments before facing an unknown situation in the real world. This paper proposes a dynamic path planning technique for AGV navigation in an off-road environment. First, a brief discussion on the traversability model and the factors mentioned in state of art such as vegetation density, soil condition, surface roughness, and slope individually. Secondly, we have proposed some modifications in the traversability model by introducing weights and exponents with each factor. Then, the A* algorithm has been analyzed by penalizing the weight and exponent values to get an optimal path. We used the Mississippi State University Autonomous Vehicular Simulator (MAVS) for simulation by creating an off-road scenario and using an AGV. We have generated a cost map based on the traversability score. The higher the score, the better the result. The optimal path is selected considering the traversability score. The novelty of this work is that we are exploring the linearity and non-linearity of the traversability model and applying the A* algorithm for path planning.
Adaptive cruise control (ACC), a common feature in an autonomous vehicle, is intended to automatically adjust the vehicle speed and maintain a safe distance from its preceding vehicle to avoid a collision. The main challenge is to filter the sensor data accurately, and the control system can make a decision quickly. This paper proposed a control method for ACC using the Extended Kalman filter (EKF) and a Proportional Integral Derivative (PID) controller, which can estimate the acceleration or braking of the preceding vehicle by adjusting the speed of the following vehicle. The proposed control method is assessed under various PID parameters using a Genetic Algorithm (GA) to optimize the ACC system using four loss metrics: (1) throttle loss, which accounts for fuel usage, and is proportional to the throttle setting; (2)ride quality, which is penalized by an excessive jerk (the first derivative of acceleration); (3) a distance penalty, which measures how far compared to the safe distance
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.