A Study on Autonomous Driving Simulation Using Deep Learning Process Model

2022 ◽  
Vol 10 (1) ◽  
pp. 0-0
Keyword(s):  
Deep Learning ◽  
Process Model ◽  
Real Data ◽  
Autonomous Driving ◽  
Learning Technology ◽  
The Road ◽  
Traffic Flow Prediction ◽  
Multiple Sensors ◽  
Cloud Server ◽  
And Control

Along with artificial intelligence technologies, deep learning technology, which has recently received a great deal of attention, has been studied on the basis of developed artificial neural networks. This thesis deals with the detection, recognition, judgment, and control that are included in the basic technologies of the autonomous driving subsystems to achieve fully autonomous driving. And this work solves many problems in this area. The use of the CARLA simulation in this project is the development of a deep learning intelligent autonomous driving system in the road environment. Autonomous driving recognizes the situation by processing the data collected through images from multiple sensors or lidars and cameras in real-time. In the cloud server process using real data, explore various deep learning models for traffic flow prediction, return the model trained onboard, perform the prediction and solve the problem of fully autonomous driving, including a module of control, which is a CARLA simulation.

scholarly journals Road-Aware Trajectory Prediction for Autonomous Driving on Highways

Sensors ◽  
2020 ◽  
Vol 20 (17) ◽  
pp. 4703
Author(s):  
Yookhyun Yoon ◽  
Taeyeon Kim ◽  
Ho Lee ◽  
Jahnghyon Park
Keyword(s):  
Deep Learning ◽  
Autonomous Vehicles ◽  
Prediction Method ◽  
Autonomous Driving ◽  
Structural Constraints ◽  
High Definition ◽  
Trajectory Prediction ◽  
The Road ◽  
Road Geometry ◽  
Efficient Learning

For driving safely and comfortably, the long-term trajectory prediction of surrounding vehicles is essential for autonomous vehicles. For handling the uncertain nature of trajectory prediction, deep-learning-based approaches have been proposed previously. An on-road vehicle must obey road geometry, i.e., it should run within the constraint of the road shape. Herein, we present a novel road-aware trajectory prediction method which leverages the use of high-definition maps with a deep learning network. We developed a data-efficient learning framework for the trajectory prediction network in the curvilinear coordinate system of the road and a lane assignment for the surrounding vehicles. Then, we proposed a novel output-constrained sequence-to-sequence trajectory prediction network to incorporate the structural constraints of the road. Our method uses these structural constraints as prior knowledge for the prediction network. It is not only used as an input to the trajectory prediction network, but is also included in the constrained loss function of the maneuver recognition network. Accordingly, the proposed method can predict a feasible and realistic intention of the driver and trajectory. Our method has been evaluated using a real traffic dataset, and the results thus obtained show that it is data-efficient and can predict reasonable trajectories at merging sections.

scholarly journals Deep learning and control algorithms of direct perception for autonomous driving

2020 ◽  
Vol 51 (1) ◽  
pp. 237-247
Author(s):  
Der-Hau Lee ◽  
Kuan-Lin Chen ◽  
Kuan-Han Liou ◽  
Chang-Lun Liu ◽  
Jinn-Liang Liu
Keyword(s):  
Deep Learning ◽  
Autonomous Driving ◽  
Direct Perception ◽  
Control Algorithms ◽  
And Control

Local Trajectory Planning for Autonomous Racing Vehicles Based on the Rapidly-Exploring Random Tree Algorithm

2021 ◽  
Author(s):  
Eugenio Tramacere ◽  
Sara Luciani ◽  
Stefano Feraco ◽  
Salvatore Circosta ◽  
Irfan Khan ◽  
...  
Keyword(s):  
Trajectory Planning ◽  
Real Data ◽  
Autonomous Driving ◽  
Front Wheel ◽  
Random Tree ◽  
Bicycle Model ◽  
Planning Algorithm ◽  
Command Signals ◽  
Three Degree Of Freedom ◽  
And Control

Abstract This paper presents a local trajectory planning method based on the Rapidly-exploring Random Tree (RRT) algorithm using Dubins curves for autonomous racing vehicles. The purpose of the investigated method is the real-time computation of a trajectory that could be feasible in autonomous driving. The vehicle is considered as a three Degree-of-Freedom bicycle model and a Model Predictive Control (MPC) algorithm is implemented to control the lateral and longitudinal vehicle dynamics. The trajectory planning algorithm exploits a perception pipeline using a LiDAR sensor that is mounted onto the front wing of the racing vehicle. The MPC computes the acceleration/ deceleration command and the front wheel steering angle to follow the predicted trajectory. The trajectory and control algorithms are tested on real data acquisition performed on-board the vehicle. For validation purposes, the vehicle is driven autonomously during different maneuvers performed in the racing environment that is structured with traffic cones. The feasibility of the algorithm is evaluated in terms of error with respect to the planned trajectory, tracking velocity and maximum longitudinal acceleration. The effectiveness of the method is also evaluated with respect to command signals for the steering and acceleration actuators featured by the retained racing vehicle. The results demonstrate that the trajectory is well-tracked and the signals are compatible with the actuator constraints.

scholarly journals A Traffic Flow Prediction Method Based on Road Crossing Vector Coding and a Bidirectional Recursive Neural Network

Electronics ◽  
2019 ◽  
Vol 8 (9) ◽  
pp. 1006 ◽  
Author(s):  
Zhao ◽  
Zhao ◽  
Bai ◽  
Li
Keyword(s):  
Neural Network ◽  
Traffic Flow ◽  
Prediction Method ◽  
The Road ◽  
Traffic Flow Prediction ◽  
Vector Coding ◽  
Road Intersections ◽  
Spatio Temporal ◽  
Traffic Guidance ◽  
And Control

Aiming at the problems that current predicting models are incapable of extracting the inner rule of the traffic flow sequence in traffic big data, and unable to make full use of the spatio-temporal relationship of the traffic flow to improve the accuracy of prediction, a Bi-directional Regression Neural Network (BRNN) is proposed in this paper, which can fully apply the context information of road intersections both in the past and the future to predict the traffic volume, and further to make up the deficiency that the current models can only predict the next-moment output according to the time series information in the previous moment. Meanwhile, a vectorized code to screen out the intersections related to the predicting point in the road network and to train and predict through inputting the track data of the selected intersections into BRNN, is designed. In addition, the model is testified through the true traffic data in partial area of Shen Zhen. The results indicate that, compared with current traffic predicting models, the model in this paper is capable of providing the necessary evidence for traffic guidance and control due to its excellent performance in extracting the spatio-temporal feature of the traffic flow series, which can enhance the accuracy by 16.298% on average.

scholarly journals Curve Path Detection in Autonomous Vehicle using Deep Learning

2018 ◽  
Author(s):  
Balasriram Kodi ◽  
Manimozhi M
Keyword(s):  
Deep Learning ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Ground Truth ◽  
Autonomous Driving ◽  
Detection Algorithm ◽  
Lane Detection ◽  
Point To Point ◽  
And Control ◽  
Mapping Point

In the field of autonomous vehicles, lane detection and control plays an important role. In autonomous driving the vehicle has to follow the path to avoid the collision. A deep learning technique is used to detect the curved path in autonomous vehicles. In this paper a customized lane detection algorithm was implemented to detect the curvature of the lane. A ground truth labelling tool box for deep learning is used to detect the curved path in autonomous vehicle. By mapping point to point in each frame 80-90% computing efficiency and accuracy is achieved in detecting path.

Smart teaching mode based on particle swarm image recognition and human-computer interaction deep learning

2020 ◽  
Vol 39 (4) ◽  
pp. 5699-5711
Author(s):  
Shirong Long ◽  
Xuekong Zhao
Keyword(s):  
Feature Extraction ◽  
Particle Swarm Optimization ◽  
Deep Learning ◽  
Real Time ◽  
Image Recognition ◽  
Particle Swarm ◽  
Learning Technology ◽  
Search Performance ◽  
Swarm Optimization ◽  
Teaching Mode

The smart teaching mode overcomes the shortcomings of traditional teaching online and offline, but there are certain deficiencies in the real-time feature extraction of teachers and students. In view of this, this study uses the particle swarm image recognition and deep learning technology to process the intelligent classroom video teaching image and extracts the classroom task features in real time and sends them to the teacher. In order to overcome the shortcomings of the premature convergence of the standard particle swarm optimization algorithm, an improved strategy for multiple particle swarm optimization algorithms is proposed. In order to improve the premature problem in the search performance algorithm of PSO algorithm, this paper combines the algorithm with the useful attributes of other algorithms to improve the particle diversity in the algorithm, enhance the global search ability of the particle, and achieve effective feature extraction. The research indicates that the method proposed in this paper has certain practical effects and can provide theoretical reference for subsequent related research.

Modelling and control of an alkaline water electrolysis process

2018 ◽  
Vol 1 (2) ◽  
pp. 9-14
Author(s):  
Marisol Cervantes-Bobadilla ◽  
Ricardo Fabricio Escobar Jiménez ◽  
José Francisco Gómez Aguilar ◽  
Tomas Emmanuel Higareda Pliego ◽  
Alberto Armando Alvares Gallegos
Keyword(s):  
Process Model ◽  
Water Electrolysis ◽  
Alkaline Water Electrolysis ◽  
Alkaline Water ◽  
Electrolysis Process ◽  
Linear Dynamic ◽  
Energy Current ◽  
Identification Technique ◽  
Nonlinear Static ◽  
And Control

In this research, an alkaline water electrolysis process is modelled. The electrochemical electrolysis is carried out in an electrolyzer composed of 12 series-connected steel cells with a solution 30% wt of potassium hydroxide. The electrolysis process model was developed using a nonlinear identification technique based on the Hammerstein structure. This structure consists of a nonlinear static block and a linear dynamic block. In this work, the nonlinear static function is modelled by a polynomial approximation equation, and the linear dynamic is modelled using the ARX structure. To control the current feed to the electrolyzer an unconstraint predictive controller was implemented, once the unconstrained MPC was simulated, some restrictions are proposed to design a constrained MPC (CMPC). The CMPC aim is to reduce the electrolyzer's energy consumption (power supply current). Simulation results showed the advantages of using the CMPC since the energy (current) overshoots are avoided.

The Frustration Regulation Journal: A Reflective Framework for Educators

Relay Journal ◽  
2019 ◽  
Author(s):  
Sam Morris
Keyword(s):  
Emotion Regulation ◽  
Process Model ◽  
Negative Impact ◽  
Language Education ◽  
Short Article ◽  
Language Classroom ◽  
As Stress ◽  
And Control ◽  
Important System ◽  
Behavioural Strategies

Teachers and advisors involved in the emotional business of language education feel frustrated from time to time, and if such emotions are not managed healthily, they may lead to negative outcomes such as stress and burnout. One important system for taking control of frustration is emotion regulation, the cognitive and behavioural strategies through which individuals manage their emotions. In this short article, I define frustration and discuss its negative impact on the language classroom. I then introduce a structured reflective journaling tool, built upon Gross’s Process model of emotion regulation (Gross, 2014, 2015) which may help teachers and advisors develop greater awareness and control over experiences of frustration.

scholarly journals Automatic Detection of Arrhythmia Based on Multi-Resolution Representation of ECG Signal

Sensors ◽  
2020 ◽  
Vol 20 (6) ◽  
pp. 1579
Author(s):  
Dongqi Wang ◽  
Qinghua Meng ◽  
Dongming Chen ◽  
Hupo Zhang ◽  
Lisheng Xu
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Channel Model ◽  
Expert Knowledge ◽  
Automatic Detection ◽  
Data Representation ◽  
Learning Technology ◽  
Arrhythmia Detection ◽  
Automatic Feature Extraction

Automatic detection of arrhythmia is of great significance for early prevention and diagnosis of cardiovascular disease. Traditional feature engineering methods based on expert knowledge lack multidimensional and multi-view information abstraction and data representation ability, so the traditional research on pattern recognition of arrhythmia detection cannot achieve satisfactory results. Recently, with the increase of deep learning technology, automatic feature extraction of ECG data based on deep neural networks has been widely discussed. In order to utilize the complementary strength between different schemes, in this paper, we propose an arrhythmia detection method based on the multi-resolution representation (MRR) of ECG signals. This method utilizes four different up to date deep neural networks as four channel models for ECG vector representations learning. The deep learning based representations, together with hand-crafted features of ECG, forms the MRR, which is the input of the downstream classification strategy. The experimental results of big ECG dataset multi-label classification confirm that the F1 score of the proposed method is 0.9238, which is 1.31%, 0.62%, 1.18% and 0.6% higher than that of each channel model. From the perspective of architecture, this proposed method is highly scalable and can be employed as an example for arrhythmia recognition.

Sign in / Sign up

Export Citation Format

Share Document