scholarly journals On Addressing Heterogeneity in Federated Learning for Autonomous Vehicles Connected to a Drone Orchestrator

2021 ◽  
Vol 2 ◽  
Author(s):  
Igor Donevski ◽  
Jimmy Jessen Nielsen ◽  
Petar Popovski
Keyword(s):  
Neural Network ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Data Distribution ◽  
Road Vehicles ◽  
Critical Object ◽  
Data Heterogeneity ◽  
Proactive Measures ◽  
Local Optimizer ◽  
Reactive Method

In this paper we envision a federated learning (FL) scenario in service of amending the performance of autonomous road vehicles, through a drone traffic monitor (DTM), that also acts as an orchestrator. Expecting non-IID data distribution, we focus on the issue of accelerating the learning of a particular class of critical object (CO), that may harm the nominal operation of an autonomous vehicle. This can be done through proper allocation of the wireless resources for addressing learner and data heterogeneity. Thus, we propose a reactive method for the allocation of wireless resources, that happens dynamically each FL round, and is based on each learner’s contribution to the general model. In addition to this, we explore the use of static methods that remain constant across all rounds. Since we expect partial work from each learner, we use the FedProx FL algorithm, in the task of computer vision. For testing, we construct a non-IID data distribution of the MNIST and FMNIST datasets among four types of learners, in scenarios that represent the quickly changing environment. The results show that proactive measures are effective and versatile at improving system accuracy, and quickly learning the CO class when underrepresented in the network. Furthermore, the experiments show a tradeoff between FedProx intensity and resource allocation efforts. Nonetheless, a well adjusted FedProx local optimizer allows for an even better overall accuracy, particularly when using deeper neural network (NN) implementations.

scholarly journals Computer vision based obstacle detection and target tracking for autonomous vehicles

2021 ◽  
Vol 336 ◽  
pp. 07004
Author(s):  
Ruoyu Fang ◽  
Cheng Cai
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Deep Learning ◽  
Target Tracking ◽  
Real Time ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Obstacle Detection ◽  
Pid Algorithm ◽  
Deep Learning Neural Network

Obstacle detection and target tracking are two major issues for intelligent autonomous vehicles. This paper proposes a new scheme to achieve target tracking and real-time obstacle detection of obstacles based on computer vision. ResNet-18 deep learning neural network is utilized for obstacle detection and Yolo-v3 deep learning neural network is employed for real-time target tracking. These two trained models can be deployed on an autonomous vehicle equipped with an NVIDIA Jetson Nano motherboard. The autonomous vehicle moves to avoid obstacles and follow tracked targets by camera. Adjusting the steering and movement of the autonomous vehicle according to the PID algorithm during the movement, therefore, will help the proposed vehicle achieve stable and precise tracking.

Comprehensive Overview of Neural Networks and Its Applications in Autonomous Vehicles

2019 ◽  
pp. 159-173
Author(s):  
Jay Rodge ◽  
Swati Jaiswal
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Neural Networks ◽  
Deep Learning ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Learning Algorithms ◽  
Activation Functions ◽  
Comprehensive Overview ◽  
Unit Component

Deep learning and Artificial intelligence (AI) have been trending these days due to the capability and state-of-the-art results that they provide. They have replaced some highly skilled professionals with neural network-powered AI, also known as deep learning algorithms. Deep learning majorly works on neural networks. This chapter discusses about the working of a neuron, which is a unit component of neural network. There are numerous techniques that can be incorporated while designing a neural network, such as activation functions, training, etc. to improve its features, which will be explained in detail. It has some challenges such as overfitting, which are difficult to neglect but can be overcome using proper techniques and steps that have been discussed. The chapter will help the academician, researchers, and practitioners to further investigate the associated area of deep learning and its applications in the autonomous vehicle industry.

An End-to-End Fully Automatic Bay Parking Approach for Autonomous Vehicles

2018 ◽  
Author(s):  
Rui Li ◽  
Weitian Wang ◽  
Yi Chen ◽  
Srivatsan Srinivasan ◽  
Venkat N. Krovi
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Human Vision ◽  
Automated Driving ◽  
Learning Framework ◽  
Research Platform ◽  
Automatic Parking ◽  
Fully Automatic

Fully automatic parking (FAP) is a key step towards the age of autonomous vehicle. Motivated by the contribution of human vision to human parking, in this paper, we propose a computer vision based FAP method for the autonomous vehicles. Based on the input images from a rear camera on the vehicle, a convolutional neural network (CNN) is trained to automatically output the steering and velocity commands for the vehicle controlling. The CNN is trained by Caffe deep learning framework. A 1/10th autonomous vehicle research platform (1/10-SAVRP), which configured with a vehicle controller unit, an automated driving processor, and a rear camera, is used for demonstrating the parking maneuver. The experimental results suggested that the proposed approach enabled the vehicle to gain the ability of parking independently without human input in different driving settings.

scholarly journals Autonomous Vehicle Fuel Economy Optimization with Deep Reinforcement Learning

Electronics ◽  
2020 ◽  
Vol 9 (11) ◽  
pp. 1911
Author(s):  
Hyunkun Kim ◽  
Hyeongoo Pyeon ◽  
Jong Sool Park ◽  
Jin Young Hwang ◽  
Sejoon Lim
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Reinforcement Learning ◽  
Velocity Profile ◽  
Fuel Economy ◽  
Autonomous Vehicles ◽  
Learning Algorithm ◽  
Autonomous Vehicle ◽  
Simulation Program ◽  
On The Road

The ever-increasing number of vehicles on the road puts pressure on car manufacturers to make their car fuel-efficient. With autonomous vehicles, we can find new strategies to optimize fuels. We propose a reinforcement learning algorithm that trains deep neural networks to generate a fuel-efficient velocity profile for autonomous vehicles given road altitude information for the planned trip. Using a highly accurate industry-accepted fuel economy simulation program, we train our deep neural network model. We developed a technique for adapting the heterogeneous simulation program on top of an open-source deep learning framework, and reduced dimension of the problem output with suitable parameterization to train the neural network much faster. The learned model combined with reinforcement learning-based strategy generation effectively generated the velocity profile so that autonomous vehicles can follow to control itself in a fuel efficient way. We evaluate our algorithm’s performance using the fuel economy simulation program for various altitude profiles. We also demonstrate that our method can teach neural networks to generate useful strategies to increase fuel economy even on unseen roads. Our method improved fuel economy by 8% compared to a simple grid search approach.

Deep learning–based traffic sign recognition for unmanned autonomous vehicles

2018 ◽  
Vol 232 (5) ◽  
pp. 497-505 ◽  
Author(s):  
Di Zang ◽  
Zhihua Wei ◽  
Maomao Bao ◽  
Jiujun Cheng ◽  
Dongdong Zhang ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Traffic Sign Recognition ◽  
Traffic Sign ◽  
Traffic Signs ◽  
Sign Recognition ◽  
The Time Domain

Being one of the key techniques for unmanned autonomous vehicle, traffic sign recognition is applied to assist autopilot. Colors are very important clues to identify traffic signs; however, color-based methods suffer performance degradation in the case of light variation. Convolutional neural network, as one of the deep learning methods, is able to hierarchically learn high-level features from the raw input. It has been proved that convolutional neural network–based approaches outperform the color-based ones. At present, inputs of convolutional neural networks are processed either as gray images or as three independent color channels; the learned color features are still not enough to represent traffic signs. Apart from colors, temporal constraint is also crucial to recognize video-based traffic signs. The characteristics of traffic signs in the time domain require further exploration. Quaternion numbers are able to encode multi-dimensional information, and they have been employed to describe color images. In this article, we are inspired to present a quaternion convolutional neural network–based approach to recognize traffic signs by fusing spatial and temporal features in a single framework. Experimental results illustrate that the proposed method can yield correct recognition results and obtain better performance when compared with the state-of-the-art work.

scholarly journals Applicability of Computer Vision Architectures and Their Influence on Traffic Safety of Autonomous Vehicles

2019 ◽  
Vol 8 (6) ◽  
pp. 5295-5301 ◽  
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Traffic Safety ◽  
Autonomous Vehicles ◽  
Vision System ◽  
Autonomous Vehicle ◽  
Computing Time ◽  
Weather Conditions ◽  
Network Architectures ◽  
Neural Network Architectures

This article considers modern rapid architectures of detecting neural networks, structural peculiarities of each selected neural network architectures are analyzed. Experiment is carried out on the basis of potentially dangerous situation upon autonomous vehicle movement; in the selected experimental environment a set of architectures for computer vision system of autonomous vehicle is analyzed, and traffic safety of autonomous vehicle is estimated under various weather conditions; computing time required for application of additional control and analysis algorithms is evaluated. Experimental results are analyzed aiming at development of reasonable selection of neural network architectures for object recognition required for variability of support of autonomous vehicle traffic. Conclusion about applicability of the considered neural network architectures is made for conditions of certain project.

Vision-Based Navigation of Autonomous Vehicles in Roadway Environments with Unexpected Hazards

2019 ◽  
Vol 2673 (12) ◽  
pp. 494-507 ◽  
Author(s):  
Mhafuzul Islam ◽  
Mashrur Chowdhury ◽  
Hongda Li ◽  
Hongxin Hu
Keyword(s):  
Object Detection ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Semantic Segmentation ◽  
Steering Wheel ◽  
Potential Hazard ◽  
Driving System ◽  
Hazardous Object ◽  
Vision Based Navigation ◽  
Navigational System

Vision-based navigation of autonomous vehicles primarily depends on the deep neural network (DNN) based systems in which the controller obtains input from sensors/detectors, such as cameras, and produces a vehicle control output, such as a steering wheel angle to navigate the vehicle safely in a roadway traffic environment. Typically, these DNN-based systems in the autonomous vehicle are trained through supervised learning; however, recent studies show that a trained DNN-based system can be compromised by perturbation or adverse inputs. Similarly, this perturbation can be introduced into the DNN-based systems of autonomous vehicles by unexpected roadway hazards, such as debris or roadblocks. In this study, we first introduce a hazardous roadway environment that can compromise the DNN-based navigational system of an autonomous vehicle, and produce an incorrect steering wheel angle, which could cause crashes resulting in fatality or injury. Then, we develop a DNN-based autonomous vehicle driving system using object detection and semantic segmentation to mitigate the adverse effect of this type of hazard, which helps the autonomous vehicle to navigate safely around such hazards. We find that our developed DNN-based autonomous vehicle driving system, including hazardous object detection and semantic segmentation, improves the navigational ability of an autonomous vehicle to avoid a potential hazard by 21% compared with the traditional DNN-based autonomous vehicle driving system.

The human-like trajectory planning for autonomous vehicles based on optimal control in a test track environment

2021 ◽  
pp. 095440702110090
Author(s):  
Xing Xu ◽  
Minglei Li ◽  
Feng Wang ◽  
Ju Xie ◽  
Xiaohan Wu ◽  
...  
Keyword(s):  
Optimal Control ◽  
Autonomous Vehicles ◽  
Optimal Trajectory ◽  
Control Method ◽  
Autonomous Vehicle ◽  
Trajectory Data ◽  
Test Track ◽  
Optimal Control Method ◽  
The Future ◽  
On The Road

A human-like trajectory could give a safe and comfortable feeling for the occupants in an autonomous vehicle especially in corners. The research of this paper focuses on planning a human-like trajectory along a section road on a test track using optimal control method that could reflect natural driving behaviour considering the sense of natural and comfortable for the passengers, which could improve the acceptability of driverless vehicles in the future. A mass point vehicle dynamic model is modelled in the curvilinear coordinate system, then an optimal trajectory is generated by using an optimal control method. The optimal control problem is formulated and then solved by using the Matlab tool GPOPS-II. Trials are carried out on a test track, and the tested data are collected and processed, then the trajectory data in different corners are obtained. Different TLCs calculations are derived and applied to different track sections. After that, the human driver’s trajectories and the optimal line are compared to see the correlation using TLC methods. The results show that the optimal trajectory shows a similar trend with human’s trajectories to some extent when driving through a corner although it is not so perfectly aligned with the tested trajectories, which could conform with people’s driving intuition and improve the occupants’ comfort when driving in a corner. This could improve the acceptability of AVs in the automotive market in the future. The driver tends to move to the outside of the lane gradually after passing the apex when driving in corners on the road with hard-lines on both sides.

scholarly journals Development of an Improved Rapidly Exploring Random Trees Algorithm for Static Obstacle Avoidance in Autonomous Vehicles

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 2244
Author(s):  
S. M. Yang ◽  
Y. A. Lin
Keyword(s):  
Path Planning ◽  
Obstacle Avoidance ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Optimal Path ◽  
Random Trees ◽  
Average Deviation ◽  
Lane Changes ◽  
Path Smoothing ◽  
Rapidly Exploring Random Trees

Safe path planning for obstacle avoidance in autonomous vehicles has been developed. Based on the Rapidly Exploring Random Trees (RRT) algorithm, an improved algorithm integrating path pruning, smoothing, and optimization with geometric collision detection is shown to improve planning efficiency. Path pruning, a prerequisite to path smoothing, is performed to remove the redundant points generated by the random trees for a new path, without colliding with the obstacles. Path smoothing is performed to modify the path so that it becomes continuously differentiable with curvature implementable by the vehicle. Optimization is performed to select a “near”-optimal path of the shortest distance among the feasible paths for motion efficiency. In the experimental verification, both a pure pursuit steering controller and a proportional–integral speed controller are applied to keep an autonomous vehicle tracking the planned path predicted by the improved RRT algorithm. It is shown that the vehicle can successfully track the path efficiently and reach the destination safely, with an average tracking control deviation of 5.2% of the vehicle width. The path planning is also applied to lane changes, and the average deviation from the lane during and after lane changes remains within 8.3% of the vehicle width.

scholarly journals Modelling of the system “driver - automation - autonomous vehicle - road”

2020 ◽  
Vol 10 (1) ◽  
pp. 175-182 ◽  
Author(s):  
Grzegorz Koralewski
Keyword(s):  
Autonomous Vehicles ◽  
Combustion Engine ◽  
Autonomous Vehicle ◽  
Application Software ◽  
Motion Simulation ◽  
Gear Shift ◽  
Shift Control ◽  
Driving Torque ◽  
Physical Quantities ◽  
Motion Quality

AbstractThe work presents a simulation model of a “driver–automation–autonomous vehicles–road” system which is the basis for synthesis of automatic gear shift control system. The mathematical description makes use of physical quantities which characterise driving torque transformation from the combustion engine to the car driven wheels. The basic components of the model are algorithms for the driver’s action logic in controlling motion velocity, logic of gear shift control functioning regarding direction and moment of switching, for determining right-hand side of differential equations and for motion quality indicators. The model is realised in a form of an application software package, comprising sub-programmes for input data, for computerised motion simulation of cars with mechanical and hydro-mechanical – automatically controlled – transmission systems and for models of characteristic car routes.

Sign in / Sign up

Export Citation Format

Share Document