Deep Reinforcement Learning based pedestrian and independent vehicle safety fortification using intelligent perception

2022 ◽  
Vol 14 (1) ◽  
pp. 0-0
Keyword(s):  
Reinforcement Learning ◽  
Traffic Congestion ◽  
Carbon Emission ◽  
Light Detection And Ranging ◽  
Vehicle Safety ◽  
Sensitive Information ◽  
Emergency Braking ◽  
Prediction Rate ◽  
Cloud Server ◽  
Optimal Reward

The Light Detection and Ranging (LiDAR) sensor is utilized to track each sensed obstructions at their respective locations with their relative distance, speed, and direction; such sensitive information forwards to the cloud server to predict the vehicle-hit, traffic congestion and road damages. Learn the behaviour of the state to produce an appropriate reward as the recommendation to avoid tragedy. Deep Reinforcement Learning and Q-network predict the complexity and uncertainty of the environment to generate optimal reward to states. Consequently, it activates automatic emergency braking and safe parking assistance to the vehicles. In addition, the proposed work provides safer transport for pedestrians and independent vehicles. Compared to the newer methods, the proposed system experimental results achieved 92.15% higher prediction rate accuracy. Finally, the proposed system saves many humans, animal lives from the vehicle hit, suggests drivers for rerouting to avoid unpredictable traffic, saves fuel consumption, and avoids carbon emission.

scholarly journals An Efficiency Enhancing Methodology for Multiple Autonomous Vehicles in an Urban Network Adopting Deep Reinforcement Learning

2021 ◽  
Vol 11 (4) ◽  
pp. 1514 ◽  
Author(s):  
Quang-Duy Tran ◽  
Sang-Hoon Bae
Keyword(s):  
Reinforcement Learning ◽  
Traffic Congestion ◽  
Autonomous Vehicles ◽  
Penetration Rate ◽  
Autonomous Vehicle ◽  
Effective Means ◽  
Urban Network ◽  
Learning Agents ◽  
Policy Optimization ◽  
The Impact

To reduce the impact of congestion, it is necessary to improve our overall understanding of the influence of the autonomous vehicle. Recently, deep reinforcement learning has become an effective means of solving complex control tasks. Accordingly, we show an advanced deep reinforcement learning that investigates how the leading autonomous vehicles affect the urban network under a mixed-traffic environment. We also suggest a set of hyperparameters for achieving better performance. Firstly, we feed a set of hyperparameters into our deep reinforcement learning agents. Secondly, we investigate the leading autonomous vehicle experiment in the urban network with different autonomous vehicle penetration rates. Thirdly, the advantage of leading autonomous vehicles is evaluated using entire manual vehicle and leading manual vehicle experiments. Finally, the proximal policy optimization with a clipped objective is compared to the proximal policy optimization with an adaptive Kullback–Leibler penalty to verify the superiority of the proposed hyperparameter. We demonstrate that full automation traffic increased the average speed 1.27 times greater compared with the entire manual vehicle experiment. Our proposed method becomes significantly more effective at a higher autonomous vehicle penetration rate. Furthermore, the leading autonomous vehicles could help to mitigate traffic congestion.

scholarly journals A Survey on Applications of Reinforcement Learning in Flying Ad-Hoc Networks

Electronics ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 449
Author(s):  
Sifat Rezwan ◽  
Wooyeol Choi
Keyword(s):  
Reinforcement Learning ◽  
Ad Hoc Networks ◽  
Wireless Ad Hoc Networks ◽  
Routing Protocol ◽  
Traffic Congestion ◽  
Ad Hoc ◽  
High Mobility ◽  
Flight Trajectory ◽  
Research Issues ◽  
Hoc Networks

Flying ad-hoc networks (FANET) are one of the most important branches of wireless ad-hoc networks, consisting of multiple unmanned air vehicles (UAVs) performing assigned tasks and communicating with each other. Nowadays FANETs are being used for commercial and civilian applications such as handling traffic congestion, remote data collection, remote sensing, network relaying, and delivering products. However, there are some major challenges, such as adaptive routing protocols, flight trajectory selection, energy limitations, charging, and autonomous deployment that need to be addressed in FANETs. Several researchers have been working for the last few years to resolve these problems. The main obstacles are the high mobility and unpredictable changes in the topology of FANETs. Hence, many researchers have introduced reinforcement learning (RL) algorithms in FANETs to overcome these shortcomings. In this study, we comprehensively surveyed and qualitatively compared the applications of RL in different scenarios of FANETs such as routing protocol, flight trajectory selection, relaying, and charging. We also discuss open research issues that can provide researchers with clear and direct insights for further research.

scholarly journals A Privacy-Preserving Reinforcement Learning Approach for Dynamic Treatment Regimes on Health Data

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Xiaoqiang Sun ◽  
Zhiwei Sun ◽  
Ting Wang ◽  
Jie Feng ◽  
Jiakai Wei ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Learning Algorithm ◽  
Homomorphic Encryption ◽  
Treatment Decision ◽  
Data Encryption ◽  
Health Data ◽  
Secure Computation ◽  
Cloud Server ◽  
Dynamic Treatment ◽  
Reinforcement Learning Algorithm

Based on the clinical states of the patient, dynamic treatment regime technology can provide various therapeutic methods, which is helpful for medical treatment policymaking. Reinforcement learning is an important approach for developing this technology. In order to implement the reinforcement learning algorithm efficiently, the computation of health data is usually outsourced to the untrustworthy cloud server. However, it may leak, falsify, or delete private health data. Encryption is a common method for solving this problem. But the cloud server is difficult to calculate encrypted health data. In this paper, based on Cheon et al.’s approximate homomorphic encryption scheme, we first propose secure computation protocols for implementing comparison, maximum, exponentiation, and division. Next, we design a homomorphic reciprocal of square root protocol firstly, which only needs one approximate computation. Based on the proposed secure computation protocols, we design a secure asynchronous advantage actor-critic reinforcement learning algorithm for the first time. Then, it is used to implement a secure treatment decision-making algorithm. Simulation results show that our secure computation protocols and algorithms are feasible.

scholarly journals PERFORMANCE ANALYSIS OF A REAL-TIME ADAPTIVE PREDICTION ALGORITHM FOR TRAFFIC CONGESTION

2018 ◽  
Author(s):  
Khodabacchus Muhamad Nadeem ◽  
Tulsi Pawan Fowdur
Keyword(s):  
Real Time ◽  
Mean Square Error ◽  
Traffic Congestion ◽  
Selection Criterion ◽  
Prediction Algorithm ◽  
Mean Square ◽  
General Packet Radio Service ◽  
Prediction Algorithms ◽  
Cloud Server ◽  
Congestion Prediction

Traffic congestion is a major factor to consider in the development of a sustainable urban road network. In the past, several mechanisms have been developed to predict congestion, but few have considered an adaptive real-time congestion prediction. This paper proposes two congestion prediction approaches are created. The approaches choose between five different prediction algorithms using the Root Mean Square Error model selection criterion. The implementation consisted of a Global Positioning System based transmitter connected to an Arduino board with a Global System for Mobile/General Packet Radio Service shield that relays the vehicle’s position to a cloud server. A control station then accesses the vehicle’s position in real-time, computes its speed. Based on the calculated speed, it estimates the congestion level and it applies the prediction algorithms to the congestion level to predict the congestion for future time intervals. The performance of the prediction algorithms was analysed, and it was observed that the proposed schemes provide the best prediction results with a lower Mean Square Error than all other prediction algorithms when compared with the actual traffic congestion states.  

scholarly journals Outsourcing Computing of Large Matrix Jordan Decomposition

2019 ◽  
Vol 2019 ◽  
pp. 1-7
Author(s):  
Hongfeng Wu ◽  
Jingjing Yan
Keyword(s):  
Large Scale ◽  
Security Analysis ◽  
Sensitive Information ◽  
Jordan Decomposition ◽  
Verification Algorithm ◽  
Resource Limited ◽  
Large Matrix ◽  
Cloud Server ◽  
Scale Matrix ◽  
Efficient Verification

The Jordan decomposition of matrix is a typical scientific and engineering computational task, but such computation involves enormous computing resources for large matrices, which is burdensome for the resource-limited clients. Cloud computing enables computational resource-limited clients to economically outsource such problems to the cloud server. However, outsourcing Jordan decomposition of large-scale matrix to the cloud brings great security concerns and challenges since the matrices usually contain sensitive information. In this paper, we present a secure, verifiable, efficient, and privacy preserving algorithm for outsourcing Jordan decomposition of large-scale matrix. Security analysis shows that our algorithm is practically secure. Efficient verification algorithm is used to verify the results returned from the cloud.

scholarly journals A Carbon Emission Calculation Model for Roadside Parking

2021 ◽  
Vol 18 (4) ◽  
pp. 1906
Author(s):  
Wei Wang ◽  
Hongming Zhong ◽  
Yu Zeng ◽  
Yachao Liu ◽  
Jun Chen
Keyword(s):  
Carbon Emissions ◽  
Traffic Congestion ◽  
Carbon Emission ◽  
Rapid Development ◽  
Measurement Model ◽  
Motor Vehicles ◽  
Estimation Methods ◽  
Future Research ◽  
Emission Measurement ◽  
Emission Model

With the sustained and rapid development of China’s national economy, the number of motor vehicles owned by families in cities is rapidly growing. Consequently, problems of traffic congestion and air pollution have also appeared in these cities. Roadside parking traffic has also become an important part of the transportation system in cities. However, there is no specific measurement model for carbon emissions caused by roadside parking in the proposed traffic carbon emission model. Therefore, we aim to establish a carbon emission measurement model for roadside parking. In this paper, we first study the characteristics of the deceleration and maneuvering of parking vehicles and the blocking impact on running vehicles in a typical roadside parking scenario. We then establish and fit models of the direct and indirect carbon emissions during roadside parking. Based on the carbon emission model, we propose a calculation method for roadside parking carbon emissions, including accounting and estimation methods. These models can be used to calculate the carbon emissions from roadside parking in a traffic carbon emissions system. We also hope that these models will help future research on the optimization of roadside parking facilities for energy saving and emission reduction.

scholarly journals Road Traffic Status and Carbon Emission Estimation Methods

2020 ◽  
Vol 7 (2) ◽  
pp. p34
Author(s):  
Yang Kaixi
Keyword(s):  
Carbon Emissions ◽  
Traffic Congestion ◽  
Carbon Emission ◽  
Evaluation Method ◽  
Road Traffic ◽  
Estimation Methods ◽  
Vehicle Exhaust ◽  
Emission Data ◽  
Traffic Conditions ◽  
The Impact

This paper mainly studies the relationship between traffic status and carbon emission, and the evaluation method of carbon emission based on traffic status. First of all, the traffic status is defined. In this paper, the traffic status is divided into traffic congestion and unobstructed traffic. Then, this paper analyzes the influence of different traffic conditions on carbon emissions in the same fleet at the same time through the study of vehicle exhaust emissions in both the unobstructed and congested traffic conditions. The unobstructed section traffic is used to simulate the unobstructed traffic state, and the intersection is used to simulate the traffic congestion. Finally, the two kinds of carbon emission data are compared to obtain the impact of traffic status on carbon emissions.

Sign in / Sign up

Export Citation Format

Share Document