A Deep Reinforcement Learning Approach for Efficient, Safe and Comfortable Driving

Selvaraj, Dinesh Cyril; Hegde, Shailesh; Amati, Nicola; Deflorio, Francesco Paolo; Chiasserini, Carla-Fabiana

doi:10.3390/app13095272

Cited by 11 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sci. 2023, 13, x FOR PEER REVIEW 7 of 17 In different external driving environments, the visual perception of drivers varies according to the characteristics of the environment [23][24][25][26]. In order to accurately quantify the features of different environments, we propose three measurement indicators: visual brightness, visual clarity, and visual obstruction.…”

Section: Analysis Of Environmental Composition Elementsmentioning

confidence: 99%

A Visual-Based Approach for Driver’s Environment Perception and Quantification in Different Weather Conditions

Luo,

Liu,

Mei

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

The decision-making behavior of drivers during the driving process is influenced by various factors, including road conditions, traffic situations, weather conditions, and so on. However, our understanding and quantification of the driving environment are still very limited, which not only increases the risk of driving but also hinders the deployment of autonomous vehicles. To address this issue, this study attempts to transform drivers’ visual perception into machine vision perception. Specifically, the study provides a detailed decomposition of the elements constituting weather and proposes three environmental quantification indicators: visibility brightness, visibility clarity, and visibility obstruction rate. These indicators help us to describe and quantify the driving environment more accurately. Based on these indicators, a visual-based environmental quantification method is further proposed to better understand and interpret the driving environment. Additionally, based on drivers’ visual perception, this study extensively analyzes the impact of environmental factors on driver behavior. A cognitive assessment model is established to evaluate drivers’ cognitive abilities in different environments. The effectiveness and accuracy of the model are validated through driver simulation experiments, thereby establishing a communication bridge between the driving environment and driver behavior. This research achievement enables us to better understand the decision-making behavior of drivers in specific environments and provides some references for the development of intelligent driving technology.

show abstract

Section: Analysis Of Environmental Composition Elementsmentioning

confidence: 99%

A Visual-Based Approach for Driver’s Environment Perception and Quantification in Different Weather Conditions

Luo,

Liu,

Mei

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Sheikh et al [28] primarily investigated collision avoidance for the on-ramp merging of autonomous vehicles and proposed a collision avoidance model that effectively reduces collision risks and improves traffic safety. Additionally, some researchers employ techniques such as deep learning [29] and reinforcement learning [30] to enhance the performance of CAV platoons under control delays and sensor measurement errors. Nonetheless, these methods require large datasets for training and face generalization challenges.…”

Section: Introductionmentioning

confidence: 99%

Modeling and Optimization of Connected and Automated Vehicle Platooning Cooperative Control with Measurement Errors

Luo,

Li,

et al. 2023

Sensors

View full text Add to dashboard Cite

This paper presents a cooperative control method for connected and automated vehicle (CAV) platooning, thus specifically addressing the challenge of sensor measurement errors that can disrupt the stability of the CAV platoon. Initially, the state-space equation of the CAV platooning system was formulated, thereby taking into account the measurement error of onboard sensors. The superposition effect of the sensor measurement errors was statistically analyzed, thereby elucidating its impact on cooperative control in CAV platooning. Subsequently, the application of a Kalman filter was proposed as a means to mitigate the adverse effects of measurement errors. Additionally, the CAV formation control problem was transformed into an optimal control decision problem by introducing an optimal control decision strategy that does not impose pure state variable inequality constraints. The proposed method was evaluated through simulation experiments utilizing real vehicle trajectory data from the Next Generation Simulation (NGSIM). The results demonstrate that the method presented in this study effectively mitigates the influence of measurement errors, thereby enabling coordinated vehicle-following behavior, achieving smooth acceleration and deceleration throughout the platoon, and eliminating traffic oscillations. Overall, the proposed method ensures the stability and comfort of the CAV platooning formation.

show abstract

“…There is a need to investigate the trade-off between optimization efficiency and model performance. While efficient optimization algorithms can improve the speed of training machine learning models, there may be a trade-off between optimization efficiency and model performance (Yu et al, 2020) (Turchetta et al, 2020) (Selvaraj et al, 2023). Previous research has explored this trade-off to some extent, but more research is needed to develop algorithms that can balance these factors and optimize both efficiency and performance.…”

mentioning

confidence: 99%

Efficient optimization algorithms for various machine learning tasks, including classification, regression, and clustering

Sihotang

Albert²,

Riandari

et al. 2023

Idea

View full text Add to dashboard Cite

The research on efficient optimization algorithms for machine learning is novel because it addresses several gaps in previous research and proposes new solutions to improve the efficiency and accuracy of machine learning models. Firstly, the proposed research focuses on developing more efficient algorithms for large-scale deep learning. While there have been many optimization algorithms proposed for deep learning, the proposed research aims to develop new algorithms that can handle the complexity and scale of these models and improve their efficiency. Secondly, the proposed research aims to explore the effectiveness of optimization algorithms for different types of machine learning tasks. While many studies have focused on deep learning, the proposed research aims to evaluate the effectiveness of optimization algorithms for other types of machine learning tasks, such as reinforcement learning, unsupervised learning, and semi-supervised learning. Thirdly, the proposed research aims to develop optimization algorithms that can handle noisy and incomplete data, which is a significant challenge for machine learning models. The proposed research aims to develop algorithms that can handle noisy and incomplete data and improve the accuracy of machine learning models. Fourthly, the proposed research aims to develop optimization algorithms that can handle non-convex objective functions. While some optimization techniques have been proposed for non-convex optimization, the proposed research aims to develop new algorithms that can handle these functions and improve the accuracy of machine learning models. The proposed research aims to investigate the trade-off between optimization efficiency and model performance. While previous research has explored this trade-off to some extent, the proposed research aims to develop algorithms that can balance these factors and optimize both efficiency and performance. The proposed research is novel because it addresses several gaps in previous research and proposes new solutions to improve the efficiency and accuracy of machine learning models for various tasks, including classification, regression, and clustering. By developing new algorithms and evaluating their effectiveness for different types of machine learning tasks, the proposed research can advance the field of machine learning and improve the accuracy and efficiency of machine learning models.

show abstract

A Deep Reinforcement Learning Approach for Efficient, Safe and Comfortable Driving

Cited by 11 publications

References 27 publications

A Visual-Based Approach for Driver’s Environment Perception and Quantification in Different Weather Conditions

A Visual-Based Approach for Driver’s Environment Perception and Quantification in Different Weather Conditions

Modeling and Optimization of Connected and Automated Vehicle Platooning Cooperative Control with Measurement Errors

Efficient optimization algorithms for various machine learning tasks, including classification, regression, and clustering

Contact Info

Product

Resources

About