Gated branch neural network for mandatory lane changing suggestion at the on‐ramps of highway

Dou, Yangliu; Fang, Yihao; Hu, Chuan; Zheng, Rong; Yan, Fengjun

doi:10.1049/iet-its.2018.5093

Cited by 23 publications

(8 citation statements)

References 22 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meanwhile, others analysed road traffic accidents. Driver behaviour, which included the prediction of distracted driving (Eraqi et al 2019), subjective risk perception while driving (Ping et al 2018), lane changing behaviour (Dou et al 2018), and braking behaviour (Christopoulos et al 2018) was predicted in 17 studies. Meanwhile, travel behaviour such as mode choice and activity classification was predicted using deep learning methods in five (5) studies.…”

Section: Areas Of Applicationmentioning

confidence: 99%

Deep Learning in Transport Studies: A Meta-analysis on the Prediction Accuracy

Varghese

Chikaraishi

Urata

2020

J. Big Data Anal. Transp.

View full text Add to dashboard Cite

Deep learning methods are being increasingly applied in transport studies, while the methods require modellers to go through a try-and-error model tuning process particularly on choosing neural network structure. Moreover, the accuracy level also depends on other factors such as the type of data, sample size, region of data collection, and time of prediction. To efficiently facilitate such a model tuning process, this study attempts to summarize the relationship between the prediction accuracy of deep learning models and the factors which influence it. We conducted a comprehensive review of the literature by adopting a detailed search strategy, followed by a meta-analysis on prediction accuracy. Four separate linear mixed effects models, taking into account unobserved heterogeneities in prediction accuracy across studies, were developed to statistically test the impacts of influential factors on prediction accuracy for (a) all observations (136 studies; 2314 cases), (b) studies with MAPE, MRE, and average accuracy indicators (86 studies; 1,878 cases), (c) classification-based studies with accuracy indicator (29 studies; 220 cases), and (d) traffic forecasting studies with MAPE, MRE, and average accuracy indicators (36 studies, 991 cases). The final model includes additional factors to test the influence of sample size and time horizon of prediction variables. The findings showed that, as expected, deep learning models, particularly ones that consider spatiotemporal dependencies of transport phenomena, show better prediction accuracies compared to conventional machine learning models. We also found that, on average, the prediction accuracy is improved by 5.90% with 100 million additional data, while the accuracy is reduced by 5.28% with 100 min increase in time horizon of prediction in traffic forecasting studies. We concluded this paper with a comprehensive summary of the existing findings on the applications of deep learning to transport studies.

show abstract

Section: Areas Of Applicationmentioning

confidence: 99%

Deep Learning in Transport Studies: A Meta-analysis on the Prediction Accuracy

Varghese

Chikaraishi

Urata

2020

J. Big Data Anal. Transp.

View full text Add to dashboard Cite

show abstract

“…In general, risk assessment can be broadly grouped to two categories: probabilistic and deterministic. Dou [17] used a gated branch neural network to probabilistically model lane changing behaviour on highways. Probabilistic methods take into account uncertainties that are present in the system.…”

Section: Related Workmentioning

confidence: 99%

Trajectory Optimization and Situational Analysis Framework for Autonomous Overtaking With Visibility Maximization

Andersen

Alonso–Mora

Eng

et al. 2020

IEEE Trans. Intell. Veh.

View full text Add to dashboard Cite

In this paper we present a trajectory generation method for autonomous overtaking of unexpected obstacles in a dynamic urban environment. In these settings, blind spots can arise from perception limitations. For example when overtaking unexpected objects on the vehicle's ego lane on a two-way street. In this case, a human driver would first make sure that the opposite lane is free and that there is enough room to successfully execute the maneuver, and then it would cut into the opposite lane in order to execute the maneuver successfully. We consider the practical problem of autonomous overtaking when the coverage of the perception system is impaired due to occlusion. Safe trajectories are generated by solving, in real-time, a non-linear constrained optimization, formulated as a receding horizon planner that maximizes the ego vehicle's visibility. The planner is complemented by a high-level behavior planner, which takes into account the occupancy of other traffic participants, the information from the vehicle's perception system, and the risk associated with the overtaking maneuver, to determine when the overtake maneuver should happen. The approach is validated in simulation and in experiments in real world traffic.

show abstract

“…It also converges fast and provided a solution for the majority of the challenges faced by different optimisers which include slow convergence and vanishing gradients. The Adam optimiser has been used in the design of a new gated branch neural network for an advanced driver assistance system [44] as well as been the most used optimiser in the recent DL model developments and has been used across diverse industrial applications [45,46].…”

Section: Adammentioning

confidence: 99%

Advances in Optimisation Algorithms and Techniques for Deep Learning

Nwankpa¹

2020

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

In the last decade, deep learning(DL) has witnessed excellent performances on a variety of problems, including speech recognition, object recognition, detection, and natural language processing (NLP) among many others. Of these applications, one common challenge is to obtain ideal parameters during the training of the deep neural networks (DNN). These typical parameters are obtained by some optimisation techniques which have been studied extensively. These research have produced state-of-art(SOTA) results on speed and memory improvements for deep neural networks(NN) architectures. However, the SOTA optimisers have continued to be an active research area with no compilations of the existing optimisers reported in the literature. This paper provides an overview of the recent advances in optimisation algorithms and techniques used in DNN, highlighting the current SOTA optimisers, improvements made on these optimisation algorithms and techniques, alongside the trends in the development of optimisers used in training DL based models. The results of the search of the Scopus database for the optimisers in DL provides the articles reported as the summary of the DL optimisers. From what we can tell, there is no comprehensive compilation of the optimisation algorithms and techniques so far developed and used in DL research and applications, and this paper summarises these facts.

show abstract

Gated branch neural network for mandatory lane changing suggestion at the on‐ramps of highway

Cited by 23 publications

References 22 publications

Deep Learning in Transport Studies: A Meta-analysis on the Prediction Accuracy

Deep Learning in Transport Studies: A Meta-analysis on the Prediction Accuracy

Trajectory Optimization and Situational Analysis Framework for Autonomous Overtaking With Visibility Maximization

Advances in Optimisation Algorithms and Techniques for Deep Learning

Contact Info

Product

Resources

About