• Corpus ID: 220265414

Deep Learning Based Anticipatory Multi-Objective Eco-Routing Strategies for Connected and Automated Vehicles

@article{Alfaseeh2020DeepLB,
  title={Deep Learning Based Anticipatory Multi-Objective Eco-Routing Strategies for Connected and Automated Vehicles},
  author={Lama Alfaseeh and Bilal Farooq},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.16472}
}
This study exploits the advancements in information and communication technology (ICT), connected and automated vehicles (CAVs), and sensing, to develop anticipatory multi-objective eco-routing strategies. For a robust application, several GHG costing approaches are examined. The predictive models for the link level traffic and emission states are developed using long short term memory deep network with exogenous predictors. It is found that anticipatory routing strategies outperformed the… 
View PDF on arXiv

References

SHOWING 1-10 OF 57 REFERENCES

Greenhouse Gas Emission Prediction on Road Network using Deep Sequence Learning

Multi-objective Eco-routing in a Distributed Routing Framework

Routing to optimize TT while adopting higher level of spatial and temporal resolution is the best among the single objective routing scenarios and multi-objective routing strategies reduced TT, GHG, and NOx when comparing to routing solely based on TT.

Multi-Objective Eco-Routing for Dynamic Control of Connected & Automated Vehicles

Analyzing the Impact of Anticipatory Vehicle Routing on the Network Performance

Link speed prediction for signalized urban traffic network using a hybrid deep learning approach

This work proposes a hybrid deep-learning-based approach for link speed prediction, aiming at capturing heterogeneous spatiotemporal correlations between road intersections, which leverages a layered graph convolution network structure to model traffic speed variations at both intersection and road network levels.

Dynamic collective routing using crowdsourcing data

Proactive Vehicular Traffic Rerouting for Lower Travel Time

Five traffic rerouting strategies designed to be incorporated in a cost-effective and easily deployable vehicular traffic guidance system that reduces travel time are presented and can significantly improve the traffic even if many drivers ignore the guidance or if the system adoption rate is relatively low.

Short-term prediction of lane-level traffic speeds: A fusion deep learning model

Real-time route diversion control in a model predictive control framework with multiple objectives: Traffic efficiency, emission reduction and fuel economy

Multi-Factor Taxonomy of Eco-Routing Models and Future Outlook

This research work is aimed at providing a three-factor taxonomy at a more disaggregated level from the optimization perspective and map eco-routing studies to the proposed taxonomy.
...