Online learning of energy consumption for navigation of electric vehicles

DOI10.1016/J.ARTINT.2023.103879arXiv2111.02314OpenAlexW3209389588MaRDI QIDQ6157210FDOQ6157210

Authors: Niklas Åkerblom, Yuxin Chen, Morteza Haghir Chehreghani 

Publication date: 19 June 2023

Published in: Artificial Intelligence (Search for Journal in Brave)

Abstract: Energy efficient navigation constitutes an important challenge in electric vehicles, due to their limited battery capacity. We employ a Bayesian approach to model the energy consumption at road segments for efficient navigation. In order to learn the model parameters, we develop an online learning framework and investigate several exploration strategies such as Thompson Sampling and Upper Confidence Bound. We then extend our online learning framework to the multi-agent setting, where multiple vehicles adaptively navigate and learn the parameters of the energy model. We analyze Thompson Sampling and establish rigorous regret bounds on its performance in the single-agent and multi-agent settings, through an analysis of the algorithm under batched feedback. Finally, we demonstrate the performance of our methods via experiments on several real-world city road networks.

Full work available at URL: https://arxiv.org/abs/2111.02314

zbMATH Keywords

online learningmulti-armed banditsThompson samplingenergy efficient navigation

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Cites Work

• A note on two problems in connexion with graphs
• On a routing problem
• Efficient Algorithms for Shortest Paths in Sparse Networks
• Stochastic shortest path problems with recourse
• 10.1162/153244303321897663
• Batched bandit problems
• Combinatorial bandits
• Thompson sampling: an asymptotically optimal finite-time analysis
• Learning to optimize via posterior sampling
• A Tutorial on Thompson Sampling
• On Bayesian index policies for sequential resource allocation
• Online learning of network bottlenecks via minimax paths
• Consumption profiles in route planning for electric vehicles: theory and applications

Cited In (2)

• A unified framework for online trip destination prediction
• Distributed Charging Control of Electric Vehicles Using Online Learning

This page was built for publication: Online learning of energy consumption for navigation of electric vehicles

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6157210)