TY  - GEN
AB  - 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.
AD  - Volvo Car Corporation
AD  - University of Chicago
AD  - Chalmers University of Technology
AU  - Åkerblom, Niklas
AU  - Chen, Yuxin
AU  - Chehreghani, Morteza Haghir
DA  - 2023-02-13
ID  - 5523
JF  - Artificial Intelligence
KW  - Energy efficient navigation
KW  - Online learning
KW  - Multi-armed bandits
KW  - Thompson Sampling
L1  - https://knowledge.uchicago.edu/record/5523/files/Online-learning-of-energy-consumption.pdf
L2  - https://knowledge.uchicago.edu/record/5523/files/Online-learning-of-energy-consumption.pdf
L4  - https://knowledge.uchicago.edu/record/5523/files/Online-learning-of-energy-consumption.pdf
LA  - eng
LK  - https://knowledge.uchicago.edu/record/5523/files/Online-learning-of-energy-consumption.pdf
N2  - 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.
PY  - 2023-02-13
T1  - Online learning of energy consumption for navigation of electric vehicles
TI  - Online learning of energy consumption for navigation of electric vehicles
UR  - https://knowledge.uchicago.edu/record/5523/files/Online-learning-of-energy-consumption.pdf
Y1  - 2023-02-13
ER  -