Emergency Response Optimization Using Online Hybrid Planning
Abstract
This paper poses the planning problem faced by the dispatcher responding to urban emergencies as a Hybrid (Discrete and Continuous) State and Action Markov Decision Process (HSA-MDP). We evaluate the performance of three online planning algorithms based on hindsight optimization for HSA- MDPs on real-world emergency data in the city of Corvallis, USA. The approach takes into account and respects the policy constraints imposed by the emergency department. We show that our algorithms outperform a heuristic policy commonly used by dispatchers by significantly reducing the average response time as well as lowering the fraction of unanswered calls. Our results give new insights into the problem such as withholding of resources for future emergencies in some situations.
Cite
Text
Dayapule et al. "Emergency Response Optimization Using Online Hybrid Planning." International Joint Conference on Artificial Intelligence, 2018. doi:10.24963/IJCAI.2018/656Markdown
[Dayapule et al. "Emergency Response Optimization Using Online Hybrid Planning." International Joint Conference on Artificial Intelligence, 2018.](https://mlanthology.org/ijcai/2018/dayapule2018ijcai-emergency/) doi:10.24963/IJCAI.2018/656BibTeX
@inproceedings{dayapule2018ijcai-emergency,
title = {{Emergency Response Optimization Using Online Hybrid Planning}},
author = {Dayapule, Durga Harish and Raghavan, Aswin and Tadepalli, Prasad and Fern, Alan},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2018},
pages = {4722-4728},
doi = {10.24963/IJCAI.2018/656},
url = {https://mlanthology.org/ijcai/2018/dayapule2018ijcai-emergency/}
}