Agile Planning for Real-World Disaster Response
Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 132-137.
Abstract
We consider a setting where an agent-based planner instructs teams of human emergency responders to perform tasks in the real world. Due to uncertainty in the environment and the inability of the planner to consider all human preferences and all attributes of the real-world, humans may reject plans computed by the agent. A naive solution that re-plans given a rejection is inefficient and does not guarantee the new plan will be acceptable. Hence, we propose a new model re-planning problem using a Multi-agent Markov Decision Process that integrates potential rejections as part of the planning process and propose a novel algorithm to efficiently solve this new model. We empirically evaluate our algorithm and show that it outperforms current benchmarks. Our algorithm is also shown to perform better in pilot studies with real humans.
@inproceedings{ijcai2015p26,
title = {Agile Planning for Real-World Disaster Response},
author = {Wu, Feng and Ramchurn, Sarvapali D. and Jiang, Wenchao and Fischer, Joel E. and Rodden, Tom and Jennings, Nicholas R.},
booktitle = {Proceedings of the Twenty-Fourth International Joint Conference on
Artificial Intelligence, {IJCAI-15}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Qiang Yang and Michael Wooldridge},
pages = {132--137},
year = {2015},
month = {7},
note = {Main Track},
url = {https://ijcai.org/proceedings/2015/26},
}
TY - CPAPER TI - Agile Planning for Real-World Disaster Response AU - Wu, Feng AU - Ramchurn, Sarvapali D. AU - Jiang, Wenchao AU - Fischer, Joel E. AU - Rodden, Tom AU - Jennings, Nicholas R. T2 - Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-15 PB - International Joint Conferences on Artificial Intelligence PY - 2015 SP - 132 EP - 137 UR - https://ijcai.org/proceedings/2015/26 ER -Copied
Machine-readable versions of this paper, for tools and AI agents: