Abstract
Artificial intelligence (AI) planning models play an important role in decision support systems for disaster management e.g. typhoon contingency plan development. However, constructing an AI planning model always requires significant amount of manual effort, which becomes a bottleneck to emergency response in a time-critical situation. In this demonstration, we present a framework of automating a domain model of planning domain definition language from natural language input through deep learning techniques. We implement this framework in a typhoon response system and demonstrate automatic generation of typhoon contingency plan from official typhoon plan documents.
Original language | English |
---|---|
Title of host publication | AAMAS '21 |
Subtitle of host publication | Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems |
Editors | Ulle Endriss, Ann Nowé, Frank Dignum, Alessio Lomuscio |
Publisher | International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS) |
Pages | 1776-1778 |
Number of pages | 3 |
ISBN (Electronic) | 9781713832621 |
ISBN (Print) | 9781450383073 |
DOIs | |
Publication status | Published - 3 May 2021 |
Event | AAMAS 2021: 20th International Conference on Autonomous Agents and Multiagent Systems - Virtual, Southampton, United Kingdom Duration: 3 May 2021 → 7 May 2021 https://aamas2021.soton.ac.uk/ |
Publication series
Name | Proceedings of AAMAS |
---|---|
Publisher | International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS |
ISSN (Print) | 2523-5699 |
Conference
Conference | AAMAS 2021 |
---|---|
Country/Territory | United Kingdom |
City | Southampton |
Period | 3/05/21 → 7/05/21 |
Internet address |
Keywords
- Planning Domain Definition Language
- Natural Language Process
- Typhoon Contingency Plan