Abstract
Artificial intelligence planning techniques have been widely used in many applications. A big challenge is to automate a planning model, especially for planning applications based on natural language (NL) input. This requires the analysis and understanding of NL text and a general learning technique does not exist in real-world applications. In this article, we investigate an intelligent planning technique for natural disaster management, e.g. typhoon contingency plan generation, through natural language process manuals. A planning model is to optimise management operations when a disaster occurs in a short time. Instead of manually building the planning model, we aim to automate the planning model generation by extracting disaster management-related content through NL processing (NLP) techniques. The learning input comes from the published documents that describe the operational process of preventing potential loss in the typhoon management. We adopt a classical planning model, namely planning domain definition language (PDDL), in the typhoon contingency plan generation. We propose a novel framework of FPTCP, which stands for a Framework of Planning Typhoon Contingency Plan, for learning a domain model of PDDL from NL text. We adapt NLP techniques to construct a ternary template of sentences of NL inputs from which actions and their objects are extracted to build a domain model. We also develop a comprehensive suite of user interaction components and facilitate the involvement of users in order to improve the learned domain models. The user interaction is to remove semantic duplicates of NL objects such that the users can select model-generated actions and predicates to better fit the PDDL domain model. We detail the implementation steps of the proposed FPTCP and evaluate its performance on real-world typhoon datasets. In addition, we compare FPTCP with two state-of-the-art approaches in applications of narrative generation, and discuss its capability and limitations.
Highlights
A RTIFICIAL intelligence (AI) planning techniques are increasingly playing a supporting role in the society from our daily life to public operations where decisions or policies need to be made in a complex environment
Instead of manually crafting the domain file, we aim to automate the domain file specification given the input of natural language (NL) text, which is coined as the domain learning in a planning domain definition language (PDDL) model
In the left-hand side, a set of 11 actions are generated by the obtained domain model while in the right-hand side, we show the original inputs of the NL sentences
Summary
A RTIFICIAL intelligence (AI) planning techniques are increasingly playing a supporting role in the society from our daily life to public operations where decisions or policies need to be made in a complex environment. A number of AI planning techniques have been developed in the past of several decades since they are the core where AI origins. They are ranged from a classical logicbased AI planner e.g. STanford Research Institute Problem Solver (STRIPS) [7], belief models for dealing with observational uncertainty e.g. partially observable Markov decision process [8], to more explicit representations of probabilistic graphical models e.g. influence diagrams, interactive dynamic influence diagrams and so on [9]. The PDDL model gives the syntax of the planning problem definition, and gives the definition of the planning from a semantic perspective. It has a strong expression ability and can describe time and numerical attributes in the planning problem
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
