Although deep learning techniques have been successfully implemented to solve domain-specific unmanned aerial vehicle planning problems, it is still a challenging task to develop a learning method to solve multidomain planning problems. Because the multidomain problems often involve learning more parameters, a dilated dataset diminishes learning speed due to its size and high dimensionality. The following two observations help tackle the issue: the state space of planning problems can be decomposed into representations of the domain state and system state, and the dimensionality problem often arises due to the huge size of the domain rather than system state. Inspired by such observations, this work presents a learning framework consisting of two networks: 1) a domain abstraction network in the form of a variational autoencoder that reduces the dimension of the domain space into a compact form, and 2) a planning network that generates a planning solution for a given domain setting. The effectiveness of the proposed learning framework is validated in case studies.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Domain-Abstraction-Based Approach for Learning Multidomain Planning


    Contributors:

    Published in:

    Publication date :

    2021-11-01




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Multidomain smart sensors [3698-50]

    Pollehn, H. K. / Ahearn, J. / SPIE | British Library Conference Proceedings | 1999


    Multidomain vertical alignment enhances LCDs

    British Library Online Contents | 1997


    Multidomain Joint Learning of Pedestrian Detection for Application to Quadrotors

    Yuan-Kai Wang / Jonathan Guo / Tung-Ming Pan | DOAJ | 2022

    Free access