TY - GEN
T1 - Goal Recognition in Latent Space
AU - Amado, Leonardo
AU - Pereira, Ramon Fraga
AU - Aires, Joao
AU - Magnaguagno, Mauricio
AU - Granada, Roger
AU - Meneguzzi, Felipe
N1 - Funding Information:
Felipe thanks CNPq for partial financial support under its PQ fellowship, grant number 305969/2016-1.
Publisher Copyright:
© 2018 IEEE.
PY - 2018/10/10
Y1 - 2018/10/10
N2 - Recent approaches to goal recognition have progressively relaxed the requirements about the amount of domain knowledge and available observations, yielding accurate and efficient algorithms. These approaches, however, assume that there is a domain expert capable of building complete and correct domain knowledge to successfully recognize an agent's goal. This is too strong for most real-world applications. We overcome these limitations by combining goal recognition techniques from automated planning, and deep autoencoders to carry out unsupervised learning to generate domain theories from data streams and use the resulting domain theories to deal with incomplete and noisy observations. We show the effectiveness of the technique in a number of domains and compare the recognition effectiveness of the autoencoded against hand-coded versions of these domains.
AB - Recent approaches to goal recognition have progressively relaxed the requirements about the amount of domain knowledge and available observations, yielding accurate and efficient algorithms. These approaches, however, assume that there is a domain expert capable of building complete and correct domain knowledge to successfully recognize an agent's goal. This is too strong for most real-world applications. We overcome these limitations by combining goal recognition techniques from automated planning, and deep autoencoders to carry out unsupervised learning to generate domain theories from data streams and use the resulting domain theories to deal with incomplete and noisy observations. We show the effectiveness of the technique in a number of domains and compare the recognition effectiveness of the autoencoded against hand-coded versions of these domains.
UR - http://www.scopus.com/inward/record.url?scp=85056490326&partnerID=8YFLogxK
U2 - 10.1109/IJCNN.2018.8489653
DO - 10.1109/IJCNN.2018.8489653
M3 - Published conference contribution
AN - SCOPUS:85056490326
T3 - Proceedings of the International Joint Conference on Neural Networks
BT - 2018 International Joint Conference on Neural Networks, IJCNN 2018 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 International Joint Conference on Neural Networks, IJCNN 2018
Y2 - 8 July 2018 through 13 July 2018
ER -