Proceedings of the 2017 International Seminar on Artificial Intelligence, Networking and Information Technology (ANIT 2017)

Trajectory Prediction using Conditional Generative Adversarial Network

Authors
Thibault Barbi,, Takeshi Nishida
Corresponding Author
Thibault Barbi,
Available Online December 2017.
DOI
10.2991/anit-17.2018.33How to use a DOI?
Keywords
Trajectory prediction, generative model, conditional generative adversarial networks.
Abstract

Optimization based planners (OBP) use a linear initialization as a prior of their optimizations which fails to use already acquired knowledge. Most of the time the linear initialization will collide with obstacles which will be the most difficult part of the OBP to optimize. We propose a method to perform trajectory prediction that leverages motion dataset by using a conditional generative adversarial network. Unlike previous methods, our proposed method does not require the dataset during execution time but instead generate new trajectories. We demonstrate the validity of our method on simulation. Our method decreases by 20% the number of colliding trajectories predicted compared to the linear initialization while being very fast.

Copyright
© 2018, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

Volume Title
Proceedings of the 2017 International Seminar on Artificial Intelligence, Networking and Information Technology (ANIT 2017)
Series
Advances in Intelligent Systems Research
Publication Date
December 2017
ISBN
978-94-6252-447-7
ISSN
1951-6851
DOI
10.2991/anit-17.2018.33How to use a DOI?
Copyright
© 2018, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Cite this article

TY  - CONF
AU  - Thibault Barbi,
AU  - Takeshi Nishida
PY  - 2017/12
DA  - 2017/12
TI  - Trajectory Prediction using Conditional Generative Adversarial Network
BT  - Proceedings of the 2017 International Seminar on Artificial Intelligence, Networking and Information Technology (ANIT 2017)
PB  - Atlantis Press
SP  - 193
EP  - 197
SN  - 1951-6851
UR  - https://doi.org/10.2991/anit-17.2018.33
DO  - 10.2991/anit-17.2018.33
ID  - Barbi,2017/12
ER  -