InfoSalGAIL: Visual Attention-empowered Imitation Learning of Pedestrian Behavior in Critical Traffic Scenarios

Igor Vozniak, Matthias Klusch, André Antakli, Christian Müller

2020

Abstract

The imitation learning of complex pedestrian behavior based on visual input is a challenge due to the underlying large state space and variations. In this paper, we present a novel visual attention-based imitation learning framework, named InfoSalGAIL, for end-to-end imitation learning of (safe, unsafe) pedestrian navigation policies through visual expert demonstrations empowered by eye fixation sequence and augmented reward function. This work shows the relation in latent space between the policy estimated trajectories and visual-attention map. Moreover, the conducted experiments revealed that InfoSalGAIL can significantly outperform the state-of-the-art baseline InfoGAIL. In fact, its visual attention-empowered imitation learning tends to much better generalize the overall policy of pedestrian behavior leveraging apprenticeship learning to generate more human-like pedestrian trajectories in virtual traffic scenes with the open source driving simulator OpenDS. InfoSalGAIL can be utilized in the process of generating and validating critical scenarios for adaptive driving assistance systems.

Paper Citation

in Harvard Style

Vozniak I., Klusch M., Antakli A. and Müller C. (2020). InfoSalGAIL: Visual Attention-empowered Imitation Learning of Pedestrian Behavior in Critical Traffic Scenarios. In Proceedings of the 12th International Joint Conference on Computational Intelligence (IJCCI 2020) - Volume 1: NCTA; ISBN 978-989-758-475-6, SciTePress, pages 325-337. DOI: 10.5220/0010020003250337

in Bibtex Style

@conference{ncta20,
author={Igor Vozniak and Matthias Klusch and André Antakli and Christian Müller},
title={InfoSalGAIL: Visual Attention-empowered Imitation Learning of Pedestrian Behavior in Critical Traffic Scenarios},
booktitle={Proceedings of the 12th International Joint Conference on Computational Intelligence (IJCCI 2020) - Volume 1: NCTA},
year={2020},
pages={325-337},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010020003250337},
isbn={978-989-758-475-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Joint Conference on Computational Intelligence (IJCCI 2020) - Volume 1: NCTA
TI - InfoSalGAIL: Visual Attention-empowered Imitation Learning of Pedestrian Behavior in Critical Traffic Scenarios
SN - 978-989-758-475-6
AU - Vozniak I.
AU - Klusch M.
AU - Antakli A.
AU - Müller C.
PY - 2020
SP - 325
EP - 337
DO - 10.5220/0010020003250337
PB - SciTePress