Abstract
Autonomous vehicles (AVs) must share space with pedestrians, both in carriageway cases such as cars at pedestrian crossings and off-carriageway cases such as delivery vehicles navigating through crowds on pedestrianized high-streets. Unlike static obstacles, pedestrians are active agents with complex, interactive motions. Planning AV actions in the presence of pedestrians thus requires modelling of their probable future behavior as well as detecting and tracking them. This narrative review article is Part II of a pair, together surveying the current technology stack involved in this process, organising recent research into a hierarchical taxonomy ranging from low-level image detection to high-level psychological models, from the perspective of an AV designer. This self-contained Part II covers the higher levels of this stack, consisting of models of pedestrian behavior, from prediction of individual pedestrians' likely destinations and paths, to game-theoretic models of interactions between pedestrians and autonomous vehicles. This survey clearly shows that, although there are good models for optimal walking behavior, high-level psychological and social modelling of pedestrian behavior still remains an open research question that requires many conceptual issues to be clarified. Early work has been done on descriptive and qualitative models of behavior, but much work is still needed to translate them into quantitative algorithms for practical AV control.
Original language | English |
---|---|
Article number | 9151337 |
Pages (from-to) | 5453-5472 |
Number of pages | 20 |
Journal | IEEE Transactions on Intelligent Transportation Systems |
Volume | 22 |
Issue number | 9 |
Early online date | 28 Jul 2020 |
DOIs | |
Publication status | Published - Sept 2021 |
Bibliographical note
Funding Information:Manuscript received October 21, 2019; revised March 26, 2020; accepted April 9, 2020. This work was supported by the EU H2020 interACT under Grant 723395. The Associate Editor for this article was S. A. Birrell. (Corresponding author: Fanta Camara.) Fanta Camara is with the Institute for Transport Studies (ITS), University of Leeds, Leeds LS2 9JT, U.K., and also with the Lincoln Centre for Autonomous Systems, University of Lincoln, Lincoln LN6 7TS, U.K. (e-mail: [email protected]). Nicola Bellotto is with the Lincoln Centre for Autonomous Systems, University of Lincoln, Lincoln LN6 7TS, U.K. Serhan Cosar is with the Institute of Engineering Sciences, De Montfort University, Leicester LE1 9BH, U.K. Florian Weber is with Bayerische Motoren Werke Aktiengesellschaft (BMW), 80809 Munich, Germany. Dimitris Nathanael is with the School of Mechanical Engineering, National Technical University of Athens, 15780 Athens, Greece. Matthias Althoff is with the Department of Computer Science, Technische Universität München, 85748 Garching bei München, Germany. Jingyuan Wu and Johannes Ruenz are with Robert Bosch GmbH, 74232 Abstatt, Germany. André Dietrich is with the Chair of Ergonomics, Technische Universität München (TUM), 85748 Garching bei München, Germany. Gustav Markkula and Natasha Merat are with the Institute for Transport Studies (ITS), University of Leeds, Leeds LS2 9JT, U.K. Anna Schieben is with the German Aerospace Center (DLR), 38108 Brunswick, Germany. Fabio Tango is with the Centro Ricerche Fiat (CRF), 10043 Orbassano, Italy. Charles Fox is with the Institute for Transport Studies (ITS), University of Leeds, Leeds LS2 9JT, U.K., also with the Lincoln Centre for Autonomous Systems, University of Lincoln, Lincoln LN6 7TS, U.K., and also with Ibex Automation Ltd., Sheffield S36 8YW, U.K. This article has supplementary downloadable material available at http://ieeexplore.ieee.org, provided by the authors. Digital Object Identifier 10.1109/TITS.2020.3006767
Publisher Copyright:
© 2000-2011 IEEE.
Keywords
- autonomous vehicles
- datasets
- detection
- eHMI
- game-theoretic models
- microscopic and macroscopic behavior models
- pedestrian interaction
- pedestrians
- Review
- sensing
- signalling models
- survey
- tracking
- trajectory prediction