Authors:
Patrick Malcolm, Georgios Grigoropoulos, Andreas Keler, Klaus Bogenberger
Keywords:
pedestrian, simulation, crowdsourcing, turing test
Abstract:
Malcolm P.; Grigoropoulos G.; Keler A. and Bogenberger K. Crowdsourced Qualitative Evaluation of Pedestrian Movement Models In: Proceedings of the Driving Simulation Conference 2021 Europe VR, Driving Simulation Association, Munich, Germany, 2021, pp. 167-172
Download .txt file
@inproceedings{Malcolm2021,
title = {Crowdsourced Qualitative Evaluation of Pedestrian Movement Models},
author = {Patrick Malcolm and Georgios Grigoropoulos and Andreas Keler and Klaus Bogenberger},
editor = {Andras Kemeny and Jean-Rémy Chardonnet and Florent Colombet},
year = {2021},
date = {2021-09-14},
booktitle = {Proceedings of the Driving Simulation Conference 2021 Europe VR},
pages = {167-172},
address = {Munich, Germany},
organization = {Driving Simulation Association},
abstract = {In driving simulator studies, it is crucial to provide a highly realistic virtual environment in order to allow for the study participants to immerse themselves more fully, which in turn provides for more realistic driver behavior. In studies involving interaction with pedestrians, this means providing realistic pedestrian behavior, which can be achieved in one of three ways: by recording pedestrian movements in the real world and playing these back in the simulation environment, by manually animating the behavior of each pedestrian, or by using a pedestrian movement model to simulate behavior. Each of these approaches has its own advantages and drawbacks, but it is clear that in order to simulate larger amounts of pedestrians in scenarios for which there is no physical analog, realistic pedestrian movement models are crucial. However, most evaluations of pedestrian models focus on macroscopic effects, such as flow rates through a bottleneck, or on their ability to reproduce certain empirically observed emergent phenomena. What is often ignored in such evaluations is the perceived realism imparted by the model at the level of an individual pedestrian, and whether humans are able to differentiate between said models and real pedestrian behavior in a driving-simulator-like environment. In order to address this issue, we propose a highly automatable methodology which leverages the power of crowdsourcing to quickly and cheaply evaluate the perceived realism of various pedestrian models, as well as the impact of their various parameters on the achieved realism. The methodology consists of generating short video clips from a 3D rendered scene, using Unity as the visualization engine, in which the movements of various pedestrians are controlled by either a model with a given set of parameters or played back from a real-world recorded trajectory. In an exercise analogous to a classical Turing Test, survey participants are shown the videos and asked to rate the realism of the displayed pedestrian behavior. The participants’ ratings of the respective real and simulated videos are then compared in order to arrive at a qualitative measure of how convincing the pedestrian behavior generated by the model is. We then perform a small proof-of-concept study applying the described methodology, present some preliminary results, and list a number of areas for future research and improvement.},
keywords = {crowdsourcing, pedestrian, simulation, turing test},
}
Download .bib file
TY - CONF
TI - Crowdsourced Qualitative Evaluation of Pedestrian Movement Models
AU - Malcolm, Patrick
AU - Grigoropoulos, Georgios
AU - Keler, Andreas
AU - Bogenberger, Klaus
C1 - Munich, Germany
C3 - Proceedings of the Driving Simulation Conference 2021 Europe VR
DA - 2021/09/14
PY - 2021
SP - 167
EP - 172
LA - en-US
PB - Driving Simulation Association
L2 - https://proceedings.driving-simulation.org/proceeding/dsc-2021/crowdsourced-qualitative-evaluation-of-pedestrian-movement-models
ER -
Download .ris file
Cite this article
Terms and Conditions for Downloading Driving Simulation Proceedings papers:
By downloading a scientific paper from proceedings.driving-simulation.org, you agree to the following terms and conditions:
- Personal Use Only:
The scientific paper provided on this website is solely for personal, educational, and non-commercial use. You may download and use the paper for your own reference and research purposes only.
- No Reproduction or Distribution:
You may not reproduce, distribute, transmit, publish, or otherwise make the paper available to any third party in any form, whether for commercial or non-commercial purposes, without the express written consent of the Driving Simulation Association.
- Copyright and Ownership:
The scientific paper is protected by copyright laws and is the intellectual property of the respective authors and publishers. All rights not expressly granted herein are reserved.
- Citation and Attribution:
If you use the scientific paper for research, presentations, or any other non-commercial purposes, you must provide appropriate citation and attribution to the original authors as per academic standards.
- No Modification:
You may not modify, alter, or adapt the content of the scientific paper in any way.
- Disclaimer:
The Driving Simulation Association makes no representations or warranties regarding the accuracy, completeness, or suitability of the scientific paper for any particular purpose. The paper is provided as-is, without any warranties, express or implied. The Driving Simulation Association reserves the right to terminate or restrict access to the scientific paper at any time and without notice.