Natural Criteria for Comparison of Pedestrian Flow Forecasting Models

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F20%3A00347506" target="_blank" >RIV/68407700:21230/20:00347506 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/IROS45743.2020.9341672" target="_blank" >https://doi.org/10.1109/IROS45743.2020.9341672</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/IROS45743.2020.9341672" target="_blank" >10.1109/IROS45743.2020.9341672</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Natural Criteria for Comparison of Pedestrian Flow Forecasting Models

Popis výsledku v původním jazyce

Models of human behaviour, such as pedestrian flows, are beneficial for safe and efficient operation of mobile robots. We present a new methodology for benchmarking of pedestrian flow models based on the afforded safety of robot navigation in human-populated environments. While previous evaluations of pedestrian flow models focused on their predictive capabilities, we assess their ability to support safe path planning and scheduling. Using real-world datasets gathered continuously over several weeks, we benchmark state-of-the-art pedestrian flow models, including both time-averaged and time-sensitive models. In the evaluation, we use the learned models to plan robot trajectories and then observe the number of times when the robot gets too close to humans, using a predefined social distance threshold. The experiments show that while traditional evaluation criteria based on model fidelity differ only marginally, the introduced criteria vary significantly depending on the model used, providing a natural interpretation of the expected safety of the system. For the time-averaged flow models, the number of encounters increases linearly with the percentage operating time of the robot, as might be reasonably expected. By contrast, for the time-sensitive models, the number of encounters grows sublinearly with the percentage operating time, by planning to avoid congested areas and times.

Název v anglickém jazyce

Natural Criteria for Comparison of Pedestrian Flow Forecasting Models

Popis výsledku anglicky

Models of human behaviour, such as pedestrian flows, are beneficial for safe and efficient operation of mobile robots. We present a new methodology for benchmarking of pedestrian flow models based on the afforded safety of robot navigation in human-populated environments. While previous evaluations of pedestrian flow models focused on their predictive capabilities, we assess their ability to support safe path planning and scheduling. Using real-world datasets gathered continuously over several weeks, we benchmark state-of-the-art pedestrian flow models, including both time-averaged and time-sensitive models. In the evaluation, we use the learned models to plan robot trajectories and then observe the number of times when the robot gets too close to humans, using a predefined social distance threshold. The experiments show that while traditional evaluation criteria based on model fidelity differ only marginally, the introduced criteria vary significantly depending on the model used, providing a natural interpretation of the expected safety of the system. For the time-averaged flow models, the number of encounters increases linearly with the percentage operating time of the robot, as might be reasonably expected. By contrast, for the time-sensitive models, the number of encounters grows sublinearly with the percentage operating time, by planning to avoid congested areas and times.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2020 IEEE/RSJ International Conference on Intelligent Robots and Systems

ISBN

978-1-7281-6212-6

ISSN

2153-0858

e-ISSN

2153-0866

Počet stran výsledku

8

Strana od-do

11197-11204

Název nakladatele

IEEE Robotics and Automation Society

Místo vydání

Piscataway

Místo konání akce

Las Vegas

Datum konání akce

25. 10. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—