Natural criteria for comparison of pedestrian flow forecasting models

Vintr, Tomas, Yan, Zhi, Eyisoy, Kerem , Kubis, Filip, Blaha, Jan, Ulrich, Jiri, Swaminathan, Chittaranjan, Molina Mellado, Sergio, Kucner, Tomasz, Magnusson, Martin, Cielniak, Grzegorz, Faigl, Jan, Duckett, Tom, Lilienthal, Achim and Krajnik, Tomas (2021) Natural criteria for comparison of pedestrian flow forecasting models. 2020 IEEE/RJS International Conference on Intelligent Robots and Systems (IROS) . pp. 11197-11204. ISSN 2153-0858

Full content URL:

Natural criteria for comparison of pedestrian flow forecasting models
Authors' Accepted Manuscript
Natural-Criteria-for-Comparison-of-Pedestrian-Flow-Forecasting-Models.pdf - Whole Document

Item Type:Article
Item Status:Live Archive


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-theart 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.

Keywords:Mobile robotics, Autonomous robots, Pedestrian Model, Human-Aware Robot Navigation
Subjects:G Mathematical and Computer Sciences > G440 Human-computer Interaction
G Mathematical and Computer Sciences > G400 Computer Science
G Mathematical and Computer Sciences > G761 Automated Reasoning
Divisions:College of Science > School of Computer Science
ID Code:48928
Deposited On:11 Apr 2022 13:18

Repository Staff Only: item control page