Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Automation and Machine Learning
  4. Vol 7, Issue 2, 2026

Interaction Behavior Characteristics between Autonomous Vehicles and Pedestrians: A Lag Sequential Analysis Approach

Download as PDF

DOI: 10.23977/autml.2026.070201 | Downloads: 3 | Views: 114

Author(s)

Yu Quan 1, Song Shujian 1

Affiliation(s)

1 School of Electrical and Control Engineering, North China University of Technology, Beijing, China

Corresponding Author

Song Shujian

ABSTRACT

In urban mixed traffic scenarios, interactions between autonomous vehicles and pedestrians exhibit high randomness and strategic diversity, making it challenging to derive interpretable sequential evidence of behavioral characteristics through instantaneous metrics. This paper proposes a micro-level interaction behavior feature extraction method based on Lag Sequential Analysis (LSA). This study constructs vehicle–pedestrian interaction samples based on the nuScenes autonomous driving dataset, extracting valid interaction segments under constraints of an interaction distance threshold of 30 m and conflict screening criteria. Continuous motion trajectories of vehicles and pedestrians are discretized into behavioral state codes, forming single-channel interaction event sequences. Adjusted Residuals (ADJR) are computed under first-order lag conditions to test the statistical significance of state transitions, identifying stable, significant transition paths and behavioral chain structures. Results demonstrate significant sequence dependencies between stable vehicle driving and pedestrian decisions such as "approach/pause." Interaction processes can be categorized into behavioral characteristics including intent uncertainty, risk aversion, efficiency orientation, and dynamic right-of-way negotiation, revealing stable, significant transition chains such as "vehicle confirmation—accelerated passage" and "pedestrian wait—vehicle passage." The identified significant behavioral chains provide interpretable, testable quantitative evidence supporting the expression of interactive intent, pedestrian behavior prediction, and autonomous driving planning decisions.

KEYWORDS

Autonomous vehicles, Pedestrians, Interactive behavior, Traffic conflicts, Lag Sequential Analysis

CITE THIS PAPER

Yu Quan, Song Shujian. Interaction Behavior Characteristics between Autonomous Vehicles and Pedestrians: A Lag Sequential Analysis Approach. Automation and Machine Learning (2026). Vol. 7, No. 2, 1-8. DOI: http://dx.doi.org/10.23977/autml.2026.070201.

REFERENCES

[1] Markkula G., Madigan R., Nathanael D., et al. Defining interactions: a conceptual framework for understanding interactive behaviour in human and automated road traffic[J].Theoretical Issues in Ergonomics Science, 2020, 21(3).DOI:10.1080/1463922X.2020.1736686.
[2] Rezwana S., Lownes N. Interactions and Behaviors of Pedestrians with Autonomous Vehicles: A Synthesis[J].Future Transportation, 2024, 4(3):722-745. DOI:10.3390/futuretransp4030034.
[3] Lee Y M., Madigan R., Giles O., et al. Road users rarely use explicit communication when interacting in today's traffic: Implications for Automated Vehicles[J].Cognition Technology and Work, 2020(9).DOI:10.1007/s10111-020-00635-y.
[4] Sripada A., Bazilinskyy P., Winter J D. Automated Vehicles that Communicate Implicitly: Examining the use of Lateral Position Within the Lane[J]. Ergonomics, 2021:1-15. DOI:10.1080/00140139.2021.1925353.
[5] Saha A., Labeye E., Caroux L., et al. Crossing the street in front of an autonomous vehicle: An investigation of eye contact between drivengers and vulnerable road users[J]. Frontiers in psychology, 2022, 13:981666. DOI:10.3389/fpsyg.2022.981666.
[6] Zou F., Ogle J., Jin W., et al. Pedestrian behavior interacting with autonomous vehicles during unmarked midblock multilane crossings: Role of infrastructure design, AV operations and signaling[J]. Transportation research, Part F. Traffic psychology and behaviour, 2024, 100(Jan.):84-100. DOI:10.1016/j.trf.2023.11.003.
[7] Hyden C., Linderholm L. The Swedish Traffic-Conflicts Technique[J]. Springer Berlin Heidelberg, 1984. DOI:10.1007/978-3-642-82109-7_12.
[8] Tarko A., Davis G A., Saunier N., et al. Surrogate Measures of Safety[J]. Safety Engineering, 2009. DOI:10.1016/b978-0-08-102671-7.10197-6.
[9] Singh D., Das P. A Review on Surrogate Safety Measures in Safety Evaluation and Analysis[J]. Springer, Singapore, 2023. DOI:10.1007/978-981-19-4204-4_7.
[10] Sackett G P. (Ed). Observing Behavior: Theory and applications in mental retardation (Vol. 1) [M]. Baltimore: University Park Press, 1978.
[11] Caesar H., Bankiti V., Lang A H., et al. nuScenes: A multimodal dataset for autonomous driving[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 11621-11631. DOI:10.1109/CVPR42600.2020.01164.
[12] Bakeman R., Quera V. Analyzing interaction: Sequential analysis with SDIS and GSEQ[M]. Cambridge: Cambridge University Press, 1995.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 5361
Visits: 273442

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.