EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Socially Compatible and Risk-Aware Driving: A Cognition-Inspired Interactive Decision-Making Framework for Autonomous Vehicles

Jizhe Wang, Yahui Zhang, Takuji Arima, Kazumune Hashimoto, Xun Shen

IEEE Open Journal of Intelligent Transportation Systems · 2026 · 7 · 978-995

DOI: 10.1109/ojits.2026.3677078 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Open Journal of Intelligent Transportation Systems, 2026. Verfasst von Jizhe Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Society for the Promotion of Science (JSPS) through JSPS KAKENHI, Research Organization of Information and Systems through the Strategic Research Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In complex mixed traffic environments, where autonomous vehicles (AVs) are bound to interact frequently with human-driven vehicles (HDVs), the ability of AVs to exhibit risk-aware and socially compatible behaviors is essential to ensuring safety and efficiency. However, existing autonomous driving systems cannot effectively capture the social risk perception and driving preferences of human drivers, leading to misaligned interactions and potential safety hazards. This paper proposes a cognitively and socially grounded interactive decision-making framework for AVs that addresses these challenges. The architecture integrates a Traffic Situation Risk Field (TSRF) module, which assesses environmental risks by unifying heterogeneous risk sources from a social-cognitive perspective, and a Self-Correcting Game Decision-Making(SCGD) module that combines dynamic game theory with Bayesian inference to reason about the evolving driving styles of interacting vehicles and make suitable driving decisions. A model predictive control (MPC) planner then generates trajectories that respect both safety constraints and socially informed decision outcomes. Simulation and human-in-the-loop experiments demonstrate that the proposed framework enables AVs to adapt to diverse traffic participants, anticipate human behaviors, and execute socially coherent, interpretable maneuvers in highway lane-changing scenarios, significantly enhancing coordination and safety in mixed traffic.

Förderung

  • Japan Society for the Promotion of Science (JSPS) through JSPS KAKENHI
  • Research Organization of Information and Systems through the Strategic Research Project

Zitieren

APA

Wang, J., Zhang, Y., Arima, T., Hashimoto, K., & Shen, X. (2026). Socially Compatible and Risk-Aware Driving: A Cognition-Inspired Interactive Decision-Making Framework for Autonomous Vehicles. IEEE Open Journal of Intelligent Transportation Systems, 7, 978-995. https://doi.org/10.1109/ojits.2026.3677078

Vancouver

Wang J, Zhang Y, Arima T, Hashimoto K, Shen X. Socially Compatible and Risk-Aware Driving: A Cognition-Inspired Interactive Decision-Making Framework for Autonomous Vehicles. IEEE Open Journal of Intelligent Transportation Systems. 2026;7:978-995. doi:10.1109/ojits.2026.3677078

BibTeX
@article{Wang2026,
  author = {Wang, Jizhe and Zhang, Yahui and Arima, Takuji and Hashimoto, Kazumune and Shen, Xun},
  title = {Socially Compatible and Risk-Aware Driving: A Cognition-Inspired Interactive Decision-Making Framework for Autonomous Vehicles},
  journal = {IEEE Open Journal of Intelligent Transportation Systems},
  year = {2026},
  volume = {7},
  pages = {978--995},
  doi = {10.1109/ojits.2026.3677078}
}
Kostenlos starten →