Modelling communication-enabled traffic interactions
DOI: 10.1098/rsos.230537
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This paper addresses the challenge of modeling reciprocal traffic interactions between autonomous vehicles (AVs) and human-driven vehicles, specifically in scenarios like highway merging. Existing models often rely on a "one-way interaction" assumption, where one driver responds to another without influencing them, or utilize game theory, which assumes rational utility maximization, discrete actions, and no communication. The authors argue these approaches fail to capture the continuous, communicative, and bounded-rational nature of human driving. To address this, they propose a Communication-Enabled Interaction (CEI) modeling framework that treats the interaction as a joint system, explicitly incorporating communication and bounded rationality. The CEI framework models each driver using four components: a deterministic plan for future actions, a probabilistic belief about the other driver’s behavior, a means of communication (implicit or explicit), and a risk-based re-planning mechanism. Drivers are assumed to act with bounded rationality, maintaining their current plan as long as the perceived risk—derived from their plan and belief about the other driver—remains below a personal threshold. Communication links one driver’s plan to the other’s belief, allowing for dynamic updates. The authors demonstrate this framework through a simulation case study of a simplified merging scenario involving two vehicles. The simulation environment defines specific track dimensions and vehicle dynamics, with the model controlling vehicle accelerations directly. The results from the merging scenario simulation show that the CEI model generates plausible interactive behaviors, including both aggressive and conservative merging strategies, depending on the drivers' risk thresholds. Drivers with lower risk thresholds adapted their plans earlier to reduce estimated risk, while those with higher thresholds maintained their plans, effectively modeling aggressive behavior. Additionally, in a car-following scenario, human-like gap-keeping behavior emerged naturally from the model’s risk perception mechanism, without explicitly programming time or distance gaps. This indicates that the framework can replicate complex operational dynamics solely through risk-based decision-making and communication. The significance of this work lies in providing a more realistic computational framework for modeling human-vehicle interactions. By relaxing the strict assumptions of game theory and incorporating communication and bounded rationality, the CEI framework offers a promising approach for developing interaction-aware autonomous vehicles. This could lead to AVs that negotiate traffic scenarios more safely and acceptably by better understanding and responding to human drivers' implicit and explicit communications. The study suggests that modeling the joint interactive system, rather than isolated drivers, is crucial for advancing autonomous driving technologies in complex, reciprocal traffic environments.
Key finding
The proposed communication-enabled-interaction framework successfully generates plausible reciprocal driving behaviors and emergent gap-keeping through risk-based decision-making and communication in simulated merging and car-following scenarios.
Methodology
simulation_modeling
Provenance
The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed. Discovered via openalex_abstract on 2026-05-08.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | — | — | — | 1 | 2026-05-07 |
| archive | success | canonical_url | — | — | 12 | 2026-06-06 |
| extract | success | cached | — | — | 3 | 2026-06-10 |
| clean | success | clean | — | — | 1 | 2026-06-04 |
| chunk | success | chunk | — | — | 1 | 2026-06-04 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-04 |
| enrich | success | openalex | — | — | 2 | 2026-05-08 |
| promote | success | — | — | — | 1 | 2026-05-07 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 2 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 15 | 2026-06-11 |
| verify | success | — | — | — | 2 | 2026-06-10 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
Information type
What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).
- Theoretical Contribution: computational model, theory or model