PLANNING AND COORDINATION IN DRIVING SIMULATION
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 presents an overview of planning and coordination mechanisms developed for the AgentDrive simulation platform, specifically focusing on its integration with the OpenDS driving simulator. The research is motivated by the need to evaluate advanced driver assistance systems (ADAS) and autonomous driving concepts before real-world deployment, as physical experiments are costly and verification of complex multi-agent traffic systems is difficult. The integration aims to combine AgentDrive’s agent-based coordination capabilities with OpenDS’s physics simulation and human-in-the-loop features, allowing researchers to study human factors, traffic efficiency, and automated driving in a realistic environment. The simulation platform architecture integrates several components: OpenDS provides the 3D visualization, physical simulation, and human driver interface, while AgentDrive handles traffic generation using OpenStreetMap data, mobility demand modeling, and multi-agent coordination. The platform supports various study categories, including traffic studies (analyzing global flow based on local behavior), human factors studies (evaluating driver acceptance and stress via external sensors), connected car studies (utilizing V2V/V2I communication for cooperative protocols), and autonomous driving studies (simulating mixed traffic scenarios with human and driver-less vehicles). The paper details specific planning and coordination applications implemented within this framework. For routing and navigation, the system uses Dijkstra’s or A* algorithms on road network graphs, with edge weights adjusted for real-time traffic conditions to enable online rerouting. For ADAS, the authors developed Cooperative Adaptive Cruise Control and Lane Change Assist systems for highway driving, employing a "Safe-Distance" method that advises drivers on speed or lane changes to maintain safety; results indicated decreased cognitive load for assisted drivers. Local coordination algorithms include reactive mechanisms like Safe-Distance for collision avoidance and the Optimized Reciprocal Collision Avoidance (ORCA) algorithm, which improves road capacity utilization but lacks lane compliance, making it less predictable for human drivers. Additionally, the paper discusses junction coordination using generalized Safe-Distance methods and Asynchronous Decentralized Prioritized Planning (ADPP) to manage collision-free passing without centralized traffic lights. Cooperative techniques such as platooning are also explored for fuel efficiency and traffic flow optimization. The significance of this work lies in providing a comprehensive toolbox for prototyping and evaluating multi-agent coordination in road traffic. By integrating agent-based planning with realistic driving simulation, the platform enables the study of complex interactions between automated systems, human drivers, and traffic infrastructure. The authors conclude that while several coordination methods are functional, challenges remain, particularly in dynamic priority assignment for junctions and balancing algorithmic efficiency with human predictability. This platform serves as a critical step toward validating the safety and efficiency of future automated driving technologies.
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.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | Crossref | — | — | 1 | 2026-06-07 |
| archive | success | canonical_url | — | — | 1 | 2026-06-09 |
| extract | success | pdftotext | — | — | 2 | 2026-06-09 |
| clean | success | clean | — | — | 1 | 2026-06-09 |
| chunk | success | chunk | — | — | 1 | 2026-06-09 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-09 |
| promote | success | — | — | — | 1 | 2026-06-07 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 1 | 2026-06-09 |
| tag | success | vector_similarity | — | — | 8 | 2026-06-11 |
| verify | success | — | — | — | 1 | 2026-06-09 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-09; 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).
- Methodological Resource: tool software, dataset resource
- Theoretical Contribution: computational model