Dynamic Coordinated Speed Control and Synergistic Performance Evaluation in Connected and Automated Vehicle Environment
archive: archived pipeline: cataloged verified
Get this paper ↗ (full text — opens at the source; we link to it, we don't host it)
Summary
This study addresses the limitations of conventional Dynamic Speed Harmonization (DSH) strategies, such as Variable Speed Limits (VSL), which suffer from low driver compliance and limited spatial impact. The research investigates how Connected and Automated Vehicles (CAVs) can enhance DSH effectiveness in mixed traffic flows involving Human-Driven Vehicles (HDVs). Motivated by the need to mitigate freeway congestion, safety risks, and emissions at bottlenecks, the authors develop a safety-oriented DSH strategy based on Deep Reinforcement Learning (DRL). This approach eliminates the need for explicit traffic dynamics modeling and allows for adaptive control in complex, mixed-traffic environments. The methodology employs a microscopic simulation environment to evaluate the proposed DRL-based DSH controller. The study is structured into three main components: first, a single-agent DRL strategy is applied to recurrent bottlenecks to assess operational performance under varying CAV Market Penetration Rates (MPRs). Second, a safety-oriented DSH strategy is tested at nonrecurrent bottlenecks, such as incident zones, utilizing Surrogate Safety Measurements (SSM) to quantify safety improvements. Third, a Multi-Agent Dynamic Speed Harmonization (MADSH) system is developed to prevent local optimization issues and enable lane-specific speed limits. The experiments analyze synergistic performance across mobility, safety, and sustainability metrics, including travel time, collision probability, and emissions, while conducting sensitivity analyses on headways, speed decrements, and adverse weather conditions. The results demonstrate that the DRL-based DSH strategy significantly improves operational performance in mixed traffic. For recurrent congestion, the method enhances mobility and achieves co-benefits with safety, with sustainability improvements becoming more pronounced at higher CAV MPRs. Spatiotemporal analysis reveals that CAV-integrated DSH effectively smooths speed variations and dampens traffic oscillations. In nonrecurrent scenarios, the strategy further improves safety and mobility as MPRs increase, mitigating the impact of special events. Sensitivity analyses confirm the agent’s adaptability to adverse weather and varying safety thresholds. Additionally, the MADSH system proves effective in avoiding local optimization traps, offering a robust solution for distributed control. The significance of this work lies in its holistic evaluation of DSH in a CAV-enabled environment, providing essential insights for intelligent transportation systems. By demonstrating that CAVs can complement traditional infrastructure to achieve synergistic benefits across safety, mobility, and sustainability, the study supports the transition toward vehicle-road synergy systems. The findings suggest that DRL-based control strategies are adaptable and effective in managing mixed traffic flows, offering a scalable solution for future freeway management where CAVs and HDVs coexist.
Key finding
Deep Reinforcement Learning-based Dynamic Speed Harmonization strategies significantly enhance freeway mobility, safety, and sustainability in mixed traffic flows, with performance improvements scaling with higher Connected and Automated Vehicle market penetration rates.
Methodology
simulator
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 bulk_ingest_rosap on 2026-05-23 (6 acquisition events logged).
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | rosap | — | — | 2 | 2026-05-23 |
| archive | success | — | — | — | 1 | 2026-05-23 |
| extract | success | cached | — | — | 2 | 2026-06-10 |
| clean | success | — | — | — | 1 | 2026-06-01 |
| chunk | success | — | — | — | 1 | 2026-06-01 |
| embed | success | — | — | — | 1 | 2026-06-02 |
| enrich | success | — | — | — | 1 | 2026-05-23 |
| promote | success | — | — | — | 1 | 2026-05-23 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 3 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 24 | 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