Reproduce “Real-World Evaluation of two Cooperative Intersection Management Approaches” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Marvin Klimke, Max Bastian Mertens, Benjamin Völz, Michael Buchholz
Cooperative intersection management approaches were evaluated in mixed traffic environments through extensive simulations and real-world experiments with prototype Connected Automated Vehicles (CAVs), demonstrating their applicability and effectiveness in reducing maneuver duration and stops, particularly for subordinate road vehicles, while coordinating movements.
Key insights
- Cooperative intersection management can significantly improve traffic efficiency by reducing stops and maneuver durations for yielding vehicles, even in mixed traffic with 50% HDV presence.
- A trade-off exists between achieving higher traffic efficiency and increased criticality measures (e.g., lower PET or DRAC), particularly observed with the optimization-based planner.
- Real-world experiments with prototype CAVs confirm the practical applicability of both optimization and RL-based cooperative planners in operational public mixed-traffic environments.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.