AI & softwareResearch findings
Impact of Origin-Destination Patterns on Large-Scale Mixed Traffic Control
Original published 2025.05.19 10:36 KSTAdded to Blackdeck 2026.11.08 20:04 KST
What has changed?
A multi-agent reinforcement learning framework that considers time-varying origin-destination patterns in large-scale mixed traffic networks
Key points
- Analyzes the impact of time-varying origin-destination patterns in large-scale mixed traffic control
- Proposes a decentralized multi-agent reinforcement learning framework for real-time intersection management
- Evaluates performance using average vehicle waiting time on a real-world network of 14 intersections in Colorado Springs
Connect it to your work
Feasibility of large-scale multi-agent traffic control under fluctuating origin-destination patterns is investigated
What remains unproven
This research note is based on an abstract; check the original for test conditions and application scope.
Originals used for this note
Links open the original publisher in a new tab.