Researchers have developed a new agent-based modeling framework that integrates reinforcement learning and multi-agent reinforcement learning to simulate cognitive smart freight corridors. This framework aims to improve the deployment of connected and automated vehicles (CAVs) by enabling adaptive decision-making for platoon formation and charging coordination. Preliminary results suggest that the cognitive scenario enhances throughput and reduces congestion, while an assisted scenario offers energy savings through platooning, with MARL coordination proving more efficient for charging capacity utilization than rule-based methods. AI
IMPACT This research could lead to more efficient logistics and transportation systems through AI-driven adaptive control of autonomous vehicles.
RANK_REASON The cluster contains a research paper detailing a new simulation framework for smart freight corridors using AI techniques. [lever_c_demoted from research: ic=1 ai=1.0]
- agent-based model
- arXiv
- Connected and Automated Vehicles Symposium
- Multi-agent reinforcement learning
- Mustafa Can Camur
- reinforcement learning
- vehicle-to-everything
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
