Active Inference Controller Optimizes Traffic Signals in Challenging Environments

Researchers have developed an active inference controller for traffic signal management in noisy and unpredictable IoT environments. This controller dynamically selects signal phases by minimizing expected free energy, offering a traceable decision-making process. Benchmarked in a traffic simulator, the active inference controller outperformed a rule-based heuristic and a deep Q-network (DQN) in scenarios with increasing noise and nonstationarity, achieving lower idle times and CO2 emissions. AI

IMPACT This research demonstrates a novel AI approach for improving traffic signal efficiency and reducing emissions in complex urban environments.

RANK_REASON The cluster contains an academic paper detailing a new AI approach for traffic signal control. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Active Inference
• Alfreds Lapkovskis
• IoT
• SUMO

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →