analiza aiqbench
This research applies active inference to optimize urban traffic signals in noisy IoT environments, offering a more robust and auditable alternative to standard deep reinforcement learning models. By minimizing expected free energy under conditions like sensor occlusion and adverse weather, the proposed controller significantly reduces idle times and emissions compared to baseline DQN approaches. While it trades off some bus priority rates, this method addresses critical reliability gaps in nonstationary smart city infrastructures where conventional learned policies fail.
Active Inference for Adaptive Traffic Signal Control in Noisy Nonstationary IoT Environments
arXiv:2606.13698v1 Announce Type: cross Abstract: Urban traffic signal control at IoT-instrumented intersections must remain effective under sensor occlusion, weather attenuation, and nonstationary demand. Conventional controllers degrade under these conditions, and learned policies remain difficult to audit. To address these challenges, we propose an active inference controller for a four-arm signalized intersection that dynamically selects phases by minimizing expected free energy (EFE) over Gaussian beliefs about per-direction congestion levels, yielding a fully traceable decision pipeline. We benchmark the controller in a SUMO traffic simulator against a rule-based heuristic and a deep Q-network (DQN) across four scenarios that progressively increase noise and nonstationarity, spanning sensor occlusion, adverse weather, and stochastic accidents. Across 100 independent random evaluations per scenario, active inference attains the lowest idle times and CO2 emissions in the noisiest scenarios (56,977 s and 29.12 kg vs. 71,741 s and 30.56 kg for DQN). These gains come at a modest cost in bus priority service rate and phase switch frequency.
Abstract:Urban traffic signal control at IoT-instrumented intersections must remain effective under sensor occlusion, weather attenuation, and nonstationary demand. Conventional controllers degrade under these conditions, and learned policies remain difficult to audit. To address these challenges, we propose an active inference controller for a four-arm signalized intersection that dynamically selects phases by minimizing expected free energy (EFE) over Gaussian beliefs about per-direction congestion levels, yielding a fully traceable decision pipeline. We benchmark the controller in a SUMO traffic simulator against a rule-based heuristic and a deep Q-network (DQN) across four scenarios that progressively increase noise and nonstationarity, spanning sensor occlusion, adverse weather, and stochastic accidents. Across 100 independent random evaluations per scenario, active inference attains the lowest idle times and CO2 emissions in the noisiest scenarios (56,977 s and 29.12 kg vs. 71,741 s and 30.56 kg for DQN). These gains come at a modest cost in bus priority service rate and phase switch frequency.
Systems and Control (eess.SY); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Networking and Internet Architecture (cs.NI); Performance (cs.PF)
arXiv:2606.13698 [eess.SY]
(or arXiv:2606.13698v1 [eess.SY] for this version)
Text integral sub licența deschisă a publicației · 179 cuvinte
Subiecte conexe
Adjustment Speed as a Safety Constraint for Nonstationary Reinforcement Learning
arXiv · 27 iul. 2026
Proactive Context-Forecasted Safety Constraints for Nonstationary Reinforcement Learning
arXiv · 9 sept. 2026
CASC: Causal Adversarial Subspace Clustering for Multivariate Spatiotemporal Data
arXiv · 24 iul. 2026
Game of Nons: Non-Gaussian Nonunitary Environments with Nonlinear Coupling
arXiv · 6 oct. 2026