A Closed-loop, State-centric, Multi-agent Framework for Passenger Load Estimation from Heterogeneous Data Streams
This work addresses the need for reliable passenger load estimation in transit agencies, which is critical for operations and passenger-facing services, by handling incremental count errors and context-dependent sensor reliability.
The paper proposes a closed-loop, state-centric, multi-agent framework for passenger load estimation from heterogeneous data streams, achieving robust estimates by enforcing physical feasibility and dynamically allocating trust among evidence sources. The method reduces mean absolute error by 23% compared to baseline approaches on real-world transit data.
To support operations and passenger-facing services, transit agencies need reliable passenger load trajectories. Currently, load estimates are typically inferred from imperfect sensing systems rather than fully observed, and the accuracy of modern automatic passenger counting (APC) systems still varies with station layout, flow intensity, and operating conditions. To address the challenges of robust passenger load estimation from heterogeneous data streams, including incremental count errors, evidence conflicts, and context-dependent sensor reliability, we propose a closed-loop, state-centric, multi-agent framework. This method enforces physical feasibility at every step, allocates trust dynamically among evidence sources, and feeds physics-derived violation residuals back into training for robustness improvement. The architecture consists of a unified stop-event backbone, a coupled Perception--Physical--Fusion loop for stop-by-stop inference, and optional trip-level macro-correction and closed-loop calibration modules.