A Closed-loop, State-centric, Multi-agent Framework for Passenger Load Estimation from Heterogeneous Data Streams

TL;DR

This paper introduces a novel multi-agent framework for accurate passenger load estimation using heterogeneous data streams, incorporating physical constraints and dynamic trust allocation to improve robustness and reliability.

Contribution

It presents a closed-loop, state-centric multi-agent architecture that enforces physical feasibility and adapts trust among evidence sources for better load estimation.

Findings

Framework enforces physical feasibility at each inference step.

Dynamic trust allocation improves robustness against sensor errors.

Closed-loop calibration enhances estimation accuracy.

Abstract

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.