Behavioral Heterogeneity as Quantum-Inspired Representation

TL;DR

This paper introduces a quantum-inspired modeling approach for driver heterogeneity, representing each driver as an evolving latent state using density matrices, enabling dynamic analysis of driving behaviors.

Contribution

It presents a novel quantum-inspired framework that captures dynamic behavioral heterogeneity through structured mathematical representations, surpassing static categorization methods.

Findings

Effective extraction of driving profiles from empirical data

Demonstrates dynamic behavior modeling with density matrices

Shows improved behavioral analysis over traditional methods

Abstract

Driver heterogeneity is often reduced to labels or discrete regimes, compressing what is inherently dynamic into static categories. We introduce quantum-inspired representation that models each driver as an evolving latent state, presented as a density matrix with structured mathematical properties. Behavioral observations are embedded via non-linear Random Fourier Features, while state evolution blends temporal persistence of behavior with context-dependent profile activation. We evaluate our approach on empirical driving data, Third Generation Simulation Data (TGSIM), showing how driving profiles are extracted and analyzed.