A Decision-Focused Neural Optimization Framework for Personalized Route Reproduction from Vehicle Trajectories

Key points

• We propose a neural pipeline that includes a perception model that embeds context covariates, which comprises individual characteristics, trip-specific attributes, and network-level traffic states, into the personalized link costs.1
• A constrained optimization (CO) layer, which determines the shortest path (SP) based on these estimated costs, follows the perception encoder.1
• To enable end-to-end training, we employ decision-focused learning to align the predicted shortest paths with observed routes.1
• Empirical evaluations demonstrate that the proposed framework outperforms baseline route choice models in path reproduction.1

Sources (1)

• [1]A Decision-Focused Neural Optimization Framework for Personalized Route Reproduction from Vehicle Trajectories
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 07:00 AM

  This study formulates individual route reproduction as a shortest-path problem over learned driver-specific latent link costs.

  We propose a neural pipeline that includes a perception model that embeds context covariates, which comprises individual characteristics, trip-specific attributes, and network-level traffic states, into the personalized link costs.

Extractive summary: sentences quoted from the sources.