Dynamic Latent Plan Models

Planning is an integral part of many behavioral aspects related to transportation: residential relocation, activity and travel scheduling, route choice etc. People make plans and then select actions to execute those plans. The plans are inherently dynamic. They evolve due to situational constraints and contextual factors, experience, inertia, or changing preferences. As a result, the chosen actions might be different from those initially planned. In this paper, the authors present the methodology to model the dynamics of choices using a two-layer decision hierarchy (choice of a plan and choice of action conditional on the plan) and its dynamics. This framework, based on Hidden Markov Model principles, assumes that the plan at every time period depends on the plan at the previous time period and the actions taken in the previous time periods as well as other variables including the characteristics of the decision maker. An action at a given time period depends on the plan during the same time period in addition to other variables including the characteristics of the decision maker. The dynamics in the observed actions are explained by the dynamics in the underlying latent (unobserved) plans. The methodology is demonstrated by modeling the dynamics associated with the driving decisions as the drivers enter a freeway. The model is estimated using disaggregate trajectory data extracted from video observations and validated in a microscopic traffic simulator. Results support the necessity of including the latent plans to the decision framework.


  • English

Media Info

  • Media Type: DVD
  • Features: Figures; References; Tables;
  • Pagination: 28p
  • Monograph Title: TRB 89th Annual Meeting Compendium of Papers DVD

Subject/Index Terms

Filing Info

  • Accession Number: 01157700
  • Record Type: Publication
  • Report/Paper Numbers: 10-2243
  • Files: TRIS, TRB
  • Created Date: Jan 25 2010 11:02AM