Understanding individual behavior travel decision, planning and scheduling using an agent-based modeling
Travel demand in POLARIS arises from a series of individual behaviors relating to generating, planning and scheduling both routine and day-to-day activity engagement and travel. The interaction of the travel demand model that generates the activity engagement with the transportation supply model (LINK) that simulates trips creates the network performance characteristics and travel outcomes that create the metrics of interest when analyzing new technologies.
POLARIS considers behavior across different timeframes:
- Long-term, behavior is impacted by household location/relocation, workplace choice, vehicle ownership and technology choice as well as other mobility options (e.g., bikes, transit passes…)
- Mid-term, work schedule, telecommuting and household errands have significant influence
- On a daily basis, traveler decisions are impacted by activity generation, planning (e.g., mode choice, location…), scheduling (e.g., routing, conflict resolution), execution and replanning
POLARIS behavioral models are unique as they comprise the travel demand model work in concert using the long term constraint, individual and household level needs, and availability travel options to develop a consistent daily activity and travel schedule for each agent that is simulated on the model network as shown below
Key POLARIS travel demand features include
- Cutting edge statistical and behavior models used to represent most behaviors and decision making, including choice models (MNL, NL, mixed-logit, ordered-probit, ICLV, etc.), machine learning (decision trees, neural networks, heuristic rule-based models) and others
- Estimated using a wide-variety of behavior data from surveys, field data collection, sensors, etc.
- Sensitive to key levers relating to mobility and future vehicle technologies including cost, travel times, value of time/reliability, accessibility, and many more
- Integrated into a consistent modeling framework to represent dependencies between decisions using the POLARIS agent-based model architecture