Traditional transportation simulation tools often use fixed agent behaviors that cannot adapt to policy changes or incentives in realistic ways. Mobilytics-Gym is innovative because it integrates data-driven learning models that allow agents to adapt their behavior dynamically, enabling more realistic evaluation of policy impacts. The framework bridges simulation and real-world dynamics by incorporating observed commuter preferences and decision patterns.
This paper introduces Mobilytics-Gym, a simulation framework for evaluating urban mobility decision strategies using agent-based models that integrate learning and preference dynamics. The framework combines traffic simulation with models for commuter decision-making that learn from experiences and adapt their route choices. The system enables evaluation of incentive policies and their effects on congestion, emissions, and user satisfaction.
When provided higher incentives for using transit, the simulation showed that 23% of agents changed their modes from cars to bus and walking when incentives were offered. The system demonstrated effective integration of agent learning models with traffic simulation, achieving a system-level cost reduction of approximately $200,000 due to incentives. The framework proved capable of evaluating sensitivity of system-level outcomes to policy parameters.
@inproceedings{Samal2019,
author = {Samal, Chinmaya and Dubey, Abhishek and Ratliff, Lillian J.},
booktitle = {IEEE} International Conference on Smart Computing, {SMARTCOMP} 2019, Washington, DC, USA},
title = {Mobilytics-Gym: {A} Simulation Framework for Analyzing Urban Mobility Decision Strategies},
year = {2019},
acceptance = {29},
month = {jun},
pages = {283--291},
abstract = {The rise in deep learning models in recent years has led to various innovative solutions for intelligent transportation technologies. Use of personal and on-demand mobility services puts a strain on the existing road network in a city. To mitigate this problem, city planners need a simulation framework to evaluate the effect of any incentive policy in nudging commuters towards alternate modes of travel, such as bike and car-share options. In this paper, we leverage MATSim, an agent-based simulation framework, to integrate agent preference models that capture the altruistic behavior of an agent in addition to their disutility proportional to the travel time and cost. These models are learned in a data-driven approach and can be used to evaluate the sensitivity of an agent to system-level disutility and monetary incentives given, e.g., by the transportation authority. This framework provides a standardized environment to evaluate the effectiveness of any particular incentive policy of a city, in nudging its residents towards alternate modes of transportation. We show the effectiveness of the approach and provide analysis using a case study from the Metropolitan Nashville area.},
bibsource = {dblp computer science bibliography, https://dblp.org},
biburl = {https://dblp.org/rec/bib/conf/smartcomp/SamalDR19},
category = {selectiveconference},
contribution = {lead},
doi = {10.1109/SMARTCOMP.2019.00064},
file = {:Samal2019-Mobilytics-Gym_A_Simulation_Framework_for_Analyzing_Urban_Mobility_Decision_Strategies.pdf:PDF},
keywords = {urban mobility, agent-based simulation, incentive policies, commuter behavior, multi-modal transportation, simulation framework},
project = {smart-transit,smart-cities},
tag = {transit},
timestamp = {Wed, 16 Oct 2019 14:14:54 +0200},
url = {https://doi.org/10.1109/SMARTCOMP.2019.00064},
month_numeric = {6}
}