G. Ganassoli, F. Mazzeo, C. Pasquale, S. Siri, M. Salazar
5 min
Traditional transport planning often prioritizes utilitarian metrics, such as minimizing average travel time or maximizing revenue, which can inadvertently disadvantage lower-income or vulnerable populations. While "transport justice" literature exists, it has historically been limited to evaluating existing inequities rather than providing actionable, operational solutions. This paper addresses this gap by developing an optimization framework for intermodal Autonomous Mobility-on-Demand (AMoD) systems that incorporates social justice principles alongside operational constraints.
The authors propose a mesoscopic, multi-layer network flow model that integrates various modes of transport: AMoD, public transit, walking, and cycling. The framework is designed to optimize system operations under several real-world constraints, including:
The researchers compare two distinct optimization paradigms:
The framework was tested using a real-world case study of Manhattan, New York. Key findings include:
This research provides city planners and policymakers with a concrete, mathematical tool to move beyond theoretical discussions of fairness. By demonstrating that operational constraints can be balanced with social justice goals, the authors show that modern, automated transport systems can be designed to serve all citizens equitably, rather than just optimizing for the average user.
To date, most of the research on transport planning has focused on optimizing revenues or utilitarian metrics such as average travel times, which often ends up penalizing the worst-off for the sake of profit or efficiency. At the same time, most of the research in transport justice has focused on assessing injustices, without being able to prescribe operational solutions. This paper contributes to bridging this gap and presents optimization models for justice-informed operational planning of intermodal mobility systems that explicitly account for the budget and safety limitations of users, and for infrastructural capacity constraints. Specifically, we first focus on an intermodal Autonomous Mobility-on-Demand (AMoD) system -- where self-driving robotaxis provide on-demand mobility jointly with public transit and active modes -- and characterize its operations from a mesoscopic planning perspective via network flow models. Second, we leverage these models to optimize system operations through both utilitarian efficiency and justice-informed objectives. We showcase our framework in a real-world case-study for Manhattan, New York. Our results show that monetary budgets significantly limit the social justice potential of AMoD systems if they are to be deployed as transportation network companies. At the same time, granting free public transit can result in sufficiency levels very close to a completely free intermodal AMoD system, where justice-informed operations can be achieved without compromising standard efficiency metrics, ultimately highlighting the strong potential of social policies.
Alex: Oh—so the math basically makes the system feel the pain of the person with the longest commute more than the person who is already doing fine?
Sam: That is a precise way to put it. This forces the optimization to re-route traffic or adjust transit flows to help those specific, struggling individuals first.
Alex: And what happens to the rest of the city when you do that? Does the whole system suffer because you're prioritizing the worst commutes?
Sam: That is where the findings get interesting. The study shows that you can achieve this kind of fairness with only a very small increase in the overall average travel time. It turns out you do not have to sacrifice the efficiency of the whole city to make sure the most vulnerable commuters are treated fairly.
Alex: Wait—so the trade-off is really that small? It sounds like we have been assuming we had to choose between fast and fair, but this research suggests that's a false choice.
Sam: That is what the data suggests. Though the study also found a major hurdle: money. Even if the math says a route is optimal, if a person cannot afford the ticket for the robotaxi or the train, the system still fails them.
Alex: Right—the model can optimize the route, but it cannot change the price of the ride. So what did they find when they changed the economics?
Sam: They tested a scenario where public transit is made free. The results were quite significant. Making public transit free achieved fairness levels almost identical to a system where even the high-tech robotaxis were free. It shows that policy—like making buses or subways free—can be just as powerful as the technology itself.
Alex: So the technology is the tool, but the policy is the steering wheel. Are there any significant limitations the authors flag?
Sam: There are, and the authors are careful to point them out. The model relies on existing data, which might carry historical biases—if certain neighborhoods have been neglected by planners for decades, the data will reflect that neglect. There is also a deeper simplification at work: the model treats human life as moving from point A to point B, which misses the actual, lived experience of travel.
Alex: So it is a useful map, but not the full territory. It tells us how to optimize the flow, but it does not tell us how to fix the deeper social issues that created the inequality in the first place.
Sam: Exactly. It is a meaningful step in how we use mathematics to plan cities, but it is one part of a much larger puzzle. The broader goal the authors point toward is treating urban mobility the way we treat water or electricity—as a public utility, where every citizen has a reliable way to get where they need to go, regardless of their income or where they live.
Alex: That is a thought worth sitting with. The question is not just how to move people efficiently, but who gets left behind when efficiency is the only goal. Thanks for listening to ResearchPod.