Search for: All records

With Mobility-as-a-Service platforms moving toward vertical service expansion, we propose a destination recommender system for Mobility-on-Demand (MOD) services that explicitly considers dynamic vehicle routing constraints as a form of a ``physical internet search engine''. It incorporates a routing algorithm to build vehicle routes and an upper confidence bound based algorithm for a generalized linear contextual bandit algorithm to identify alternatives which are acceptable to passengers. As a contextual bandit algorithm, the added context from the routing subproblem makes it unclear how effective learning is under such circumstances. We propose a new simulation experimental framework to evaluate the impact of adding the routing constraints to the destination recommender algorithm. The proposed algorithm is first tested on a 7 by 7 grid network and performs better than benchmarks that include random alternatives, selecting the highest rating, or selecting the destination with the smallest vehicle routing cost increase. The RecoMOD algorithm also reduces average increases in vehicle travel costs compared to using random or highest rating recommendation. Its application to Manhattan dataset with ratings for 1,012 destinations reveals that a higher customer arrival rate and faster vehicle speeds lead to better acceptance rates. While these two results sound contradictory, they provide important managerial insights for MOD operators. 

We tackle the problem of evaluating the impact of different operation policies on the performance of a microtransit service. This study is the first empirical application using the stable matching modelling framework to evaluate different operation cost allocation and pricing mechanisms on microtransit service. We extend the deterministic stable matching model to a stochastic reliability-based one to consider user’s heterogeneous perceptions of utility on the service routes. The proposed model is applied to the evaluation of Kussbus microtransit service in Luxembourg. We found that the current Kussbus operation is not a stable outcome. By reducing their route operating costs of 50%, it is expected to increase the ridership of 10%. If Kussbus can reduce in-vehicle travel time on their own by 20%, they can significantly increase profit several folds from the baseline. 

While public transit network design has a wide literature, the study of line planning and route generation under uncertainty is not so well covered. Such uncertainty is present in planning for emerging transit technologies or operating models in which demand data is largely unavailable to make predictions on. In such circumstances, this paper proposes a sequential route generation process in which an operator periodically expands the route set and receives ridership feedback. Using this sensor loop, a reinforcement learning-based route generation methodology is proposed to support line planning for emerging technologies. The method makes use of contextual bandit problems to explore different routes to invest in while optimizing the operating cost or demand served. Two experiments are conducted. They (1) prove that the algorithm is better than random choice; and (2) show good performance with a gap of 3.7% relative to a heuristic solution to an oracle policy. 

Mobility-as-a-service systems are becoming increasingly important in the context of smart cities, with challenges arising for public agencies to obtain data from private operators. Only limited mobility data are typically provided to city agencies, which are not enough to support their decision-making. This study proposed an entropy-maximizing gravity model to predict origin–destination patterns of both passenger and mobility fleets with only partial operator data. An iterative balancing algorithm was proposed to efficiently reach the entropy maximization state. With different trip length distributions data available, two calibration applications were discussed and validated with a small-scale numerical example. Tests were also conducted to verify the applicability of the proposed model and algorithm to large-scale real data from Chicago transportation network companies. Both shared-ride and single-ride trips were forecast based on the calibrated model, and the prediction of single-ride has a higher level of accuracy. The proposed solution and calibration algorithms are also efficient to handle large scenarios. Additional analyses were conducted for north and south sub-areas of Chicago and revealed different travel patterns in these two sub-areas.

 

Traditionally vehicles act only as servers in transporting passengers and goods. With increasing sensor equipment in vehicles, including automated vehicles, there is a need to test algorithms that consider the dual role of vehicles as both servers and sensors. The paper formulates a sequential route selection problem as a shortest path problem with on-time arrival reliability under a multi-armed bandit setting, a type of reinforcement learning model. A decision-maker has to make a finite set of decisions sequentially on departure time and path between a fixed origin-destination pair such that on-time reliability is maximized while travel time is minimized. The upper confidence bound algorithm is extended to handle this problem. Several tests are conducted. First, simulated data successfully verifies the method, then a real-data scenario is constructed of a hotel shuttle service from midtown Manhattan in New York City providing hourly access to John F. Kennedy International Airport. Results suggest that route selection with multi-armed bandit learning algorithms can be effective but neglecting passenger scheduling constraints can have negative effects on on-time arrival reliability by as much as 4.8% and combined reliability and travel time by 66.1%. 

Despite the increasing relevance of private transport operators as Mobility-as-a-Service in the success of smart cities, desire for privacy in data sharing limits collaborations with public agencies. We propose an original model that circumvents this limitation, by designing a diffusion of the data - in this case, service tour data - such that passenger travel times remain reliable to the recipient agency. The Tour Sharing Privacy Design Problem is formulated as a nonlinear programming problem that maximizes entropy. We investigate properties of the model and iterative tour generation algorithms, and conduct a series of numerical experiments on an instance that has 90 feasible tours. The experimental results show that a k-best shortest tour approach of generating tours iteratively initially increases the gap to a lower bound before decreasing toward a final constraint gap. The model is shown to recognize the trade-offs between more reliability in data and more anonymity. Comparisons between the true and diffused travel times and OD matrices are made.