The simultaneous rapidly increasing demand for home delivery of goods and on-demand expectancy of customers over the past years leaves a tough challenge for the logistical branch. They have to keep up with this increasing demand and simultaneously they are obliged to satisfy consumer service level demands to preserve their customers. On the other hand, as economic goals drive these businesses, they are prompted to operate cost-effectively. As a result, the fleet, deployed to execute the last-mile delivery, should meet both the requirement of cost-efficiency as well as the requirement for meeting consumer service level demands. This raises the question of how to efficiently design a fleet for last-mile on-demand logistics. For a fleet to be able to operate cost-efficiently, the fleet design decisions are required to take both fixed and variable costs into account. As such, the fleet design decisions need to include the consideration of the size of the fleet as well as the distance the vehicles travel on daily basis. Therefore, the goal of this thesis is to develop a novel method for fleet design for last-mile on-demand logistics. This work contributes by being the first to investigate methods for doing fleet design specifically for last-mile on-demand logistics considering multiple depots and variable pick-up locations. The purpose of the method is to determine the operational plans of the individual vehicles, the number of vehicles needed throughout a certain time period, the pick-up locations for all orders and the total distance travelled by the full fleet of vehicles. The proposed method builds upon established fleet design methods for ride-sharing taxi problems. The optimization method is adapted for last-mile on-demand logistics, yielding the required number of vehicles and their individual operational plans. The input of the system is a set of trips, which represent a path of a single vehicle to deliver one or multiple orders from a depot. Connecting two trips, which is called chaining, has the benefit of reducing the number of vehicles used, as chained trips are served by a single vehicle. Additionally, from multiple available depots where orders can be picked up, the method determines the best depot per order. This part of the method is called depot re-assignment. Furthermore, the fleet design problem is modelled as a multi-objective optimisation problem to find the trade-off between fleet size and the total distance the vehicles travel. Three different modelled datasets, each containing 10.000 order requests in the city centre of Amsterdam, are used to prove the value of the given method. A comparison between the method with and without depot re-assignment is made, to prove the value of the given addition of depot re-assignment. It is proven that depot re-assignment is valuable as it decreases or retains the fleet size for all test cases. The experiments conducted show that a significant decrease of the required fleet size can be established by a minor increase in total travelled distance. Furthermore, the optimal trade-off between the fleet size and the total distance travelled can be determined for a specific operation with the knowledge of operational costs for that operation.

In recent years, Shared Mobility-on-Demand systems have emerged as a great method for door-to-door transportation. Studies have shown that it is possible to route vehicles and assign requests to vehicles efficiently in large-scale systems. These studies commonly report one-dimensional performance metrics such as average vehicle occupancy, service rate, or average waiting time. We repeated a case study using a state-of-the-art Fleet Management Framework and focused on the distribution of the service level over the operation area. We observed that the chance of receiving service in a low demand area was much higher than in a high demand area. Going from this observation, this research’s objective was to research how the state-of-the-art framework can be adjusted such that the rejection rates are more evenly spread over the operation area. We developed different methods that adjust the decision of which mobility requests are serviced or which trips are selected. The methods work such that a request located in an above-average rejection rate area has an increased chance of being serviced. Similarly, a trip that goes through an area of above-average rejection rate also has priority. We set up a Discrete Event Simulation that simulates a Shared Mobility-on-Demand system to research the effects of our added method compared to the original framework. We simulated an artificial city and New York City. The Gini index was used to measure how evenly the rejection rates were spread over the operation area. In many cases, our methods were able to lower both the average rejection rate and the Gini index. With this work, we showed that the state-of-the-art framework’s objective can be extended to a broader goal. This opens up new possibilities to tune the system to match specific transportation needs in different areas of a city.