Lab
R.R. Negenborn's Lab
Institution: Delft University of Technology
Featured research (11)
Several measures have been developed to prevent emissions from inland water transportation. However, it is challenging to weigh all the aspects to identify the pathway that will ultimately result in zero-emission inland shipping. A data-driven virtual representation of the inland shipping system can be used to evaluate zero-emission strategies, effectiveness of policies and technologies, and consequences of their implementation. This multi-level digital twin can realistically represent the system with all relevant components, which needs to be validated using real-world data. Subsequently, future scenarios can be imposed on the digital twin, and the proposed intervention measures can be applied, based on which their efficiency can be assessed together with the inland shipping sector. This study discusses the essential aspects of designing a digital twin for an IWT. Three aspects are considered essential: individual ships, logistics chains, and infrastructure. As these research topics span various scales, ranging from a single vessel to an entire infrastructure network, an agent-based approach is suitable for forming the basis of the digital twin. Consequently, potential interventions can be considered, ranging from the application of new technologies to individual vessels to policy measures implemented for an entire shipping corridor or various bunker infrastructure strategies in the network. Additionally, the impact of the implemented interventions can be evaluated at any desired scale, ranging from the individual ship level and its emissions to the network level and aggregated emissions in an entire area, or the impact on the logistics chain.
Ships and ports are ripe for operation without humans — but only if the maritime industry can work through the practical, legal and economic implications first. Ships and ports are ripe for operation without humans — but only if the maritime industry can work through the practical, legal and economic implications first.
Global synchromodal transportation involves the movement of container shipments between inland terminals located in different continents using ships, barges, trains, trucks, or any combination among them through integrated planning at a network level. One of the challenges faced by global operators is the matching of accepted shipments with services in an integrated global synchromodal transport network with dynamic and stochastic travel times. The travel times of services are unknown and revealed dynamically during the execution of transport plans, but the stochastic information of travel times are assumed available. Matching decisions can be updated before shipments arrive at their destination terminals. The objective of the problem is to maximize the total profits that are expressed in terms of a combination of revenues, travel costs, transfer costs, storage costs, delay costs, and carbon tax over a given planning horizon. We propose a sequential decision process model to describe the problem. In order to address the curse of dimensionality, we develop a reinforcement learning approach to learn the value of matching a shipment with a service through simulations. Specifically, we adopt the Q-learning algorithm to update value function estimations and use the epsilon-greedy strategy to balance exploitation and exploration. Online decisions are created based on the estimated value functions. The performance of the reinforcement learning approach is evaluated in comparison to a myopic approach that does not consider uncertainties and a stochastic approach that sets chance constraints on feasible transshipment under a rolling horizon framework.
Current mobility services cannot compete on equal terms with self-owned mobility products concerning service quality. Due to supply and demand imbalances, ridesharing users invariably experience delays, price surges, and rejections. Traditional approaches often fail to respond to demand fluctuations adequately since service levels are, to some extent, bounded by fleet size. With the emergence of autonomous vehicles, however, the characteristics of mobility services change and new opportunities to overcome the prevailing limitations arise. In this paper, we consider an autonomous ridesharing problem in which idle vehicles are hired on-demand in order to meet the service level requirements of a heterogeneous user base. In the face of uncertain demand and idle vehicle supply, we propose a learning-based optimization approach that uses the dual variables of the underlying assignment problem to iteratively approximate the marginal value of vehicles at each time and location under different availability settings. These approximations are used in the objective function of the optimization problem to dispatch, rebalance, and occasionally hire idle third-party vehicles in a high-resolution transportation network of Manhattan. The results show that the proposed policy outperforms a reactive optimization approach in a variety of vehicle availability scenarios while hiring fewer vehicles. Moreover, we demonstrate that mobility services can offer strict service level contracts (SLCs) to different user groups featuring both delay and rejection penalties.
Traditionally, terminal operators create an initial berthing plan before the arrival of incoming vessels. This plan involves decisions on when and where to load or discharge containers for the calling vessels. However, disruptive unforeseen events (i.e., arrival delays, equipment breakdowns, tides, or extreme weather) interfere with the implementation of this initial plan. For terminals, berths and quay cranes are both crucial resources, and their capacity limits the efficiency of port operations. Thus, one way to minimize the adverse effects caused by disruption is to ally different terminals to share berthing resources. In some challenging situations, terminal operators also need to consider the extensive transshipment connections between feeder and mother vessels. Therefore, in this work, we investigate a collaborative variant of the berth allocation recovery problem which focuses on the collaboration among terminals and transshipment connections between vessels. We propose a mixed-integer programming model to (re)-optimize the initial berth and quay crane allocation plan and develop a Squeaky Wheel Optimization metaheuristic to find near-optimal solutions for large-scale instances. The results from the performed computational experiments, considering multiple scenarios with disruptive events, show consistent improvements of up to 40% for the suggested collaborative strategy (in terms of costs for the terminal operators).