This paper discusses SESAR’s Auto-Steer Taxi at Airport (ASTAIR) project, which seeks to advance airport ground operations including engine-off taxiing to move towards sustainable airports. The ASTAIR concept integrates human–AI teaming to optimize aircraft movement from gates to runways, with the primary objectives of improving predictability, efficiency, and environmental sustainability at large airports. Building on previous initiatives such as SESAR’s AEON, ASTAIR brings high-level automation to tasks like autonomous taxiing and vehicle routing. The system assists operators by calculating conflict-free routes for vehicles and dynamically adjusting operations based on real-time data. Based on workshops with several stakeholders, we describe the operational challenges involved in implementing ASTAIR, including managing parking stand availability and adapting to unforeseen events. A significant challenge highlighted is the human–automation partnership, where AI plays a supportive role but humans retain control over critical decisions, particularly in cases of system failure. The need for clear and consistent collaboration between AI and human operators is emphasized to ensure safety, efficiency, and improved compliance with take-off schedules, which in turn facilitates in-flight optimization.

We aim to contribute to the automation of ground handling tasks using autonomous ground support equipment (GSE) at airports. Automation of airside operations has recently become critical for the airports to achieve higher levels of safety and efficiency under growing traffic demand and requires solving a complex scheduling and path planning problem. To address this problem, we present a multi-agent task allocation and path planning model for handling airside operations on the apron. In the problem, the ground handling tasks are to be allocated to the equipment, the trips of vehicles should be scheduled within specific time windows considering the flight schedules, and the collisions of vehicles on the apron and service roads should be avoided. We present a centralized multi-agent task allocation and routing model which aims to optimize the allocation and routing of various types of ground handling tasks over a heterogeneous set of GSE vehicles. We convert the allocation and routing problem into vehicle routing problem with time windows, pick-ups, deliveries and solve the problem using a warm start mixed integer linear programming (MILP) model. We also introduce a nonlinear objective function which converts the MILP model into a mixed integer nonlinear programming (MINLP) model, to minimize the time service locations at the stands are occupied. Then, we solve the corresponding path finding problem to find collision free paths for the GSE, by the multi-agent path finding model. The proposed model outperforms the decentralized approach in previous research regarding the allocation rate of assigning tasks to vehicles and the performance indicators of finding conflict free paths, and in CPU time. The mean deviations from shortest paths were considerably small in path planning which means that the solution quality was high. Furthermore, the CPU time of allocating tasks has been reduced by 48% compared to the CPU time of decentralized allocation.

Inspired by the vision of fully autonomous airside operations at Schiphol airport, this study aims to contribute to the short-term goal of automated aircraft ground handling. In this research, we design and evaluate a multi-agent system for planning of automated ground handling. There are two main components in the system: task allocation optimization and multi-agent path planning. To allocate tasks to ground support equipment (GSE) vehicles, an auction mechanism inspired by temporal sequential single item (TeSSI) auction is proposed. Ground handling tasks scheduling for GSE vehicles is modeled as several single-vehicle pickup and delivery optimization problems (SPDP), and the values of the objective functions are used to generate bids for GSE vehicle agents in the auction. Prioritized safe interval path planning for large agents (LA-SIPP) is used to plan collision-free paths for GSE vehicle agents in the model to execute tasks. The aim is to increase the success rates of allocating tasks and finding collision free paths without causing flight delays, given the limited resources such as a small number of available GSE vehicles, time windows constraints and conflicting interests of different agents. Due to the results, even for the instances with frequent flights and the most limited resources, the success rates of allocation and path planning were higher than 81% and 98%, respectively. Furthermore, periodic task allocation and path planning of the ground handling tasks for flights in three aircraft stands during a planning time window of the day, as well as replanning in case of disruptions were performed in a short CPU time. There is a lack of research dealing with the complete process of ground handling, since existing studies concerning the automation of ground handling operations involve fleet assignment or task scheduling models without an integration of detailed path planning. Our main contribution is to present a framework that combines task allocation and path planning for automation of ground handling operations and provides solutions using a multi-agent perspective.

eCommerce, postal and logistics’ planners require to solve large-scale capacitated vehicle routing problems (CVRPs) on a daily basis. CVRP problems are NP-Hard and cannot be easily solved for large problem instances. Given their complexity, we propose a methodology to reduce the size of CVRP problems that can be later solved with state-of-the-art optimization solvers. Our method is an efficient version of clustering that considers the constraints of the original problem to transform it into a more tractable version. We call this approach Constrained Clustering Capacitated Vehicle Routing Solver (CC-CVRS) because it produces a soft-clustered vehicle routing problem with reduced decision variables. We demonstrate how this method reduces the computational complexity associated with the solution of the original CVRP and how the computed solution can be transformed back into the original space. Extensive numerical experiments show that our method allows to solve very large CVRP instances within seconds with optimality gaps of less than 16%. Therefore, our method has the following benefits: it can compute improved solutions with small optimality gaps in near real-time, and it can be used as a warm-up solver to compute an improved solution that can be used as an initial solution guess by an exact solver.

Application of deep learning to NP-hard combinatorial optimization problems is an emerging research trend, and a number of interesting approaches have been published over the last few years. In this work we address robust optimization, which is a more complex variant where a max-min problem is to be solved. We obtain robust solutions by solving the inner minimization problem exactly and apply Reinforcement Learning to learn a heuristic for the outer problem. The minimization term in the inner objective represents an obstacle to existing RL-based approaches, as its value depends on the full solution in a non-linear manner and cannot be evaluated for partial solutions constructed by the agent over the course of each episode. We overcome this obstacle by defining the reward in terms of the one-step advantage over a baseline policy whose role can be played by any fast heuristic for the given problem. The agent is trained to maximize the total advantage, which, as we show, is equivalent to the original objective. We validate our approach by solving min-max versions of standard benchmarks for the Capacitated Vehicle Routing and the Traveling Salesperson Problem, where our agents obtain near-optimal solutions and improve upon the baselines.

This study introduces a model to solve a dynamic network optimization model on a heterogeneous graph. We use this model to optimize the collection and consolidation operations on a cross-country multi-modal distribution network. The model's dynamic objects are trucks, trailers, orders, unvisited collection and customs check points. Information about dynamic objects is extracted from a realtime database. The model's static objects include objects that are known in advance, such as warehouses. The constraints of the problem include due dates, vehicle capacity, availability of vehicles, and precedence constraints of visiting locations. We propose a mixed-integer programming model and provide a solution using matheuristics. We decompose the master MIP model into subproblems that can be solved to optimality with LP solvers. We also reduce the graph complexity by variable fixing due to optimized subproblems or by bounding the maximum number of paths to be selected due to the solutions of priority-based bin packing algorithms. Finally, we convert the resulting problem into a bipartite matching problem by expanding the graph nodes which can then be solved in polynomial time. We implement our solution method on real-time data retrieved from the tracking system of a third-party logistics company. Experiments show that our solution method significantly outperforms other heuristics in terms of solution quality which is measured with respect to lateness, empty kilometers traveled, travel times, number of required/used vehicles, load factors, and ratio of served orders.

We develop search algorithms based on local search, and a matheuristic that solves a set of mixed integer programming models to improve the robustness of a set of solutions for an academic timetabling problem. The matheuristic uses the solution pool feature of CPLEX while solving two related MIP models iteratively. The solutions form a network (Akkan et al. in Eur J Oper Res 249(2):560–576, 2016. doi:10.1016/j.ejor.2015.08.047), in which edges are defined by the Hamming distance between pairs of solutions. This network is used to calculate a robustness measure, where disruption of a solution is assumed to occur when the time slot to which a team had been assigned is no longer feasible for that team and the heuristic response to this disruption is choosing one of the neighbors of the disrupted solution. Considering the objective function of the timetabling problem and this robustness measure results in a bi-criteria optimization problem where the goal is to improve the Pareto front by enlarging the network. We compare the performance of the heuristics on a set of random instances and seven semesters’ actual data. These results show that some of the proposed local search algorithms and the matheuristic find high quality approximate Pareto fronts. Besides being one of the few timetabling algorithms in the literature addressing robustness, a key contribution of this research is the demonstration of the effectiveness of the matheuristic approach. By using this matheuristic approach, for any discrete optimization model that can be solved optimally or near-optimally in an acceptable time, researchers can develop a robustness improvement algorithm.