Intermodal freight transport (IFT) requires a large number of optimisation measures to ensure its attractiveness. This involves numerous control decisions on different time scales, making integrated optimisation with traditional methods almost unfeasible. Recently, a new trend in optimisation science has emerged: the application of Deep Learning (DL) to combinatorial problems. Neural combinatorial optimisation (NCO) enables real-time decision-making under uncertainties by considering rich context information—a crucial factor for seamless synchronisation, optimisation, and, consequently, for the competitiveness of IFT. The objective of this study is twofold. First, we systematically analyse and identify the key actors, operations, and optimisation problems in IFT and categorise them into six major classes. Second, we collect and structure the key methodological components of the NCO framework, including DL models, training algorithms, design strategies, and review the current State of the Art with a focus on NCO and hybrid DL models. Through this synthesis, we integrate the latest research efforts from three closely related fields: optimisation, transport planning, and NCO. Finally, we critically discuss and outline methodological design patterns and derive potential opportunities and obstacles for learning-based frameworks for integrated optimisation problems. Together, these efforts aim to enable a better integration of advanced DL techniques into transport logistics. We hope that this will help researchers and practitioners in related fields to expand their intuition and foster the development of intelligent decision-making systems and algorithms for tomorrow’s transport systems.

Finding prompt and optimal solutions to the vehicle routing problem (VRP) is a prerequisite for efficient freight transport, seamless logistics, and sustainable mobility. This requires algorithms that can quickly produce accurate solutions in minimal computational time. Traditional optimization methods struggle with the real-world complexity of VRPs that involve various constraints and different objectives. Recently, advances in neural combinatorial optimization (NCO), which employs generative artificial intelligence to solve combinatorial problems, have demonstrated mature results with promising perspectives. We present an NCO solution method for a time-constrained capacitated VRP with finite vehicle fleet. Our method incorporates customer constraints dynamically, making it flexible and applicable across various transport logistics scenarios. The pointer amplifier, a mechanism introduced here, prioritizes urgent services during tour generation by directly rescaling attention scores in the pointer network. For capacity constraints, we apply reward function penalties with masking to exclude infeasible actions. The architecture uses an encoder-decoder following the Policy Optimization with Multiple Optima protocol and trained via the Proximal Policy Optimization algorithm. The proposed framework was successfully trained and validated for medium and large instances, providing competitive cost-efficient solutions while exhibiting robustness and generalization, compared with state-of-the-art heuristics. Finally, we provide a critical analysis of the solutions generated by NCO and discuss the challenges and opportunities of this new branch of deep learning algorithms.

Finding a feasible and prompt solution to the Vehicle Routing Problem (VRP) is a prerequisite for efficient freight transportation, seamless logistics, and sustainable mobility. Traditional optimization methods reach their limits when confronted with the real-world complexity of VRPs, which involve numerous constraints and objectives. Recently, the ability of generative Artificial Intelligence (AI) to solve combinatorial tasks, known as Neural Combinatorial Optimization (NCO), demonstrated promising results, offering new perspectives. In this study, we propose an NCO approach to solve a time-constrained capacitated VRP with a finite vehicle fleet size. The approach is based on an encoder-decoder architecture, formulated in line with the Policy Optimization with Multiple Optima (POMO) protocol and trained via a Proximal Policy Optimization (PPO) algorithm. We successfully trained the policy with multiple objectives (minimizing the total distance while maximizing vehicle utilization) and evaluated it on medium and large instances, benchmarking it against state-of-the-art heuristics. The method is able to find adequate and cost-efficient solutions, showing both flexibility and robust generalization. Finally, we provide a critical analysis of the solution generated by NCO and discuss the challenges and opportunities of this new branch of intelligent learning algorithms emerging in optimization science, focusing on freight transportation.