This study addresses the two-dimensional weakly homogeneous Bin Packing Problem (2D-BPP) in the context of robotic packing, where items must be arranged in a manner feasible for robotic manipulation. Traditional heuristics for this NP-hard problem often lack adaptability across diverse datasets, while metaheuristics typically suffer from slow convergence. To overcome these limitations, we propose a novel neural-driven constructive heuristic. The method employs a population of simple feed-forward neural networks, which are trained using black-box optimization via the Covariance Matrix Adaptation Evolution Strategy (CMA-ES). The resulting neural network dynamically scores candidate placements within the constructive heuristic. Unlike conventional heuristics, the approach adapts to instance-specific characteristics without relying on predefined rules. Evaluated on datasets generated by 2DCPackGen and real-world logistic scenarios, the proposed method consistently outperforms benchmark heuristics such as MaxRects and Skyline, reducing the average number of bins required across various item types and demand ranges. The most significant improvements occur in complex instances, with up to 86% of 2DCPackGen cases yielding superior results. This heuristic offers a flexible and extremely fast, data-driven solution to the algorithm selection problem, demonstrating robustness and potential for broader application in combinatorial optimization while avoiding the scalability issues of reinforcement learning-based methods.

The paper presents a novel approach to instant on-the-road electric vehicle charging scheduling planning. It benefits from a mixed-integer mathematical optimization model employed to efficiently select charging stations along the route. It also utilizes machine learning models to approximate the traction battery state of charge using data on driving conditions (energy, speed, travel time, etc.) for individual route sections, considering the driver’s habits and preferences. The research details the functional requirements of this procedure application and its architecture. A step-by-step description of the optimization model is provided, in particular, the constraints responsible for the non-linear model of charging time, the varying time zone-dependent trip parameters (including rush hours), as well as the used optimization criteria, and the scalarization methods. Unlike other existing methods, the combination of the aforementioned mixed-integer mathematical optimization model and machine learning predictors allows for consideration of several factors and adaptation to actual data. Experiments are carried out on the operation of the application, including very long routes (with the actual Warsaw-Zakopane, 412 km long test drives). The results show enhanced, satisfactory execution times, from 0.088 [s] (for a simple model without time zones and with a linear charging model) to 0.365 [s] (for a model without time zones and with a non-linear charging model).

Long-term archiving of digital resources is a serious problem that has not yet found sufficient attention from the IT industry, nor widely available solutions. Preservation of usability of stored resources in the digital archive requires not only reliable storage of data files, but also the possibility of efficient searching, as well as verification of data authenticity and its correct interpretation both in the technical (data format, etc.), and semantic sense (information understanding in an appropriate context, etc.). The paper discusses these problems and presents solutions adopted in the CREDO project.

Lexicographic max-min (LMM) optimization is of considerable importance in many fairness-oriented applications. LMM problems can be reformulated in a way that allows to solve them by applying the standard lexicographic maximization algorithm. However, the reformulation introduces a large number of auxiliary variables and linear constraints, making the process computationally complex. In this paper, two approximation schemes for such a reformulation are presented, resulting in problem size reduction and significant performance gains. Their influence on the quality of the solution is shown in a series of computational experiments concerned with the fair network dimensioning and bandwidth allocation problem.