Artificial Intelligence for Improved Container Loading Efficiency (AI4CL)



This project is funded by the Austrian Research Promotion Agency (FFG) within the AI for Green funding call (FFG project page). The project is a collaboration between the Combinatorial Optimization group at Graz University of Technology and the start-up S2data. The project started in autumn 2024 and will run for 3 years.

Project goals

The goal of the project is to develop new algorithms for container loading problems. The task there is to find an efficient placement of boxes into transport containers such that special loading constraints (e.g., box stacking rules, weight distribution rules, rules about the placement location of dangerous goods) are satisfied. A special focus within this project will be on achieving more efficient and greener transports. From a methodological point of view, the project will involve approaches from different areas of mathematical optimization, computer science and operations research. The developed suite of algorithms will vary strongly in their mathematical foundation. Techniques that we envisage to make use of include mixed-integer programming, column generation, local search algorithms, metaheuristics, tree search based algorithms with neural network state-evaluations and constraint generation approaches. The developed algorithms will be tested and evaluated not only on existing academic benchmark data but also on real industry data.

Project staff

At TU Graz At S2data

Project news