Our current development project focuses on how goods get into the package—specifically, the "perfect package." We are using AI to help make the packing process more efficient and optimize shipping, making both more economical and environmentally friendly without compromising delivery times.
Together with our project partners from the Institute for Materials Handling and Logistics at the Karlsruhe Institute of Technology (KIT) as well as the software company specializing in intralogistics TUP , our AI experts at AMAI aim to present initial results in the form of a demonstration using real-world data by the end of the year. The project is funded by the "AI Innovation Competition Baden-Württemberg" of the Ministry of Economic Affairs, Labour and Housing of the State of Baden-Württemberg. By supporting innovative and complex collaborative research projects, the initiative aims to accelerate the transfer of AI technologies and knowledge, particularly to small and medium-sized enterprises, ensuring they remain competitive in global markets in the future.
Today, however, picking, packing, and transport processes are often characterized by inefficiency, prioritizing fast delivery times at the expense of resources and CO2 emissions. With the rapid annual growth in parcel shipping—a trend accelerated by the COVID-19 crisis—companies and institutions, especially in B2C e-commerce, have enormous potential for savings if they take a more holistic view of their logistics processes rather than focusing solely on outbound speed. The "perfect package" addresses exactly this, ensuring that packages are packed more efficiently in the future—meaning less empty space, less packaging waste, and fewer transport runs due to smaller package sizes. Delivery times remain unaffected, ensuring customers continue to receive their orders promptly.
This is made possible by AI-based reinforcement learning. While complex algorithms have previously only been able to solve and improve individual sub-tasks independently, "reinforcement learning" allows the artificial intelligence to represent and solve the entire process holistically, accounting for all interactions and interdependencies. Compared to complex algorithms, AI-based methods have significantly shorter runtimes and require less computing power. At the same time, the AI can be continuously optimized through reinforcement learning, allowing it to adapt to a wide variety of warehouse configurations and business models. It not only suggests the best possible utilization of transport vehicles but also determines which ordered items should be packed together and how they should be positioned for optimal results.
This innovative AI solution for logistics shapes the packing and shipping processes of the future, making them more economical and environmentally friendly without compromising delivery times. At AMAI GmbH, our AI experts are happy to advise you on AI, reinforcement learning, or the optimization of your (logistics) processes using artificial intelligence.
