Exploration is underway for new AI applications in the logistics sector. One recent advancement was announced on December 3 by The Massachusetts Institute of Technology Center for Transportation & Logistics (MIT CTL) and intralogistics group Mecalux.
They have begun a five-year collaborative project to expedite the integration of self-learning artificial intelligence (AI) in logistics through MIT’s Intelligent Logistics Systems Lab.
“The objective of our collaboration with Mecalux is to foster disruptive innovation and achieve two highly impactful use cases where AI transforms industry decision-making," says Dr. Matthias Winkenbach, director of research at MIT CTL and the Intelligent Logistics Systems Lab, in a statement. "We will train complex self-learning machine learning models to ultimately reduce costs, lower carbon footprints, and improve service quality for customers.”
During the first year of the project two key research areas to accelerate innovation will be developed. The first will focus on increasing the productivity of autonomous warehouse robots. Using advanced simulation, optimization, and machine learning techniques, researchers will develop a “swarm intelligence” system enabling multiple robots to operate as a single entity, making collective decisions.
“We aim to create a new generation of autonomous robots that learn from human behavior to foster greater collaboration and efficiency in warehouses,” says Winkenbach.
The second research area will focus on training self-learning AI models. The Intelligent Logistics Systems Lab will design systems capable of learning from demand patterns and anticipating new customer purchasing habits.
“Current distribution systems fail to account for the full complexity of logistics networks and often make strong simplifying assumptions," says Winkenbach. "This project seeks to help companies operating large networks of warehouses, distribution centers, and stores automatically determine the most efficient way to fulfill each order taking into account the real-time status of the distribution network.”
