The Massachusetts Institute of Technology (MIT) Center for Transportation & Logistics (CTL) is investigating potential of machine learning (ML) and artificial intelligence (AI) to transform the future of logistics operations and goods transportation.
It is doing this by commissioning a new research lab, Intelligent Logistics Systems, which will examine several research streams that may lead to new state-of-the-art approaches to address some of the industry’s most complex challenges.
For instance, the lab will investigate cutting edge methods and tools that are capable of producing highly accurate near-term predictions at a high spatial and temporal resolution. Such near-term predictive capabilities are critical in enabling same-day or sub-same-day delivery and similar services designed to meet the increasingly challenging needs of both consumers and commercial customers.
The lab was funded by Mecalux.
This innovation space will be led by Dr. Matthias Winkenbach, Director of Research at MIT CTL. “We want to support the application of new AI- and machine-learning-based technologies to tackle the most impactful real-world challenges faced by companies and society,” says Winkenbach.
Technology for operational excellence
The activities of the new research lab at MIT CTL will enable the entire industry to design supply chains and logistics systems that provide state-of-the-art customer service and set new standards in terms of sustainability and cost-effectiveness.
“Operational excellence relies on the seamless integration of autonomous technology into warehouse processes. AI and machine learning can be crucial in planning and monitoring these resources,” says Javier Carrillo, CEO of Mecalux, which funded the lab. in a statement.
The Intelligent Logistics Systems Lab at MIT CTL will also study the role of new technologies in controlling autonomous transportation and delivery systems and in automating processes such as picking, sorting, packing, and shipping orders from warehouses or stores.
Another area of research will be the development of hybrid methods at the intersection of operations research (OR) and ML. The goal will be to solve the increasingly complex and multi-faceted combinatorial optimization problems that are crucial for the success of the logistics industry, including vehicle routing, inventory planning, network design, transportation planning, and related issues.
