The MIT Intelligent Logistics Systems Lab (ILS) is dedicated to advancing the science and practice of logistics through the integration of operations research, artificial intelligence, and machine learning. We develop innovative methods and decision-support systems that address some of the most complex and high-impact challenges facing modern logistics and supply chain operations.
The ILS Lab brings together academic researchers, industry practitioners, and public-sector stakeholders to design, test, and deploy intelligent logistics solutions that are data-driven, scalable, and grounded in real-world operational constraints. The lab’s work spans strategic, tactical, and operational decision-making across freight transportation, warehousing, last-mile delivery, healthcare logistics, and autonomous systems.
Building on the legacy of the MIT Megacity Logistics Lab, the ILS Lab continues its leadership in urban and last-mile logistics, while expanding its scope to include autonomous technologies, collective system behavior, and human–AI collaboration. The lab’s overarching mission is to enable logistics systems that are more efficient, resilient, sustainable, and customer-centric, and that can continuously adapt to uncertainty, disruption, and rapid change.
Research Areas
Predictive Intelligence for Time-Critical Logistics
The ILS Lab develops advanced predictive models that leverage machine learning, generative AI, and large-scale spatio-temporal data to anticipate short-term and near-term logistics dynamics. This includes forecasting demand, congestion, operational bottlenecks, and service risks in highly dynamic environments such as urban delivery networks and time-critical medical logistics. These predictive capabilities support faster, more reliable logistics services and enable proactive operational decisions rather than reactive responses.
Prescriptive Intelligence and Optimization Under Uncertainty
A core research area of the lab focuses on combining operations research with AI to solve complex, large-scale optimization problems. The lab develops hybrid prescriptive models for challenges such as network design, routing, inventory positioning, and warehouse operations, explicitly accounting for uncertainty, non-linear trade-offs, and real-world constraints. A strong emphasis is placed on interactive and computationally efficient models that allow decision-makers to explore scenarios and stress-test strategic and operational choices in real time.
Autonomous and Robotic Logistics Systems
The ILS Lab explores how autonomous technologies—including mobile robots, automated material handling systems, and unmanned aerial systems—can be effectively integrated into logistics operations. Research in this area focuses on learning-based control, adaptive navigation, and system-level performance optimization in environments shared with humans and other machines. The lab investigates how autonomy can improve productivity, safety, and robustness while reducing reliance on rigid, pre-defined rules and workflows.
Collective Intelligence and Multi-Agent Coordination
Modern logistics systems increasingly rely on fleets of interacting agents—robots, vehicles, facilities, and human operators—whose decisions are interdependent. The ILS Lab studies collective intelligence mechanisms that enable coordinated, system-level optimization rather than isolated local decisions. Drawing inspiration from natural and engineered multi-agent systems, this research develops AI-driven coordination, task assignment, and resource allocation methods that scale effectively as system size and complexity grow.
Augmented Intelligence and Decision Support
The lab investigates how human expertise can be enhanced—not replaced—by intelligent decision-support systems. This research focuses on visual analytics, interactive simulation, and human-in-the-loop optimization tools that help decision-makers understand complex trade-offs, explore alternatives, and build consensus. By combining advanced analytics with intuitive interfaces, the ILS Lab enables more transparent, explainable, and actionable use of AI in logistics planning and operations.
Strategic Partnership with Mecalux
A cornerstone of the MIT Intelligent Logistics Systems Lab is its strategic research partnership with Mecalux, a global leader in intralogistics technology and warehouse automation. This collaboration provides the foundation for the lab’s mission to advance intelligent, data-driven logistics systems that are both scientifically rigorous and operationally relevant.
The partnership combines MIT’s academic leadership in operations research, artificial intelligence, and machine learning with deep industry expertise and real-world operational insight. Through this collaboration, the ILS Lab is able to ground its research in real logistics challenges while exploring forward-looking solutions that push the boundaries of current practice.
Support from Mecalux enables the lab to pursue ambitious, high-impact research on topics such as autonomous warehouse systems, multi-agent coordination, AI-driven optimization, and next-generation decision-support tools. The partnership also accelerates the translation of research outcomes into practice, ensuring that new methods, models, and technologies can be tested, validated, and refined in realistic operational contexts.
Beyond funding, the collaboration fosters an ongoing exchange of ideas between researchers and practitioners, helping shape research agendas that address pressing industry needs while contributing to long-term innovation in logistics and supply chain management. Together, MIT CTL and Mecalux aim to set new standards for efficiency, resilience, and operational excellence in intelligent logistics systems.
From Research to Real-World Impact
A defining characteristic of the ILS Lab is its strong connection to real operational challenges. Research projects are designed not only to advance academic knowledge, but also to produce deployable prototypes, decision-support tools, and validated methodologies that can inform practice and policy. Through close collaboration with industry and public-sector partners, the lab ensures that its work remains relevant, implementable, and impactful.
By integrating predictive, prescriptive, autonomous, collective, and augmented intelligence, the MIT Intelligent Logistics Systems Lab is shaping the next generation of logistics systems—systems that are smarter, more adaptive, and better equipped to serve society in an increasingly complex and fast-paced world.
What the Partners Say
“We are thrilled to support MIT CTL in this new research venture, as it aligns with our vision of integrating autonomous technologies and smart systems into logistics processes. This partnership will drive research-based innovation into practice and set new standards for operational excellence in the industry.”
— Javier Carrillo, CEO, Mecalux
“This new lab represents a significant step forward in our mission to innovate and improve global logistics systems. With the support of Mecalux, we are confident that our research will lead to groundbreaking advancements in the field.”
— Prof. Yossi Sheffi, Director, MIT Center for Transportation & Logistics
“We aim to harness the power of AI and machine learning in combination with state-of-the-art optimization methods to tackle the most significant real-world challenges facing the logistics industry today.”
— Dr. Matthias Winkenbach, Director of Research, MIT Center for Transportation & Logistics
