AI Planner of the Future

December 2020 - November 2025

Operations, Planning and Control


Information Systems

Technology, Innovation & Society

Tom van Woensel (overall project lead)

Nevin Mutlu

Laurens Bliek

Frauke Behrendt

€ 2,2 M EUR      


The instant exchange of data offered by the Internet of Things enables optimization of key operational processes in supply chains and logistics. Yet, transforming the operations of supply chains and logistics to fully benefit from these emerging evolutions is challenging.

Decision-making in supply chains and logistics is complex and different from other areas as it involves many intertwined multi-disciplinary decisions (e.g., transport, inventory, location, human resources, ICT systems) and key performance indicators (including people, profit and planet dimensions as well as other dimensions such as ethics and corporate social responsibility).

This project focuses on developing supply chain and logistics planning based on a hybrid form of decision-making in which both human and artificial intelligence are combined to be able to properly handle the complexity.

A unique approach

Our perspective on AI supply chain and logistics planning is a unique approach that is highly relevant for businesses and academia, and it calls for different methodological approaches than the classical AI planning approaches that have been explored so far. While there is quite some practical evidence of working AI-enabled environments, e.g. smart thermostats, home service robots, intelligent conversational chatbots, autonomous drones, or even self-driving cars, decision-making in supply chain and logistics is different from decision-making in these areas.

Processes within supply chain and logistics environments are highly complex, interdependent, and intertwined. Increasing process efficiencies lead to improved agility and transparency in the supply chain. These efficiencies are enabled by, for example, advanced analytics, AI, and blockchain. As such, supply chain and logistics data are activated and used to proactively mitigate disruption and simplify these processes. Moreover, enabled by (real-time) data, supply chain visibility on the order process, inventory, delivery, and potential supply chain disruptions is facilitated. Advanced embedded AI capabilities provide real-time intelligence and actionable planning recommendations. Supply chain and logistics planning also requires the inclusion of harder-to-measure concepts such as human (interaction), sustainability, and ethical concerns, creating a distinct perspective and following recent calls in the literature (e.g., Sanders et al. 2019). The Human In-The-Loop (HITL) versus the Human Out-of-The-Loop (HOTL) situation is an important planning aspect to be considered here as well. Note that not only monetary aspects are important (e.g., cost reductions) but it is also important to investigate (if and) how AI enables supply chains and logistics to make a major contribution towards reducing greenhouse gas emissions (Dauvergne 2020) and the sustainability element of companies’ Corporate Social Responsibility (CSR) agenda.

Human and AI-enabled decisions



The role and contribution of AI to classical planning is identified as a key AI application domain before but has remained “a largely unsolved core AI competency due to the complexity of the tasks both in terms of representation as well as reasoning” (Sreedharan et al. 2020). We address this gap by alleviating the complexity of fully automated reasoning with abundant human expert and domain knowledge, leading to human and artificial intelligence enabled decision-making and support systems, with a focus on supply chains and logistics. Concluding, planning as we know it is certainly dead, but we envision the planning “nouveau” to be a “hybrid” form of decision-making in which both human and artificial intelligence are combined.

In order to research the explicit intertwining of technical and human elements in the context of AI planning for supply chains and logistics, the program needs a broad range of research fields and a rich set of involved companies. Hence, it combines the extensive knowledge of researchers from all multi-disciplinary IE&IS domains and the real-life living labs of European Supply Chain Forum companies from diverse industries.

The research program is a unique research and valorization network. It combines 25 Artificial Intelligence researchers from all multi-disciplinary IE&IS domains, 12 PhD students, and over 50 Bachelor and Master students, for five years (2021-2026).




Within the setting of decision-making where both human and artificial intelligence interact and meet each other, the following 12 PhD projects have been identified:

Learning about customers: Demand implications of logistics-related decision-making in B2B

Sarah Gelper, Nevin Mutlu, Fred Langerak

Context matters: optimizing shared decision making in real-world forecasting and inventory management

Pascale Le Blanc, Philippe van de Calseyde, Anna-Sophie Ulfert-Blank

AI-based replenishment and order fulfillment strategies for omnichannel supply chains

Zümbül Atan, Albert Schrotenboer, Tom Van Woensel

Food valorisation in sustainable supply chains

Ahmadreza Marandi, Sonja Rohmer, Tom Van Woensel

Digital Twins: An ingenious AI companion or an evil twin?

Néomie Raassens, Jeroen Schepers, Tom Van Woensel

AI for sustainable last-mile delivery by micro mobility: a socio-technical perspective

Frauke Behrendt, Floor Alkemade

Data-driven optimization using Digital Twins for sustainable last-mile delivery

Yingqian Zhang, Laurens Bliek, Tom Van Woensel

Online supply chain planning

Remco Dijkman, Willem van Jaarsveld

From feared competitor to trusted companion: understanding and enhancing trust in AI over time

Chris Snijders, Gerrit Rooks, Marijn Willemsen

Widening the Frame: Improving Automated Rational Choice through Metacognition

Diego Morales, Vincent Müller, Patrik Hummel, Dirk Fahland

Human decision making in production planning systems: How do superior information and systematic bias impact the performance?

Lijia Tan, Ton de Kok, Rob Basten

Data-driven robust optimization approach: theory and human decision-makers

Lijia Tan, Ahmadreza Marandi, Rob Basten

Funded by