Special Sessions

• Dr. Giovanni Campuzano, Department of Maritime and Transport Technology, Delft University of Technology, The Netherlands
• Prof. dr. Martijn Mes, Department of High-tech Business and Entrepreneurship, University of Twente, The Netherlands

Summary of the scope: Reinforcement Learning (RL) has become a powerful approach for tackling sequential decision-making challenges in logistics, with applications spanning vehicle routing, port operations, airline scheduling, and warehouse management. By learning from interactions with dynamic environments and prioritizing long-term rewards over short-term gains, RL offers a robust framework for handling uncertainty in logistics operations.

This session will bring together researchers and practitioners to explore recent advancements in RL for logistics, bridging theoretical insights with real-world implementations. Discussions will cover a range of RL techniques—including value- and policy-based methods, hybrid approaches, and agent-based RL—highlighting their role in optimizing decision-making. A key focus will be on integrating RL with traditional heuristics and metaheuristics to enhance search strategies, improve real-time decision-making, and dynamically adjust parameter controls for better exploration-exploitation balance.

We invite contributions from researchers working at the intersection of artificial intelligence and operations research, addressing critical challenges such as generalization across problem instances, interpretability of learned policies, and computational efficiency. Submissions covering theoretical innovations, practical applications, and benchmarking studies that demonstrate the impact of RL in logistics are highly encouraged.

• Prof. Dr. Frank Phillipson (TNO & Maastricht University)

Summary of the scope: Recent advancements in quantum computing have the potential to revolutionize computational logistics, a field heavily influenced by operations research and artificial intelligence. Quantum computing offers novel capabilities for solving complex optimization problems such as route planning, scheduling, inventory management, and supply chain design, which are often constrained by the computational limits of classical methods. This session will explore how quantum algorithms, such as quantum annealing and variational quantum algorithms (VQAs), can tackle computational challenges in logistics.

The session will focus on the intersection of quantum computing and logistics, highlighting both theoretical breakthroughs and practical applications. Topics will include:

• Optimization and Scheduling: Demonstrating the application of quantum methods to optimize delivery routes, minimize energy consumption, and streamline resource allocation.
• Supply Chain Management: Investigating quantum approaches to model and manage uncertainty in supply chains, such as stochastic demand and fluctuating lead times.
• Hybrid Quantum-Classical Solutions: Discussing how hybrid models leverage quantum computing’s strengths alongside classical techniques to handle real-world logistics problems.
• Scalability and Practicality: Addressing the current challenges in integrating quantum computing into logistics, including hardware limitations, algorithm design, and case studies of successful implementations.

The session will also discuss the implications of quantum advancements for industries such as e-commerce, transportation, and manufacturing, offering insights for researchers, practitioners, and decision-makers in the logistics sector. By bridging the gap between emerging quantum technologies and real-world logistical challenges, this session will illuminate a path toward the next era of computational logistics.

• Dr. Yongqiu Zhu, co-director of the Decision Science for Mobility Lab in the Department of Transport and Planning, TU Delft, the Netherlands
• Dr. Mahnam Saeednia, co-director of Freight Transport & Logistics Lab in the Department of Transport and Planning, TU Delft, the Netherlands

Summary of the scope: Rail-based passenger and freight transport each face unique operational complexities, which become even more pronounced when sharing infrastructure. Passenger rail systems must adhere to strict timetables, ensuring punctuality and high-frequency service to meet demand, while freight transport requires flexibility to accommodate varying cargo volumes, long-haul operations, and unpredictable delays. The complexity further increases when disruptions and disturbances occur, such as infrastructure failures, extreme weather events, or demand fluctuations, affecting service reliability and user experience.

The rapid advancement of learning-based methodologies is reshaping decision-making processes in rail-based public transport systems, offering transformative opportunities for both passenger and freight transportation. This special session aims to provide a platform for exploring diverse applications of machine learning and artificial intelligence techniques, including  Bayesian decision-making, reinforcement learning, multi-agent systems, and hybrid approaches that integrate ML with traditional optimization methods to address key challenges in the field.

Topics of interest include, but are not limited to: handling large-scale optimization problems, improving robustness against expected demand fluctuations, service time uncertainties, improving resilience to unexpected disruptions (e.g., natural disaster, incidents), and incorporating strategic interactions among multiple stakeholders in the decision-making process. We welcome contributions within the scope of rail-based public transport, covering passenger transport, freight transport, or their integration (Freight-on-Transit).

Prof. Dr. Lin Xie, Chair of Information Systems and Business Analytics, Brandenburg University of Technology, Germany

Summary of the scope: The increasing complexity of warehouse operations requires intelligent decision-making for tasks such as storage allocation, order fulfillment, and robotic coordination. Operations Research (OR) has long provided effective solutions through exact algorithms, heuristics, metaheuristics, and simulation, while Artificial Intelligence (AI) offers new capabilities with machine learning, reinforcement learning, and deep learning. The combination of OR and AI is now unlocking even greater efficiency, scalability, and adaptability in warehouse logistics.

This session invites contributions from OR, AI, and hybrid approaches, covering topics such as:

• OR for Warehousing:
  • Exact algorithms (MILP, CP), heuristics, metaheuristics (ALNS, tabu search).
  • Simulation-based decision-making for dynamic warehouse environments.
• AI for Warehouse Optimization:
  • Machine learning for demand forecasting, inventory control, and adaptive slotting.
  • Reinforcement learning for real-time decision-making and robotic fleet management.
• Hybrid AI-OR Approaches:
  • AI-enhanced heuristics and metaheuristics.
  • Combining reinforcement learning with OR models for adaptive strategies.
  • Simulation-optimization frameworks integrating AI-driven learning.
• Automation and Robotics in Warehousing:
  • OR-based scheduling and AI-driven task allocation
  • Motion planning, path optimization, and self-learning warehouse automation

This session brings together academics, researchers, and industry professionals to discuss cutting-edge methodologies and real-world applications in warehouse optimization. We welcome theoretical advancements, algorithmic innovations, and case studies demonstrating how OR, AI, and their integration are transforming modern logistics.

• Dr. Nadia Pourmohammadzia, Assistant Professor, Data-driven methods in Port and Waterways,  Faculty of Civil Engineering, TU Delft
• Dr. Mahnam Saeednia, Assistant Professor, AI in Freight Transportation and Logistics, Faculty of Civil Engineering, TU Delft

Summary of the scope: We are pleased to invite you to contribute to the ICCL25 conference at the Technical University of Delft (TUD) in September 2025. The session on “ Smart Solutions for Resilient Port-Hinterland Connections” explores the resilience of port-hinterland connections, examining the disruptions and challenges affecting multimodal freight transportation.  As global trade becomes more complex and vulnerable to various disruptions—such as natural disasters, climate change, operational failures and variations, and geopolitical tensions— ensuring the resilience of transport networks beyond the port gates has never been more critical. This session will highlight strategies to enhance the adaptability and efficiency of port-hinterland connections, safeguarding the smooth movement of freight across waterborne supply chains.

This session invites contributions on the resilience of ports and hinterland transport connections, focusing on adaptation to both short-term disruptions (such as extreme weather events, traffic incidents, and system failures) and long-term challenges (including infrastructure deterioration, climate change impacts, and policy shifts). We welcome research that proposes innovative solutions, technologies, and strategies to strengthen the adaptability and efficiency of these critical transport networks.

• Topics of interest include but are not limited to:
• Best Practices and Case Studies, real-world applications of smart solutions in enhancing resilience.
• Mitigating the impact of disruptions in port-hinterland transportation logistics
• Port and inland waterway connection at times of drought
• The Role of infrastructure investment and design in enhancing resilience
• Resilience in the Context of Climate Change and Environmental Challenges
• AI and Predictive Analytics for Disruption Management
• Digital Twins and Simulation Technologies to enhance decision-making and scenario planning.
• IoT and Sensor-Based Monitoring and Smart tracking systems for real-time visibility of cargo, infrastructure conditions, and traffic flow.
• Smart Multimodal Coordination Platforms for optimizing hinterland transport choices and reducing bottlenecks.