Approved Proposal for Special Session at iCaMaL 2026
Intelligent Methods in System Modeling, Scheduling and Design
Supervision, Analysis, and Management of Transportation Systems with Artificial Intelligence
AI-Driven Scheduling, Logistics Optimization, and Control in Complex Systems
Towards Industry 6.0: AI-Driven Operation and Optimized Scheduling for Industrial Manufacturing
Artificial Intelligence-Driven Scheduling for Manufacturing, Transportation and Logistics
#1 Intelligent Methods in System Modeling, Scheduling and Design
Synopsis of the Special Session:
The increasing complexity of modern industrial and service systems demands a paradigm shift towards intelligent, data-driven, and adaptive methods for their modeling, scheduling, and design. The integration of advanced computational intelligence, machine learning, and data analytics is importantly transforming how systems are conceived, optimized, and controlled. These intelligent methods offer unprecedented capabilities for handling uncertainty, learning from data, and making autonomous decisions, thereby enhancing performance, robustness, and sustainability. This special session aims to bridge the gap between research and practical applications by providing a platform for sharing novel contributions on intelligent methodologies in system modeling, scheduling, and control. We invite contributions on new methodologies, algorithms, and case studies that bridge their advanced research with practical implementation.
Sub-topics of the Special Session
Artificial Intelligence and Machine Learning for Systemm Optimization
Deep Reinforcement Learning for Dynamic Scheduling and Control
Evolutionary Algorithms, Heuristics, and Hybrid Optimization Techniques
Intelligent Agents and Multi-Agent Systems for Distributed Coordination
Intelligent Algorithms in Semiconductor Production and Transportation Control
AI-enhanced Simulation and Emulation for Performance Evaluation
Intelligent Resource Allocation and Task Scheduling
Large Language Models (LLMs) and Generative AI in Process Modeling and Automation
Real-Time Anytime Algorithms for Adaptive Scheduling
Organizers
Bo Huang, Professor, Nanjing University of Science and Technology, e-mail: huangbo@njust.edu.cn
Xiaoyu Lu, Lecturer, Nanjing University of Science and Technology, e-mail: xiaoyu.lu@njust.edu.cn
#2 Supervision, Analysis, and Management of Transportation Systems with Artificial Intelligence
Synopsis of the Special Session:
This special session explores the transformative potential of Artificial Intelligence (AI) in revolutionizing modern transportation systems. We bring together cutting-edge research on AI-driven modeling techniques that capture the complex dynamics of urban mobility, alongside innovative analysis and management approaches that leverage AI technologies, e.g., machine learning, deep learning, reinforcement learning, swarm intelligence, and generative AI, for real-time decision-making. The session addresses critical optimization challenges in intelligent transportation systems, from traffic flow enhancement to resource allocation. Key focus areas include AI-powered perception systems, such as object detection and tracking, as well as reinforcement learning applications for autonomous control. Additionally, the integration of Internet of Things and Internet of Vehicles technologies is crucial for creating connected ecosystems. Furthermore, accurate modeling is necessary for hybrid traffic environments where connected autonomous vehicles coexist with human-driven ones. We examine the robustness and generalization capabilities of AI scheduling methods, ensuring practical deployment across diverse scenarios. Particular attention is devoted to the integration of AI algorithms with conventional operations research models, as well as system modeling, solution methodologies, and deployment of data-driven intelligent decision-making in complex highly-constrained multi-level dynamic environments. Additionally, we investigate the emerging role of large language models in developing intuitive, human-centric scheduling algorithms. This session welcomes contributions spanning theoretical foundations, computational methodologies, and empirical validations. Our goal is to foster dialogue among researchers, practitioners, and policymakers advancing safer, more efficient, and sustainable transportation systems through AI technologies. All accepted papers will be indexed by EI Compendex. Selected papers will be recommended to some special issues for SCI journals (e.g., IEEE T-ITS, T-ASE, and IEEE IoT Journal).
Sub-topics of the Special Session
AI-driven modeling and analysis of transportation systems
AI-powered perception systems including object detection and tracking
Ensemble AI-based models and algorithms with mathematical optimization for scheduling in transportation and logistics
Intelligent algorithms for large-scale optimization
Internet of Things and Internet of Vehicles in transportation systems
AI-based approach for management of transportation systems
Machine learning and data analysis in transportation systems
Control of transportation systems with reinforcement learning
Modeling and simulation of hybrid traffic of connect autonomous vehicles and human-driven vehicles
Generalization performance measurement and improvement of AI-driven scheduling methods in transportation
Large language model-assisted scheduling models and algorithms
Organizers
Liang Qi, Associate Professor, Shandong University of Science and Technology, email: qiliang@sdust.edu.cn
Hua Han, Professor, Shanghai University of Engincering Science, email: 2070967@mail.dhu.edu.cn
Yangming Zhou, Associate Professor, Shanghai Jiao Tong University, email: yangming.zhou@sjtu.edu.cn
Yi-Sheng Huang, Professor, National Ilan University, email: yshuang@niu.edu.tw
Fuxin Zhang, Associate Professor, Shandong University of Science and Technology, email: zhangfuxin@sdust.edu.cn
#3 AI-Driven Scheduling, Logistics Optimization, and Control in Complex Systems
Synopsis of the Special Session:
Modern industrial systems operate at large scale and under highly dynamic, uncertain, and interconnected environments, involving complex interactions among production resources, logistics networks, and control systems. Traditional rule-based or model-centric approaches often struggle to cope with such complexity, especially when facing frequent disturbances, heterogeneous resources, and evolving operational requirements.
AI-driven approaches offer new opportunities to enhance decision-making and automation across planning, scheduling, logistics optimization, and control layers. By integrating data-driven intelligence with domain knowledge and system mechanisms, AI-driven methods enable adaptive scheduling, intelligent logistics coordination, and closed-loop control for complex manufacturing and logistics systems. In particular, the coordinated optimization of production scheduling, transportation, and operational control is becoming a key enabler for achieving efficiency and flexibility in next-generation automated systems.
This special session aims to provide a dedicated forum for researchers and practitioners to present recent advances in AI-driven scheduling, logistics optimization, and control in complex systems within manufacturing, transportation, and logistics domains. The session encourages contributions on methodological innovations, system architectures, and real-world applications that support intelligent and automated operation of industrial systems.
Sub-topics of the Special Session
AI-driven scheduling and planning in manufacturing systems
Intelligent logistics and transportation optimization
Integrated optimization of production, logistics, and control
AI-enabled automation for manufacturing and logistics systems
Data-, knowledge-, and mechanism-integrated decision-making
Digital twin-enabled scheduling, logistics, and operational control
AI-driven multi-agent coordination in manufacturing and logistics
Human-machine collaboration in automated production and logistics
Resource, capacity, and energy optimization in complex systems
AI-driven operation and control of cyber-physical systems
Organizers
Ziyan Zhao, Assistant Professor, Northeastern University, email: zhaoziyan@mail.neu.edu.cn
Lijun He, Assistant Professor, Wuhan University of Technology, email: helj@whut.edu.cn
Dan You, Associate Research Professor, Zhejiang Gongshang University, email: youdan@zjgsu.edu.cn
Wenfeng Li, Professor, Wuhan University of Technology, email: liwf@whut.edu.cn
Shixin Liu, Professor, Northeastern University, email: sxliu@mail.neu.edu.cn
#4 Towards Industry 6.0: AI-Driven Operation and Optimized Scheduling for Industrial Manufacturing
Synopsis of the Special Session:
The advent of Industry 6.0 marks a transformative era in industrial manufacturing, where artificial intelligence (AI), digital twins, predictive analytics, advanced robotics, and smart automation converge to create manufacturing systems that are not only highly efficient but also adaptive, resilient, and capable of self-optimization. Unlike previous industrial revolutions, Industry 6.0 emphasizes seamless integration between humans and intelligent machines, enabling real-time decision-making, autonomous production planning, and predictive maintenance. This convergence facilitates proactive problem detection, dynamic scheduling, and resource optimization, while simultaneously enhancing sustainability, reducing downtime, and improving product quality.
This special issue seeks to explore cutting-edge research, novel methodologies, and practical applications that push the boundaries of intelligent operation, maintenance, and scheduling in industrial processes. Contributions may include, but are not limited to, the development of AI-driven algorithms for predictive and prescriptive maintenance, digital twin-based simulation and optimization of production systems, human–AI collaborative decision-making frameworks, energy-efficient and sustainable manufacturing solutions, and case studies showcasing real-world implementation of Industry 6.0 technologies. By bringing together insights from academia and industry, this special issue aims to highlight the next generation of smart manufacturing practices, providing a roadmap toward fully autonomous, resilient, and adaptive industrial systems.
Sub-topics of the Special Session
Predictive and prescriptive maintenance strategies using machine learning
Optimization of scheduling and resource allocation in complex manufacturing systems
Integration of digital twins for real-time monitoring and decision-making
Human–AI collaboration for enhanced operational efficiency
Energy-efficient and sustainable manufacturing processes enabled by AI
Cyber-physical systems and IoT-enabled intelligent production
Case studies demonstrating Industry 6.0 implementation in industrial settings
Heuristic search algorithms
Intelligent factory
Real-time operation management
Real-time task allocation
Real-time task scheduling
Machine learning and reinforcement learning in manufacturing
Smart sensing and control
Smart logistics management
System simulation and performance evaluation
Sustainability manufacturing
Workstation load balancing in manufacturing, assembly and disassembly
Organizers
Jun Wang, Professor, Shenyang University of Chemical Technology, e-mail: wangjun@syuct.edu.cn
Xu Wang, Associate Professor, Shenyang University of Chemical Technology, e-mail: wangxu@syuct.edu.cn
XiWang Guo, Associate Professor, Liaoning Petrochemical University, e-mail: x.w.guo@163.com
#5 Artificial Intelligence-Driven Scheduling for Manufacturing, Transportation and Logistics
Synopsis of the Special Session:
With the rapid advancement of digitalization and intelligent technologies, the manufacturing, transportation, and logistics sectors are undergoing profound structural transformations. The employment of artificial intelligence (AI) has gone beyond simple automation and system integration, fundamentally reshaping operational logic and decision-making processes across these industries. Currently, AI enables intelligent monitoring and dynamic optimization in manufacturing, transportation, and logistics systems, allowing management and control strategies to be adaptively adjusted based on real time data, thereby enhancing operational efficiency, lowering energy consumption, and minimizing resource waste.
AI is increasingly providing powerful support for addressing the notoriously NP-hard scheduling problems encountered in manufacturing, transportation, and logistics, facilitating a transition from human-experience–based decision to data-driven, intelligent, and adaptive optimization. Advanced techniques such as machine learning, deep learning, reinforcement learning, swarm intelligence, and generative AI have been widely adopted to foster the integration and innovation of intelligent manufacturing, transportation networks, and logistics supply chains. These developments open up a promising frontier for further exploration. As the field continues to evolve, it is essential for researchers and practitioners to remain informed of the latest advancements and actively contribute to the growing body of knowledge on AI applications in these critical domains.
Sub-topics of the Special Session
AI-driven scheduling models in uncertain environments
AI-driven multi-objective and multi-task scheduling
Using AI-driven for human-machine collaborative scheduling;
Applications of AI in dynamic scheduling in transportation and logistics
Implementation of AI for real-time scheduling in manufacturing, transportation and logistics
Applications of AI in supply chain and transportation network designs
AI-driven scheduling strategies for achieving sustainable development goals
AI-driven scheduling in manufacturing and agriculture supply chains
AI-driven scheduling and routing optimization for autonomous systems in manufacturing, transportation and logistics
Organizers
Yaping Fu, Professor, Qingdao University, e-mail: fuyaping@qdu.edu.cn
Kaizhou Gao, Associate Professor, Macau University of Science and Technology, e-mail: gaokaizh@aliyun.com
Xujin Pu, Professor, Jiangnan University, e-mail: puyiwei@ustc.edu.cn
#6 Towards Intelligent and Adaptive Human-Robot Interaction: Motion Planning, Sensing and Control Innovations
Synopsis of the Special Session:
Intelligent and adaptive human-robot interaction has emerged as a pivotal pillar in modern automation systems (e.g., manufacturing, transportation, and logistics). Recent decades have witnessed notable advances in core enabling technologies: flexible sensors for high-fidelity human motion recognition, adaptive motion planning algorithms for robots, and intelligent control strategies tailored to dynamic interaction scenarios. Despite progress in individual technologies, the integration of motion planning, sensing, and control into a cohesive, intelligent adaptive HRI framework is not yet fully optimized for reliable, large-scale practical applications.
The main objective of this special session is to bring together researchers, engineers, and practitioners from both academia and industry to present cutting-edge techniques, technologies, experimental results, fundamental principles, and comprehensive surveys focused on intelligent and adaptive human-robot interaction, with an emphasis on motion planning, sensing, and control innovations.
Sub-topics of the Special Session
Flexible sensor-based human motion recognition and perception for human-robot interaction
Adaptive robot motion planning under dynamic human-robot collaboration scenarios
Intelligent and low-latency human-robot interactive control strategies
AI/ML-driven adaptive control for intelligent human-robot interaction
Safety-aware motion planning for human-robot collaborative tasks in manufacturing/logistics
Organizers
Daojin Yao, Associate Professor, East China Jiaotong University, email: ydaojin@ecjtu.edu.cn
Wentao Dong, Associate Professor, East China Jiaotong University, email: wentao_dong@163.com
Lin Yang, Associate Professor, Huazhong Agricultural University, email: lin.yang@hzau.edu.cn
#7 AI-Driven Systems for Next-Generation Industrial Automation
Synopsis of the Special Session:
AI-Driven Systems for Next-Generation Industrial Automation refers to the development and deployment of intelligent system-level solutions that combine AI with industrial automation to improve the performance, adaptability, and reliability of manufacturing, transportation, and logistics operations. From the perspective of industrial engineering and intelligent automation, AI has long been introduced into automation pipelines to support perception, prediction, planning, scheduling, control, and decision support. By enhancing system awareness, enabling timely responses to disturbances, and assisting operators and autonomous agents in complex environments, AI-driven approaches can substantially improve efficiency and service quality under practical constraints. In recent years, fueled by the rapid progress of industrial digitalization (e.g., cyber-physical systems and Industrial IoT) and the growing demand for real-time, resilient, and sustainable operations, AI-driven industrial automation has attracted broad attention from both academia and industry, showing strong potential in diverse domains such as smart manufacturing, autonomous logistics, intelligent transportation, and integrated production–distribution systems.
The main aim of this special session is to report on the latest advancements in AI-driven systems for next-generation industrial automation, spanning methodologies, system architectures, and practical applications. Special emphasis will be placed on the design of end-to-end automation systems and workflows that connect data acquisition, modeling, decision-making, and execution, as well as on solution approaches for planning, scheduling, routing, resource allocation, and control in dynamic and uncertain environments. This special session will also focus on evaluation practices, including benchmarking, reproducibility, performance assessment under disturbances, and lessons learned from real-world deployments. We expect submitted papers to explore how to build effective automation systems by leveraging problem structures and industrial requirements, and by integrating appropriate techniques from AI, optimization, operations research, control, and hybrid paradigms. It is anticipated that this special session will introduce new system frameworks and solution strategies for a wide range of industrial problems and highlight future research directions toward trustworthy, scalable, and sustainable industrial automation. We welcome theoretical, methodological, and applied contributions that advance this area across manufacturing, transportation, and logistics.
Sub-topics of the Special Session
Novel optimization methods (e.g., mathematical programming, decomposition, matheuristics, metaheuristics, and other optimizers) for industrial automation problems, and so on.
Evolutionary computation and swarm intelligence methods (e.g., multi-objective evolutionary algorithms, memetic algorithms, ant colony optimization, particle swarm optimization, and their variants) for scheduling, routing, and resource allocation, and so on.
Learning-based decision-making for industrial automation (e.g., reinforcement learning, predictive modeling, learning-augmented optimization, transfer and generalization across scenarios), and so on.
Multi-objective and many-objective optimization, preference-based optimization, and decision support for industrial operations, and so on.
Robust, stochastic, and risk-aware optimization under uncertainty, disruptions, and time-varying environments, and so on.
Real-time and online optimization (e.g., rolling-horizon strategies, rescheduling, dispatching, dynamic routing), and so on.
Hybrid frameworks integrating artificial intelligence, optimization, simulation, and control for next-generation industrial automation, and so on.
Applications and case studies in manufacturing, transportation, and logistics (e.g., smart manufacturing scheduling, vehicle routing with time windows and related variants, fleet and warehouse operations, integrated production inventory distribution, emergency logistics, green and sustainable automation), and so on.
Benchmarking, theoretical and empirical analysis, and performance assessment for automation-oriented optimization methods, and so on.
Organizers
Zhiwei Xu, Assistant Professor, Wuhan University of Science and Technology, email: xuzhiwei@wust.edu.cn
Qianqian Yu, Assistant Professor, Wuhan University of Science and Technology, email: yqq@wust.edu.cn
Kai Zhang, Professor, Wuhan University of Science and Technology, email: zhangkai@wust.edu.cn
Mingcheng Zuo, Associate Professor, China University of Mining and Technology, email: mingcheng.zuo@cumt.edu.cn
Javier Del Ser, Professor, TECNALIA, Basque Research and Technology Alliance (BRTA), Derio, Spain / University of the Basque Country (UPV/EHU), email: javier.delser@tecnalia.com
