In today’s hyper-connected world, traffic and transportation systems rank among the most complex socio-technical systems. They are distributed, dynamic, and heterogeneous, spanning geographic, organizational, and decision-making boundaries. Their subsystems, ranging from vehicles to infrastructure operators, and mobility platforms, exhibit increasing autonomy and intelligence, while remaining deeply interdependent. Under strong operational, regulatory, and societal constraints, these systems must support real-time decision-making, while ensuring safety, efficiency, equity, resilience, and sustainability under uncertainty. Meeting these competing objectives requires new paradigms for coordination, control, and adaptation at scale.
The availability of large-scale, high-frequency, and multi-modal data from sensors, connected and autonomous vehicles, mobile devices, and digital platforms further increases complexity. This calls for advanced AI techniques enabling scalable reasoning, learning, coordination, and control in dynamic and partially observable environments. Recent advances in multi-agent reinforcement learning, deep learning, foundation and large language models, graph neural networks, digital twins, and hybrid AI are reshaping how intelligent transportation systems are modeled, simulated, and operated. Ensuring robustness, safety, interpretability, fairness, and real-world deployability of such AI-driven systems remains a critical research frontier.
The ATT 2026 workshop aims to bring together researchers and practitioners to exchange ideas and results on how large-scale traffic and transportation systems can be modeled, simulated, controlled, and managed at both micro and macro levels, using autonomous agents and multiagent systems. The workshop welcomes theoretical, methodological, and applied contributions combining machine learning, optimization, control, simulation, and data-driven AI approaches. In particular, work on deep learning and data-centric approaches to address challenges in traffic and transportation are strongly encouraged.
Autonomous and connected vehicles, collaborative driving
Intelligent vehicles, intelligent assistance systems and human involvement
Coordination in intelligent transportation systems and vehicle fleets
Agent based intervehicular communication and V2I communication
Autonomic and autonomous transportation systems
Intelligent Optimization (e.g., traffic assignment, routing, route choice)
Distributed decision making in traffic, transportation and transport logistics
Self-* properties and theory of intelligent traffic and transportation systems
Intelligent, adaptive, and learning-based traffic control
Multi-agent reinforcement learning and game-theoretic approaches
Data-driven approaches in the domain of traffic and transportation
Deep learning and graph-based architectures for spatio-temporal traffic data
Intelligent monitoring of transportation systems, data collection, filtering, prediction and distribution of traffic information and transportation data
Agent-based simulation of traffic and transportation systems and their behavior
Microscopic modeling of vehicle, pedestrian, and traveler behavior
Agent-based pedestrian and crowd simulation
Digital twins for traffic operations and mobility planning
Verification, validation, and testing of intelligent transportation systems
Shared mobility systems, e.g., car-sharing, ride-sharing, bike and e-scooter sharing
Multi-modal journey planning and mobility orchestration
Mobility-as-a-Service (MaaS) platforms and ecosystems
Smart transportation systems leveraging mobile and edge devices
Applications in traffic, mobility, and transport logistics
Future mobility technologies and concepts