Human-MASS Interaction in Decision-Making for Safety and Efficiency in Mixed Waterborne Transport Systems

The thesis by Dr. Rongxin Song explores the integration of Maritime Autonomous Surface Ships (MASS) into Mixed Waterborne Transport Systems (MWTS), addressing critical challenges in ensuring navigational safety and operational efficiency. 

Dr. Rongxin Song

Delft University of Technology - PhD candidate, section Safety & Security Science

Recognising the complexities of interactions in MWTS, especially in scenarios without direct communication between vessels, the research develops a decision-making framework that integrates situational awareness, human preference-aware navigation, and trust dynamics. These components collectively aim to support seamless interactions between autonomous and manned vessels, ensuring safe and efficient navigation in the MWTS.

The proposed framework builds on a systematic exploration of key challenges in MASS operations. For situational awareness, an ontology-driven knowledge maps model is introduced, enabling MASS to integrate multi-source data and maritime regulations. This model is further combined with a Dynamic Window Approach (DWA) path planner, allowing for real-time compliance with COLREGs and proactive collision avoidance. The research also advances human-preference-aware navigation by extracting and modeling navigational behaviours of manned vessels using AIS data. An LSTM-autoencoder with clustering methods is utilised to identify navigational preferences, which are then incorporated into a trajectory prediction model based on Multi-Task Learning Sequence-to-Sequence LSTM with attention architectures. This integration enhances MASS decision-making by aligning manoeuvring strategies with human operators’ expectations, reducing the likelihood of misinterpretation in mixed traffic scenarios.

Additionally, the dynamics of human trust in MASS are explored through experimental studies and modelled using a Bayesian Network. The analysis reveals how trust evolves across navigation stages, influenced by decision-making strategies and timing, and demonstrates the cascading effects of intermediate trust levels on overall operator confidence. The model offers guidance for designing transparent and dependable MASS behaviour to support adoption. 

The research underscores the dual priorities of safety and efficiency throughout the framework. Safety is addressed by ensuring effective situational awareness and collision avoidance capabilities, while efficiency is enhanced by optimising travel time, reducing resource consumption, and minimising navigational delays. Together, these contributions offer a foundation for improving MASS operations in MWTS.

Despite its contributions, the research has limitations. The validation primarily relies on simulation-based experiments, which may not fully capture the complexities of real-world maritime conditions, such as varying sea states and traffic densities. Additionally, the geographic scope and vessel types analysed are restricted, and computational challenges in high-density scenarios remain underexplored. Future work should involve field trials, broader operational scenarios, and refinement of trust models with physiological feedback. 

In summary, the thesis by Song proposes an integrated decision-making framework that addresses the critical aspects of situational awareness, human preferences, and trust in autonomous navigation. By bridging key gaps in transparency, adaptability, and reliability, the research lays a solid foundation for safe, efficient, and collaborative MASS operations in MWTS, supporting the maritime industry’s transition towards more autonomous and intelligent systems.

Click here to read Dr. Rongxin Song's PhD thesis.