Periodic Reporting for period 2 - AUTOBarge (European training and research network on Autonomous Barges for Smart Inland Shipping)
Reporting period: 2023-10-01 to 2025-09-30
According to the European Commission, passenger transport is projected to increase 42% by 2050, and freight transport up to 60%. Needless to say, this puts an enormous burden on transport networks and our environment. Compared to other modes of transport – which often face congestion and capacity problems – inland waterway transport is characterised by reliability, energy efficiency and a capacity for increased use. More than 37,000 km of waterways connect hundreds of cities and industrial regions in Europe. In the EU, 13 countries share an interconnected waterway network, highlighting the potential for increasing the modal share of inland waterway transport. This will not happen unless we can make inland waterways economically competitive. However, with crew costs accounting for 60% of the total cost, autonomous inland vessels represent an exciting disruptive technology.
AUTOBarge seized this opportunity by unlocking the innovation potential of Europe’s inland waterways through advanced research and high-level training. Europe’s rivers and canals constitute a valuable transport infrastructure that has long been underutilised. With recent developments in automation and digital technologies, these waterways can be exploited more intensively without the environmental impact associated with constructing new roads or airport infrastructure. The 15 early-stage researchers trained within AUTOBarge have taken important steps towards enabling this transformation.
AUTOBarge offered the first-ever training programme for the application of unmanned or autonomous vessels for smart inland shipping and their role in the overall multi-modal transport activity in Europe and had three scientific/technical objectives:
Objective 1 (WP1): Maximize the situational awareness (Sense and Understand) of an unmanned or autonomous inland vessel by covering the state and manoeuvrability of the vessel itself, the location and motion of other vessels, other relevant static and moving objects in the vicinity, features like buoys or traffic signs, as well as the wireless communication of information between the different waterway actors.
Objective 2 (WP2): Exploit the above situational awareness (Decide and Act) obtained for a safe, robust and energy-efficient path planning and motion control of the autonomous inland vessel with a focus on model predictive control, control methods supported by real-time machine learning, energy-efficiency, and fault identification and isolation schemes such that those do not affect the operation of autonomous vessels in a negative way.
Objective 3 (WP3): In-depth analysis of the socio-technical, economic and legal aspects that are needed to make autonomous inland shipping a success in the near future, including safety assurance, collaborative decision making for maximized performance, logistics, economic benefits, and the required changes to the regulatory framework.
AUTOBarge seized this opportunity by unlocking the innovation potential of Europe’s inland waterways through advanced research and high-level training. Europe’s rivers and canals constitute a valuable transport infrastructure that has long been underutilised. With recent developments in automation and digital technologies, these waterways can be exploited more intensively without the environmental impact associated with constructing new roads or airport infrastructure. The 15 early-stage researchers trained within AUTOBarge have taken important steps towards enabling this transformation.
AUTOBarge offered the first-ever training programme for the application of unmanned or autonomous vessels for smart inland shipping and their role in the overall multi-modal transport activity in Europe and had three scientific/technical objectives:
Objective 1 (WP1): Maximize the situational awareness (Sense and Understand) of an unmanned or autonomous inland vessel by covering the state and manoeuvrability of the vessel itself, the location and motion of other vessels, other relevant static and moving objects in the vicinity, features like buoys or traffic signs, as well as the wireless communication of information between the different waterway actors.
Objective 2 (WP2): Exploit the above situational awareness (Decide and Act) obtained for a safe, robust and energy-efficient path planning and motion control of the autonomous inland vessel with a focus on model predictive control, control methods supported by real-time machine learning, energy-efficiency, and fault identification and isolation schemes such that those do not affect the operation of autonomous vessels in a negative way.
Objective 3 (WP3): In-depth analysis of the socio-technical, economic and legal aspects that are needed to make autonomous inland shipping a success in the near future, including safety assurance, collaborative decision making for maximized performance, logistics, economic benefits, and the required changes to the regulatory framework.
ESR01 (Yan-Yun Zhang, KU Leuven) focused on short-horizon trajectory prediction, supporting real-time control and decision-making. Representative manoeuvring scenarios including straight sailing, bend following, turning at pivot point, and evasive manoeuvres were emphasized.
ESR02 (Martin Baerveldt – NTNU) focused on algorithms combining Multiple Extended Object Tracking (MEOT) and Simultaneous Localization and Mapping (SLAM) using LiDAR data, enhancing MEOT for LiDAR and incorporating map data for localization.
ESR03 (Zhongbi Luo – KU Leuven) developed and published a framework using LiDAR-GNSS fusion for live chart updates of Inland Electronic Navigational Charts (IENCs) turning them into dynamic, real-time systems for autonomous vessels.
ESR04 (Hoang Anh Tran – NTNU) focused on a distributed collision avoidance (COLAV) protocol for inland waterway ships, with three solutions proposed and the COLAV framework extended to machine-to-human communication.
ESR05 (AmirReza H. Mojaveri – Periskal) improved the Track Keeping Pilot in the AUTOBarge framework, focusing on Model Predictive Control (MPC) for obstacle avoidance and path following.
ESR06 (Dhanika Mahipala – Kongsberg) adapted the Scenario Based Model Predictive Control (SB-MPC) algorithm for autonomous collision avoidance in inland waterway vessels.
ESR07 (Yuhan Chen – Chalmers) created a real-time autonomous ship navigation platform with multi-objective voyage optimization algorithms, emphasizing real-time local route planning and collision risk avoidance.
ESR08 (Chengqian Zhang– Chalmers) developed a voyage planning system for energy optimization in autonomous barges, analyzing operational energy consumption and behaviors.
ESR09 (Abhishek Dhyani – TU Delft) focused on fault diagnosis algorithms for safe navigation of autonomous inland vessels and also took the initiative for the development of AUTOBargeSim, a simulation platform for autonomous inland navigation.
ESR10 (Yunjia Wang – KU Leuven) evaluated vulnerabilities in real-time vision-based object detection for autonomous vessels, proposing insights for improved robustness, and introducing a methodology for dynamic safety assurance in machine learning models.
ESR11 (Rana Saha – Chalmers) developed a theoretical framework for data collection and processing in smart autonomous inland shipping, conducting field studies and investigating barriers to automation in European inland waterways.
ESR12 (Lingyu Zhang – UHamburg) assessed the impact of autonomous vessels on transportation choices, predicting inland waterway shipping demand, conducting industry surveys, and aiming to forecast the potential demand for autonomous vessels.
ESR13 (Dhaneswara Al Amien– Nord University) developed an economic implication model for the adoption of autonomous inland shipping, progressing through literature review, data survey, and decision-making model development.
ESR14 (Sophie Orzechowski – IDIT) addressed regulatory challenges in autonomous inland shipping, conducting a regulatory framework analysis and exploring solutions through a comparative analysis.
ESR15 (Camilla Domenighini – University of Antwerp) assessed risk distribution in the autonomous inland shipping ecosystem, finding technology providers often limit liability while shipowners face mandatory liabilities, with challenges in proving negligence and compensating damages under different national legislations.
ESR02 (Martin Baerveldt – NTNU) focused on algorithms combining Multiple Extended Object Tracking (MEOT) and Simultaneous Localization and Mapping (SLAM) using LiDAR data, enhancing MEOT for LiDAR and incorporating map data for localization.
ESR03 (Zhongbi Luo – KU Leuven) developed and published a framework using LiDAR-GNSS fusion for live chart updates of Inland Electronic Navigational Charts (IENCs) turning them into dynamic, real-time systems for autonomous vessels.
ESR04 (Hoang Anh Tran – NTNU) focused on a distributed collision avoidance (COLAV) protocol for inland waterway ships, with three solutions proposed and the COLAV framework extended to machine-to-human communication.
ESR05 (AmirReza H. Mojaveri – Periskal) improved the Track Keeping Pilot in the AUTOBarge framework, focusing on Model Predictive Control (MPC) for obstacle avoidance and path following.
ESR06 (Dhanika Mahipala – Kongsberg) adapted the Scenario Based Model Predictive Control (SB-MPC) algorithm for autonomous collision avoidance in inland waterway vessels.
ESR07 (Yuhan Chen – Chalmers) created a real-time autonomous ship navigation platform with multi-objective voyage optimization algorithms, emphasizing real-time local route planning and collision risk avoidance.
ESR08 (Chengqian Zhang– Chalmers) developed a voyage planning system for energy optimization in autonomous barges, analyzing operational energy consumption and behaviors.
ESR09 (Abhishek Dhyani – TU Delft) focused on fault diagnosis algorithms for safe navigation of autonomous inland vessels and also took the initiative for the development of AUTOBargeSim, a simulation platform for autonomous inland navigation.
ESR10 (Yunjia Wang – KU Leuven) evaluated vulnerabilities in real-time vision-based object detection for autonomous vessels, proposing insights for improved robustness, and introducing a methodology for dynamic safety assurance in machine learning models.
ESR11 (Rana Saha – Chalmers) developed a theoretical framework for data collection and processing in smart autonomous inland shipping, conducting field studies and investigating barriers to automation in European inland waterways.
ESR12 (Lingyu Zhang – UHamburg) assessed the impact of autonomous vessels on transportation choices, predicting inland waterway shipping demand, conducting industry surveys, and aiming to forecast the potential demand for autonomous vessels.
ESR13 (Dhaneswara Al Amien– Nord University) developed an economic implication model for the adoption of autonomous inland shipping, progressing through literature review, data survey, and decision-making model development.
ESR14 (Sophie Orzechowski – IDIT) addressed regulatory challenges in autonomous inland shipping, conducting a regulatory framework analysis and exploring solutions through a comparative analysis.
ESR15 (Camilla Domenighini – University of Antwerp) assessed risk distribution in the autonomous inland shipping ecosystem, finding technology providers often limit liability while shipowners face mandatory liabilities, with challenges in proving negligence and compensating damages under different national legislations.
Before AUTOBarge, no commercial vessels operated at full autonomy although most of them are equipped with basic technologies for increased autonomy. Previous research projects (e.g. Watertruck+, Novimar, AUTOSHIP, ShippingLab, etc.) mainly focused on prototypes or the application of new technologies or processes to facilitate autonomy (5G, GNSS, radar, risk analysis…). Most effort was focused on autonomous shipping at sea. AUTOBarge did not aim at prototypes but rather wanted to develop and integrate more advanced methodologies (MPC, lidar, SLAM, IENC, etc.) within the specific context of autonomous shipping on the European inland waterways. AUTOBarge deliberately focused a large part of its research to the socio-technical, economic, and legal impact of autonomous shipping which are key skills for future experts in this field.