Randomly Testing an Autonomous Collision Avoidance System with Real-World Ship Encounter Scenario from AIS Data

Abstract

Maritime Autonomous Surface Ship (MASS) is promoted as the future of intelligent shipping. While autonomy technologies offer a solution for MASS, they have also resulted in new challenges for performance validation. To address this, a scenario-based validation method to test the autonomous collision avoidance system is proposed in this paper, including mining ship encounter scenarios from massive historical AIS data and randomly generated virtual test scenarios according to the parameter probability distributions from the collected real scenarios, as well as the final experiments: a total of 2900 generated scenarios including single ship and multi-ship encounter situations are created and applied to conduct testing experiments on the further assessment of our collision avoidance algorithm. The results indicate that the proposed method has the ability to quickly create appropriate testing scenarios according to AIS records, which are helpful to catch potential defects in a collision avoidance algorithm of MASS and to further analyze its navigating features. As a result, the research forms a systematic set of validation procedures from data gathering to practical experiments conduction, incorporating both the real statistics and the random generation method.

The Application of Artificial Intelligence Technology in Shipping: A Bibliometric Review

“…Chen et al [60] introduced a deep learningbased framework to accurately predict ship trajectories, supported by AIS data, which predicted the trajectory changes in single and multiple ships, and this study can help maritime regulators make reasonable traffic control and management decisions. Zhu et al [61] proposed a scenario-based test validation method for ship collision avoidance systems, which solves the potential flaws in previous ship collision avoidance algorithms by mining historical AIS data and randomly producing virtual test scenarios to quickly create appropriate test scenarios. However, there are data-quality and -acquisition problems with AIS data, and such problems may lead to the application of AIS data in some shipping fields being hindered.…”

A Multi-Ship Collision Avoidance Algorithm Using Data-Driven Multi-Agent Deep Reinforcement Learning

“…The following situation may occur during the process of maned-vessel collision avoidance in the real waters: one or more vessels do not take coordinated communication or take collision avoidance actions based on COLREGs, resulting in uncoordinated collision avoidance behaviors [24]. Meanwhile, there will be a mixed traffic scenario in which manned ships and autonomous ships coexist for a certain period in the future [25].…”

“…In this paper, the real encounter situation scenario data obtained from the literature [24] are used as the real-data training set for the algorithm. The specific approach is to screen out five groups of encounter information with different ship numbers, which are used as five units in the training set to serve the model training.…”

Development of a Graph-Based Collision Risk Situation Model for Validation of Autonomous Ships’ Collision Avoidance Systems

“…The systematic development and testing of potential scenarios is inherently complex and multifaceted. Though research has identified methods for comprehensive scenario development for testing collision avoidance systems, their effectiveness in thoroughly understanding and replicating the multifaceted and varied collision risks in real navigation settings is limited, sometimes due to the increased number and complexity of the parameters involved [21][22][23][24][25][26][27][28][29][30][31][32].…”