Scenario-based Testing of a Ship Collision Avoidance System

We propose a method for scenario-based testing of maritime collision avoidance systems. The goal is to test an autonomous agent in scenarios that can lead to an unacceptable risk of collision or may clearly not comply with the International Regulations for Preventing Collisions at Sea (COLREGs).Our method is based on the use of a discriminating artificial neural network that is trained online while performing the testing of the agents. Our experimental results show that the proposed algorithm generates test suits composed mostly of challenging scenarios. This allows us to validate quickly if the agent under test can perform the collision avoidance maneuvers safely while abiding the COLREGs.

[1]  Massimo Figari,et al.  A COLREG-Compliant Ship Collision Avoidance Algorithm , 2019, 2019 18th European Control Conference (ECC).

[2]  Martin Bergström,et al.  A systemic hazard analysis and management process for the concept design phase of an autonomous vessel , 2019, Reliab. Eng. Syst. Saf..

[3]  Lokukaluge P. Perera,et al.  Experimental Evaluations on Ship Autonomous Navigation and Collision Avoidance by Intelligent Guidance , 2015, IEEE Journal of Oceanic Engineering.

[4]  C. Tam,et al.  Review of Collision Avoidance and Path Planning Methods for Ships in Close Range Encounters , 2009, Journal of Navigation.

[5]  Lionel C. Briand,et al.  Testing Vision-Based Control Systems Using Learnable Evolutionary Algorithms , 2018, 2018 IEEE/ACM 40th International Conference on Software Engineering (ICSE).

[6]  Lokukaluge P. Perera,et al.  Deep Learning Toward Autonomous Ship Navigation and Possible COLREGs Failures , 2020 .

[7]  Zengshi Chen,et al.  Reinforcement Learning: An Introduction: R.S. Sutton, A.G. Barto, MIT Press, Cambridge, MA 1998, 322 pp. ISBN 0-262-19398-1 , 2000, Neurocomputing.

[8]  Lionel C. Briand,et al.  Testing advanced driver assistance systems using multi-objective search and neural networks , 2016, 2016 31st IEEE/ACM International Conference on Automated Software Engineering (ASE).

[9]  Shyh-Kuang Ueng,et al.  A ship motion simulation system , 2008, Virtual Reality.

[10]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[11]  David Silver,et al.  Deep Reinforcement Learning with Double Q-Learning , 2015, AAAI.

[12]  Satyandra K. Gupta,et al.  Automated generation of diverse and challenging scenarios for test and evaluation of autonomous vehicles , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[13]  Lokukaluge P. Perera,et al.  Possible COLREGs Failures under Digital Helmsman of Autonomous Ships , 2019, OCEANS 2019 - Marseille.

[14]  Thomas Porathe.  Maritime Autonomous Surface Ships (MASS) and the COLREGS: Do We Need Quantified Rules Or Is “the Ordinary Practice of Seamen” Specific Enough? , 2019 .

[15]  Dragos Truscan,et al.  Automatic exploratory performance testing using a discriminator neural network , 2020, 2020 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW).

[16]  Luigi del Re,et al.  Outcome Oriented Evaluation of Autonomous Driving Functions , 2018, 2018 IEEE Conference on Decision and Control (CDC).

[17]  Michael T. Wolf,et al.  Safe maritime navigation with COLREGS using velocity obstacles , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[18]  C. Guedes Soares,et al.  Intelligent Ocean Navigation and Fuzzy-Bayesian Decision/Action Formulation , 2012, IEEE Journal of Oceanic Engineering.

[19]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[20]  Alexander Pretschner,et al.  Fitness Functions for Testing Automated and Autonomous Driving Systems , 2019, SAFECOMP.

[21]  Liang Hu,et al.  A Multiobjective Optimization Approach for COLREGs-Compliant Path Planning of Autonomous Surface Vehicles Verified on Networked Bridge Simulators , 2020, IEEE Transactions on Intelligent Transportation Systems.

[22]  Lokukaluge P. Perera,et al.  Solutions to the Failures and Limitations of Mamdani Fuzzy Inference in Ship Navigation , 2014, IEEE Transactions on Vehicular Technology.

[23]  Jens Krause,et al.  Testing and Validating Tactical Lane Change Behavior Planning for Automated Driving , 2017 .