On the Verification and Validation of AI Navigation Algorithms
This work tackles the problem of ensuring safety and reliability in autonomous ship navigation, which is crucial for maritime industries, but it is incremental as it builds on existing validation methods.
The paper addresses the verification and validation of AI navigation algorithms for autonomous surface ships by conducting a systematic mapping study, finding that most research relies on limited manual simulations, and proposes a systematic scenario-based testing approach to improve validation.
This paper explores the state of the art on to methods to verify and validate navigation algorithms for autonomous surface ships. We perform a systematic mapping study to find research works published in the last 10 years proposing new algorithms for autonomous navigation and collision avoidance and we have extracted what verification and validation approaches have been applied on these algorithms. We observe that most research works use simulations to validate their algorithms. However, these simulations often involve just a few scenarios designed manually. This raises the question if the algorithms have been validated properly. To remedy this, we propose the use of a systematic scenario-based testing approach to validate navigation algorithms extensively.