GRAVITAS: A Model Checking Based Planning and Goal Reasoning Framework for Autonomous Systems
This addresses trustworthiness in autonomous systems, but appears incremental as it builds on existing verification-as-planning paradigms.
The paper tackles the problem of interpretability and uncertainty in AI for autonomous systems by proposing GRAVITAS, a framework that uses model checking for planning and goal reasoning, demonstrated in a simulated underwater vehicle survey mission.
While AI techniques have found many successful applications in autonomous systems, many of them permit behaviours that are difficult to interpret and may lead to uncertain results. We follow the "verification as planning" paradigm and propose to use model checking techniques to solve planning and goal reasoning problems for autonomous systems. We give a new formulation of Goal Task Network (GTN) that is tailored for our model checking based framework. We then provide a systematic method that models GTNs in the model checker Process Analysis Toolkit (PAT). We present our planning and goal reasoning system as a framework called Goal Reasoning And Verification for Independent Trusted Autonomous Systems (GRAVITAS) and discuss how it helps provide trustworthy plans in an uncertain environment. Finally, we demonstrate the proposed ideas in an experiment that simulates a survey mission performed by the REMUS-100 autonomous underwater vehicle.