Active World Model for Testing Autonomous Systems Using CEFSM.

Abstract

This paper describes a model-based test generation approach for testing autonomous systems interacting with their environment (i.e., world). Unlike other approaches that assume a static world with attributes and values, we present and test a dynamic world. We use Communicating Extended Finite State Machine (CEFSM) to illustrate an active world model that describes behaviors of environmental factors (i.e., actors). Abstract World Behavioral Test Cases (AWBTCs) are then generated by covering the active world model using graph coverage criteria. We also generate test-data by input-space partitioning to transform the generated AWBTCs into executable test cases. We apply the World Model-based Test Generation (WMBTG) technique to a case study from the Human-Robot Interaction domain (HRI) specifically a tour-guide robot. Reachability of the active world model and efficiency of coverage criteria are also discussed.