Max Robotics — Global Service Robot Directory + US Certification

About

Anneliese Andrews is a leading researcher in model-based testing for autonomous systems, with a focus on dynamic environments. Her key contributions center on developing world models that enable rigorous testing of autonomous robots, particularly in unpredictable settings like urban search and rescue (USAR). Unlike traditional approaches that assume static worlds, Andrews pioneered the use of Petri Nets and Communicating Extended Finite State Machines (CEFSM) to represent and test dynamic, evolving environments. Her most cited work, "World Model for Testing Autonomous Systems Using Petri Nets" (2016, 9 citations), introduces a novel test generation approach that accounts for real-time interactions between autonomous systems and their surroundings. She has also advanced testing for real-time adaptive motion planning (RAMP) systems, addressing the challenge of verifying functionality in environments with unknowns and unpredictability. Her research has significant practical implications for safety-critical autonomous technologies, from USAR robots to adaptive motion planning systems. With a career spanning foundational work in AI planner-assisted test generation (2002, 8 citations) to recent innovations in active world models, Andrews continues to shape how autonomous systems are validated in complex, real-world scenarios.