Alice Miller
Papers
5
Total Citations
38
H-Index
3
About
Alice Miller is a researcher at the forefront of formal verification for autonomous systems, specializing in the safe and reliable design of robotic and agent-based behaviors. Her work bridges theoretical computer science and practical robotics, with a core focus on model checking, abstraction techniques, and probabilistic modeling to prove critical properties of autonomous agents. Miller’s major contributions include developing abstract definitions of autonomy that enable scalable formal analysis, as demonstrated in her most-cited work, “Autonomous Agent Behaviour Modelled in PRISM – A Case Study” (2016, 13 citations), which uses probabilistic model checking to verify robot decision-making. She also advanced signal reconstruction with the GBRAMP algorithm (2021, 13 citations), showcasing her versatility. Her pioneering efforts in formal modeling of robot learning (2013, 6 citations) and environment abstraction for model checking (2011) have laid groundwork for proving safety in complex, learning-enabled systems. Through these contributions, Miller has established herself as a key figure in ensuring that autonomous systems can be rigorously proven safe before deployment, addressing a critical challenge in modern robotics and AI.
Research Focus
Key Achievements
Top Papers
- 1Autonomous Agent Behaviour Modelled in PRISM – A Case Study13 citations · 2016
- 2
- 3Formal Modeling of Robot Behavior with Learning6 citations · 2013
- 4Abstraction for model checking robot behaviour3 citations · 2011
- 5Autonomous Agent Behaviour Modelled in PRISM -- A Case Study3 citations · 2016