Sara Bernardini

Professor Sara Bernardini
Room
317,
Wolfson Building,
Parks Road, Oxford OX1 3QD
United Kingdom
Interests
Sara’s research is in Artificial Intelligence (AI), specifically decision-making for intelligent autonomous systems (e.g. ground robots, drones, and underwater vehicles). She is a world-leading expert in automated planning, which involves equipping artificial agents with the ability to synthesise plans to reach specific goals. Sara’s long-term objective is to provide the theoretical foundations for creating agents that can seamlessly support humans in undertaking sophisticated and temporally extended tasks, which, going beyond perception and pattern matching, require deliberation at the cognitive level.
At the heart of Sara’s research is the desire to combine theoretical and technical advancements in AI with the demands of the real world. Over the past few years, she has led several projects on intelligent autonomous systems for extreme environments. She has worked closely with industry and stakeholders, ensuring her solutions are crucial to tackling end users’ practical problems. She has worked in several domains, such as space mission operations, nuclear decommissioning, mining, underwater missions, and offshore energy, leading several projects funded by Innovate UK, EPSRC, NERC, the Turing Institute, and the Leverhulme Trust.
Sara’s research is regularly published in top-ranked AI and robotics journals and conferences, such as AIJ, JAIR, RA-L, TOCHI, AAAI, IJCAI, AAMAS, IROS, KR and ICAPS.
Biography
Sara Bernardini is a professor of Computer Science at the University of Oxford and a Tutorial Fellow in Computer Science at Mansfield’s College. Her academic journey includes positions at Royal Holloway, King's College, and University College London in the UK, as well as stints at MIT and NASA Ames in the US. She recently served as the Principal Research Scientist in AI and Data Science at the UK National Oceanography Centre and as a Senior Fellow at the Alan Turing Institute.
She is a member of the Executive Council of the Association for the Advancement of Artificial Intelligence (AAAI), where she leads the Partnership Committee, and the International Conference on Automated Planning and Scheduling (ICAPS). She was the Program Chair of ICAPS 2024 and the Associate General Chair of AAAI-23. At AAAI-23, she initiated the Bridge Program, fostering cross-fertilisation between AI and other disciplines, a program she continued at AAAI-24 and AAAI-25.
Sara is also an associate editor of the Artificial Intelligence Journal and the managing guest editor of the Artificial Intelligence Journal Special Issue on ‘Risk-Aware Autonomous Systems’, a testament to her commitment to AI safety.
Selected Publications
-
Optimizing pathfinding for goal legibility and recognition in cooperative partially observable environments
Sara Bernardini‚ Fabio Fagnani‚ Alexandra Neacsu and Santiago Franco
In Artif. Intell.. Vol. 333. Pages 104148. 2024.
Details about Optimizing pathfinding for goal legibility and recognition in cooperative partially observable environments | BibTeX data for Optimizing pathfinding for goal legibility and recognition in cooperative partially observable environments | DOI (10.1016/J.ARTINT.2024.104148) | Link to Optimizing pathfinding for goal legibility and recognition in cooperative partially observable environments
-
Exploiting Geometric Constraints in Multi−Agent Pathfinding
Dor Atzmon‚ Sara Bernardini‚ Fabio Fagnani and David Fairbairn
In Sven Koenig‚ Roni Stern and Mauro Vallati, editors, Proceedings of the Thirty−Third International Conference on Automated Planning and Scheduling‚ Prague‚ Czech Republic‚ July 8−13‚ 2023. Pages 17–25. AAAI Press. 2023.
Details about Exploiting Geometric Constraints in Multi−Agent Pathfinding | BibTeX data for Exploiting Geometric Constraints in Multi−Agent Pathfinding | DOI (10.1609/ICAPS.V33I1.27174) | Link to Exploiting Geometric Constraints in Multi−Agent Pathfinding
-
Helpful Information Sharing for Partially Informed Planning Agents
Sarah Keren‚ David Wies and Sara Bernardini
In Proceedings of the Thirty−Second International Joint Conference on Artificial Intelligence‚ IJCAI 2023‚ 19th−25th August 2023‚ Macao‚ SAR‚ China. Pages 5377–5385. ijcai.org. 2023.
Details about Helpful Information Sharing for Partially Informed Planning Agents | BibTeX data for Helpful Information Sharing for Partially Informed Planning Agents | DOI (10.24963/IJCAI.2023/597) | Link to Helpful Information Sharing for Partially Informed Planning Agents