PeopleofSuperintelligence

Researcher

Alban Grastien

Alban Grastien is an AI researcher whose work spans model-based diagnosis, planning and pathfinding. He wrote a 2005 PhD thesis on decentralized, online diagnosis of reconfigurable discrete-event systems, coauthored a grid-pruning method for pathfinding in 2011, and helped develop diagnosis planning in 2017. He coauthored a 2021 paper on plans that signal normative compliance, a 2023 general theory of diagnosis, and a 2025 paper introducing CAISAR for machine-learning verification. As of October 2026, he is an Honorary Senior Fellow at ANU's School of Computing.

Links
Website, Google Scholar and LinkedIn

Timeline

  1. 2005

    A thesis on system diagnosis

    He writes a 2005 PhD thesis on decentralized, online diagnosis of reconfigurable discrete-event systems.

  2. 2011

    Grid pathfinding with jump points

    With Daniel Harabor, he introduces an online pruning method for grid pathfinding in 2011. Their method expands selected jump points, preserves optimal paths and speeds A* by an order of magnitude or more.

  3. 2017

    Planning for system diagnosis

    In 2017, he and four coauthors propose a diagnosability plan for partially controllable discrete-event systems. The plan leads the system from an initial belief state to a diagnosable belief state, where it can run freely.

  4. July 2019

    ANU research fellowship

    In July 2019, he is a research fellow at ANU's Research School of Social Sciences.

  5. 2021

    Plans that signal compliance

    In 2021, he and Claire Benn and Sylvie Thiébaux define a method for computing AI plans that signal normative compliance. Their paper gives a formal definition and an algorithm for finding permissible plans that observers can recognize.

  6. September 2023

    A broader diagnosis theory

    In September 2023, he, Patrik Haslum and Sylvie Thiébaux generalize model-based diagnosis across system types. They present two implementations that use test solvers based on satisfiability and heuristic search.

  7. June 2025

    CAISAR for machine learning

    In June 2025, he coauthors a paper presenting CAISAR, an open-source platform for machine-learning specification and verification. Its language covers neural networks, support-vector machines and boosted trees.

  8. As of October 2026

    Honorary Senior Fellow at ANU

    As of October 2026, he is an Honorary Senior Fellow at ANU's School of Computing.

  1. The United States employs an estimated 48% of people shaping AIIncludes Australian National University. We estimate where the people shaping AI work today, how universities, companies and research institutes split across countries, and how country shares have changed since the 1960s.
  2. The median h-index is 48 at universities and 14 at frontier AI labsIncludes Australian National University. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.
  3. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Australian National University. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.
  4. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Australian National University. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Alban Grastien yet. Send us a free-licensed photo.

  1. Alban Grastien csauthors.net. Checked 20 October 2026.
  2. Online Graph Pruning for Pathfinding On Grid Maps ojs.aaai.org. Checked 20 October 2026.
  3. Diagnosability Planning for Controllable Discrete Event Systems ojs.aaai.org. Checked 20 October 2026.
  4. Welcoming New Colleagues at ANU School of Philosophy philosophy.cass.anu.edu.au. Checked 20 October 2026.
  5. Computing Plans that Signal Normative Compliance researchportalplus.anu.edu.au. Checked 20 October 2026.
  6. A More General Theory of Diagnosis from First Principles arxiv.org. Checked 20 October 2026.
  7. The CAISAR Platform: Extending the Reach of Machine Learning Specification and Verification arxiv.org. Checked 20 October 2026.
  8. Alban Grastien | ANU School of Computing comp.anu.edu.au. Checked 20 October 2026.