Christopher Thierauf, PhD

All Updates

  • Deployments of a Deep Submergence Gravimeter

    Deployments of a Deep Submergence Gravimeter

    Masako Tominaga, Maurice Tivey, Sean Kelley, Christopher Thierauf, Justin Fujii, Jyun-Nai Wu, Hannah Mark, Daniel Aliod, Nigel Brady, Sam Bailey, Allisa Dalpe, Zac Berkowitz, IEEE/MTS OCEANS 2026.

    Can we measure gravity from a robot flying 65 meters above the seafloor, 5,600 meters down?

    This summarizes a recent publication on work we did this March integrating a new gravimeter with AUV Sentry, which you can read here. The project was led by Masako Tominaga, Maurice Tivey, and Sean Kelley, and brought together people from WHOI, Lamont-Doherty, and Dynamic Gravity Systems. If you followed along with my Mariana Trench fieldwork earlier this year, this is one of the things we were up to.

    (more…)

    Masako Tominaga, Maurice Tivey, Sean Kelley, Christopher Thierauf, Justin Fujii, Jyun-Nai Wu, Hannah Mark, Daniel Aliod, Nigel Brady, Sam Bailey, Allisa Dalpe, Zac Berkowitz, IEEE/MTS OCEANS 2026.

    Can we measure gravity from a robot flying 65 meters above the seafloor, 5,600 meters down?

    This summarizes a recent publication on work we did this March integrating a new gravimeter with AUV Sentry, which you can read here. The project was led by Masako Tominaga, Maurice Tivey, and Sean Kelley, and brought together people from WHOI, Lamont-Doherty, and Dynamic Gravity Systems. If you followed along with my Mariana Trench fieldwork earlier this year, this is one of the things we were up to.

    (more…)

  • Towards Transparent Marine Autonomy: Visual Mission Composition for Teleoreactive AUVs

    Towards Transparent Marine Autonomy: Visual Mission Composition for Teleoreactive AUVs

    Christopher Thierauf, Charlotte Stieve, IEEE/MTS OCEANS 2026

    Can a scientist plan a deep-sea robot mission themselves, without learning to program it?

    This summarizes a recent publication, which you can read here. It builds directly on the cognitive teleoreactive framework I’ve been developing for AUV Sentry: that work gave Sentry the ability to reason about goals, and this work is about giving people a way to hand it those goals. Two open-source packages are released alongside it, which I’ll get to below.

    (more…)

    Christopher Thierauf, Charlotte Stieve, IEEE/MTS OCEANS 2026

    Can a scientist plan a deep-sea robot mission themselves, without learning to program it?

    This summarizes a recent publication, which you can read here. It builds directly on the cognitive teleoreactive framework I’ve been developing for AUV Sentry: that work gave Sentry the ability to reason about goals, and this work is about giving people a way to hand it those goals. Two open-source packages are released alongside it, which I’ll get to below.

    (more…)

  • What Matters in Designing Resilient Systems

    What Matters in Designing Resilient Systems

    Christopher Thierauf, Matthias Scheutz, IEEE ERAS 2025.

    How should our autonomous systems be designed around failure? We argue that we shouldn’t design around failure as a special case at all: instead, failure should be treated as just another state to plan around, and we must instead interpret and integrate failure into our planning problem.

    (more…)

    Christopher Thierauf, Matthias Scheutz, IEEE ERAS 2025.

    How should our autonomous systems be designed around failure? We argue that we shouldn’t design around failure as a special case at all: instead, failure should be treated as just another state to plan around, and we must instead interpret and integrate failure into our planning problem.

    (more…)

  • Bard College Seminar 2026

    I presented on oceanographic technology and my work at Bard College in late March. If you’re here from that presentation, you may find these links interesting for follow-on reading or reference.

    AUV Sentry is part of NDSF at WHOI. I’m part of the team of engineers that works on that system and helps deploy it for the scientific community.

    I’m working on a “cognitive teleoreactive architecture”.

    • My two main inspirations are DIARC and T-REX
      • DIARC: the cognitive architecture being developed at the Tufts HRI Lab, and which my experiments pre-WHOI have incorporated/developed within (paper link).
      • T-REX: the teleoreactive architecture developed at MBARI, which saw at-sea use but is no longer being developed (paper link).
    • I rely on symbolic logics. If you’d like to better understand how these work and are used, I wrote a simple introduction (here).

  • Mariana Trench 2026

    We’ve boarded the Thomas G. Thompson for Sentry fieldwork deployments to the Mariana Trench. If successful, we will collect data about the oldest possible geologic features on our planet, which the science party hopes to use in understanding the early stages of earth.

    We depart and return to Guam.

    Also on board is an experimental new sensor (details not yet public), and a potential opportunity to revisit updated deployments of the DYNOS architecture.

  • A Gentle Introduction to Symbolic Planning and Reasoning

    Tags: , ,

    Symbolic planning, decision making, and logics made simple(r).

    (more…)

  • Deployment and Development of a Cognitive Teleoreactive Framework for Deep Sea Autonomy.

    Tags: ,

    Deployment and Development of a Cognitive Teleoreactive Framework for Deep Sea Autonomy.

    Christopher Thierauf, IEEE/MTS OCEANS 2025.

    Can we make deep-sea robots smart enough to act on their own?

    (more…)

    Christopher Thierauf, IEEE/MTS OCEANS 2025.

    Can we make deep-sea robots smart enough to act on their own?

    (more…)

  • Design of a Depth Triggered Mechanical Fuse.

    Tags:

    Design of a Depth Triggered Mechanical Fuse.

    Ethan Rowe, Christopher Thierauf. IEEE/MTS OCEANS 2025.

    How can we make sure our deep-sea assets return to the surface, even under the most catastrophic failure conditions?

    (more…)

    Ethan Rowe, Christopher Thierauf. IEEE/MTS OCEANS 2025.

    How can we make sure our deep-sea assets return to the surface, even under the most catastrophic failure conditions?

    (more…)

  • Robots that Learn to Solve Symbolic Novelties with Self-Generated RL Simulations.

    Tags: ,

    Christopher Thierauf, Matthias Scheutz. International Conference on Development and Learning (ICDL) 2025.

    We solve hard problems by imagining different outcomes in our head. How can robots do the same?

    (more…)

  • Self-Debugging Robots: Fault recovery through reasoning and planning.

    Tags: ,

    Christopher Thierauf, Matthias Scheutz. IEEE Resilience Week 2025.

    Can robots reason about what actions to take to better understand failure? I show a technique and demonstrate how this is possible.

    (more…)