Christopher Thierauf, PhD

All Updates

Fixing Symbolic Plans with Reinforcement Learning in Object-Based Action Spaces.

Publications

Tags: Neurosymbolic, Reinforcement Learning, Resilience

Christopher Thierauf, Matthias Scheutz. IEEE IROS 2024.

We can redesign the typical reinforcement learning pipeline to train faster and integrate with symbolic plans by training on the environment directly, not the robot within it.

You can read the paper here.
(more…)
“Do This Instead”—Robots That Adequately Respond to Corrected Instructions.

Publications

Tags: Autonomy, DIARC, HRI, Resilience

Christopher Thierauf, Ravenna Thielstrom, Bradley Oosterveld, Will Becker, Matthias Scheutz. ACM Transactions on HRI.

How can robots handle self-corrections in human commands?
(more…)
Toward Competent Robot Apprentices: Enabling Proactive Troubleshooting in Collaborative Robots.

Publications

Tags: Autonomy, DIARC, HRI, Resilience

Christopher Thierauf, Theresa Law, Tyler Frasca, Matthias Scheutz. MDPI Machines 2024.

How can robots use dialog to explain, understand, and resolve failure?

You can read the full paper here.
(more…)
ACuTE: Automatic Curriculum Transfer from Simple to Complex Environments

Publications

Tags: Reinforcement Learning

Y Shukla, C Thierauf, R Hosseini, G Tatiya, J Sinapov. Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2022).

Reinforcement Learning problems can be reduced into simpler steps that improve learning. Can we automate that process?
(more…)
Robot Development and Path Planning for Indoor Ultraviolet Light Disinfection.

Publications

Tags: Autonomy, DIARC

J Conroy, C Thierauf, P Rule, E Krause, H Akitaya, A Gonczi, M Korman, M Scheutz. 2021 IEEE International Conference on Robotics and Automation (ICRA).

How do we make a robot that can provably cover a complex region?

You can read the full paper here.
(more…)

All Updates

Fixing Symbolic Plans with Reinforcement Learning in Object-Based Action Spaces.

“Do This Instead”—Robots That Adequately Respond to Corrected Instructions.

Toward Competent Robot Apprentices: Enabling Proactive Troubleshooting in Collaborative Robots.

ACuTE: Automatic Curriculum Transfer from Simple to Complex Environments

Robot Development and Path Planning for Indoor Ultraviolet Light Disinfection.