Thanana
Home
Biography
Publication
Research
World Models and Control
Holonomic Systems
Human-robot Interaction
Cyber-physical Systems
Teaching
Reinforcement Learning
Introduction to Robotics
Software
Robotics
Image Processing

Thanana Nuchkrua, Ph.D.

Thanana Nuchkrua 

Robotics & Control Researcher | Compliant Intelligence

Independent PI in Control and Robotics group

Highlights:

  • 10.2026: New preprints on certified learning-enabled estimation and control: Hysteretic Selection, Neural Belief MPC (IEEE TAC, submitted).

  • 2026: \(''\)Bayesian Model Predictive Control for Open Quantum Systems: Robust Qubit State Regulation under Decoherence\(''\) accepted at IFAC 2026. [project page]

  • 09.2019: \(''\)Contouring Control Consensus for Robot Manipulators\(''\) won the best young paper award, finalist at The 58th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE), Japan.

  • 01.2019: \(''\)Sparse Bayesian Learning-based Adaptive Impedance Control in Physical Human-robot-interaction\(''\) won the best paper award at The 2019 International Symposium on Instrumentation, Control, Artificial Intelligence, and Robotics.

Research Philosophy

Action is bound by physics; belief must be bound by math. I treat a learning-enabled system's belief as a mathematically constrained structure. My defining question is: how aggressively can an autonomous system adapt, correct, or switch its belief under uncertainty without violating the strict safety tolerances of the physical actions it drives?

“Agile in learning. Provable in action.”

Research Vision

Learning drives adaptation, but guaranteed bounds establish trust:

Compliant Intelligence; Feel → Believe → Adapt → Decide → Interact

Professional Services

Reviewer Board

  • Machines

Program Committee

  • The 2025 International Conference on Automation and Intelligent Technology (ICAIT 2025), China.

  • The 2019 IEEE International Conference on Robotics and Biomimetics (ROBIO 2019), Yunnan, China.

Session Chair

  • \(''\)Model Learning for Control\(''\), 14th IEEE International Conference on Automation Science and Engineering (CASE 2018), August 20-24, 2018, TU München, Germany.

  • \(''\)Robotic and Automation Systems II\(''\), The 58th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE), September 10-13, 2019, Hiroshima, Japan.

Selected Talk

  • Control, Learning, and Optimization: from physic-based to data-driven

  • Learning-based Non-linear Adaptive Robust Control Framework: Dual-arm Robot