I'm a Reinforcement Learning Engineer at VinRobotics in Hanoi, where I lead the reinforcement learning team building humanoid robots that walk, carry, recover balance, and understand terrain and context under real payloads. Before this, my undergraduate thesis at HCMUT was a structured-light vision system for robotic bin-picking. That was a different scale, but both are ultimately the same core problem: closing the gap between what a robot perceives and what it can safely do.
I'm looking at PhD programs in robot learning, focused on whole-body control and loco-manipulation, and the learning methods that make them work on real hardware, not just in simulation. I'm also open to full-time opportunities and research collaborations in the meantime, please reach out if that's you.
Outside the lab, I'm usually the one already looking at flights for the next trip. More in News.
Last touched September 2026
A perceptive locomotion system for payload-robust humanoid walking. Multi-channel terrain cost maps guide a GPU-parallel foothold planner, with virtual wrench injection enabling payload-compliance training without force sensors. Achieves 1.0 m/s on stairs with 20 cm risers and zero-shot transfer to a physical humanoid carrying up to 20 kg.
Project page →
Whole-body compliance for a 70 kg heavy humanoid under high-payload and external-force scenarios. A multi-site impedance reference controller, variational force latent encoder, and bounded residual mechanism jointly edit impedance equilibria, validated on surface wiping, force reaction, loaded squatting, and cooperative transport with a 0.98 success rate.
Project page →