Embodied intelligence, today!

Robotics is likely the biggest category of my work. It encompasses everything from hardware development to algorithmic studies all with the central goal of creating agents that can better interact with our physical world (even in indirect ways, like traffic lights).

I have so many open areas of research here, and am open to inquiries.

In this paper we set out to understand the causes of compounding prediction errors in one-step learned models. With this, we hope a next generation of models can be used to improve model-based reinforcement learning.
A simulator for studying high-agent-count networked systems!
Trying to reframe the MBRL framework with long-term predictions instead of one-step predictions!
A collections of steps towards a data-driven autonomous microrobot.
Learning how to walk with a real-world hexapod using a hierarchy of model-free RL for basic motion primitives with model-based RL for higher level planning.
We used deep model-based reinforcement learning to have a quadrotor learn to hover from less than 5 minutes of all experimental training data.
A collection of steps towards controlled flight of The Ionocraft, a completely silent microrobot with ion thrust!