Takuma Yoneda

About me

Takuma Yoneda
Takuma Yoneda

I am a PhD student at Toyota Technological Institute at Chicago (TTIC),
interested in Robotics, Reinforcement Learning and Natural Language Processing.

I am now at Robot Intelligence through Perception Lab working with Prof. Matthew R. Walter.

I got a Bachelor of Engineering from Toyota Technological Institute (Nagoya, Japan) and worked on Graph Embedding and Natural Language Processing with Prof. Makoto Miwa and Prof. Yutaka Sasaki at Computational Intelligence Lab.

Publications (Google Scholar)





Dexterous manipulation with a three-finger robot

We participated in Real Robot Challenge, where participants develop a method that can grasp and manipulate an object with TriFinger robot.
We won 1st place in both competition phases (Phase 2 & 3), and received 12,500 EUR as a cash prize.
[code] [paper] [videos]

Auxiliary Tasks for Navigation in Unknown Environments (class project)

We used a simulator to train an agent that navigates itself in a photo-realistic 3-D indoor environment. The agent only observes first-person view image. We trained the agent with several different auxiliary tasks such as depth prediction, and compare them to see what auxiliary tasks can help navigation.
The gif on the left shows a PPO agent trained with reward (distance to the goal) and auxiliary depth-prediction.