free website maker

Guilherme Maeda
Preferred Networks researcher in robotics and robot motor skill learning

Eventually, our society will depend on robots as general-purpose helpers that will assist us throughout our entire lives. This vision requires robots capable of learning skills by themselves to manipulate and interact with the world in a way that is useful for us. To this end, my work involves the investigation and design of learning control methods, and their implementation and validation using real robots. 

News and upates

  1. In August 2020 I am giving an invited (online) talk at the IAS group in TU Darmstadt on our new movement primitive formulation.
  2. July 2020. The virtual RSS workshop was held on the 13th of July 2020 with great success and many lessons learned! We will update it with some conclusions soon. "Closing the Academia to Real-World Gap in Service Robotics". You can watch the entire live sessions here.
  3. July 2020. Our paper "Visual Task Progress Estimation with Appearance Invariant Embeddings for Robot Control and Planning" was accepted at IROS 2020. Pre-print (to be updated) here !

Past news and updates [here].

Research overview