Filipe Veiga

Filipe Veiga

Assistant Professor

George Mason University

Filipe Veiga

I am an assistant professor in the Department of Electrical and Computer Engineering at George Mason University.

Prior to joining GMU, I was Postdoctoral Associate at the Computer Science & Artificial Intelligence Lab at the Massachusetts Institute of Technology working with Prof. Edward Adelson in the development and usage of GelSight fingertip sensors for improving the dexterous manipulation skills of robots.

I obtained a PhD in Machine Learning and Robotics from the Technische Universitaet Darmstadt under the supervision of Prof. Jan Peters after I got my Master Degree in Electrical and Computer Engineering from Instituto Superior Técnico under the supervision of Prof.Alexandre Bernardino and Prof.José Santos-Victor.

My research interests focus on the exploration of biomimetic control approaches in conjunction with state of the art machine learning in order to learn real time state estimation and control systems. In particular, these topics are explored in he context of robot manipulation and multi-model perception.

Interests

  • Robotics
  • Robot Grasping
  • In-Hand Manipulation
  • Tactile Sensing
  • Biomimetic Control
  • Reinforcement Learning

Education

  • Postdoctoral Associate

    Massachusetts Institute of Technology, 2021

  • PhD in Machine Learning and Robotics

    Technische Universität Darmstadt, 2018

  • MSc in Electrical and Computer Engineering

    Instituto Superior Técnico, 2012

Recent Publications

Soft, Round, High Resolution Tactile Fingertip Sensors for Dexterous Robotic Manipulation

High resolution tactile sensors are often bulky and have shape profiles that make them awkward for use in manipulation. This becomes …

Grip Stabilization through Independent Finger Tactile Feedback Control

Grip force control during robotic in-hand manipulation is usually modeled as a monolithic task, where complex controllers consider the …

Learning Attribute Grammars for Movement Primitive Sequencing

Movement primitives are a well studied and widely applied concept in modern robotics. However, composing primitives out of an existing …

Contact

  • ffveiga@gmu.edu
  • Nguyen Engineering Building, Fairfax, VA 22030