Maria Bauza, MIT PhD Candidate
I am PhD student at the Massachusetts Institute of Technology (MIT) working with Prof. Alberto Rodriguez.
I develop algorithms that make robots more reactive through accurate feedback. In my work, I have studied both the power of closed-loop control in frictional systems and the capabilities of high-resolution tactile sensing for manipulation tasks, such as grasping and localization. My goal is to make robots highly reactive and dexterous at manipulation by effectively leveraging real-time tactile and visual feedback. MIT News
Here you can find some of my projects as PhD student, and work done during my undergraduate studies.
My research has been supported by LaCaixa and Facebook fellowships.
Tactile Localization and Mapping
Shape reconstruction and object localization using a vision-based tactile sensor, GelSlim.
Tactile regrasping using a high-resolution tactile second to improve grasp stability. Best Poster Award
at ICRA 2018 workshop on Active touch for perception and interaction.
Graph Element Networks
Adaptive, structured computation and memory.
We present a large high-quality on planar pushing that includes RGB-D video and extense object variability.
We explore the data-complexity required for controlling, rather than modeling, planar pushing.
Simulators and Object-Based Networks for Control
We propose a hybrid dynamics model, simulator-augmented interaction networks (SAIN),
combining a physics engine with an object-based neural network for dynamics modeling.
We augment an analytical rigid-body simulator with a neural network that
learns to model uncertainty as residuals. Best Paper Award on Cognitive Robotics at IROS 2018.
With the MIT-Princeton team we developed a robust robotic system for bin picking.
Amazon Robotics Best Systems Paper Award .
We developed the algorithm GP-SUM: a GP-Bayes filter that propagates in time non-Gaussian beliefs.
Characterizing the uncertainty of different pushes allows better action selection.
More than a million datapoints collected on real pusing experiments. Best Paper Finalist Award at IROS 2016 .
A cheap autonomous RC car
Hacking the car's controller, we made it be a self-driving car.
The drawing robot
Our homemade robot can draw an image from the Internet onto any blackboard.