english only
EPFL > STI > IMT > LASA > People > figueroa_fernan
LASA MENU
Home
Research
Publications
Teaching
People
Arriving to LASA
Videos / Photos
Press & News

GitHub Repository
Older Source Codes
The Blog
Intranet

Prospective Students

Member figueroa_fernan

Nadia Figueroa

PhD Student

Email:
nadia.figueroafernandez@epfl.ch

Room:
ME A3 424

Phones:

  • Office: +41 21 69 31060

Personal Home Page:
lasa.epfl.ch/files/NadiaCV2018.pdf

Fields of Interest

  • Learning from Demonstration
  • Incremental/Interactive Learning
  • Human-Robot Collaboration
  • Multi-Robot Coordination
  • Shared Autonomy and Control


Projects

  • The main goal of my research is to endow robots with the capabilities of learning, aiding and smoothly interacting with humans in unstructured and complicated tasks, from household activities such as cooking and cleaning to difficult industrial tasks such as assemblies, carrying/lifting large objects, etc.
  • In order to achieve this goal, I focus on leveraging machine learning techniques with concepts from dynamical systems theory to solve salient problems in the areas of learning from demonstration, incremental/interactive learning, human-robot collaboration, multi-robot coordination, shared autonomy and control.
  • I've worked on the following research projects which have been funded by the EU projects ROBOHOW and COGIMON.

    (2015/2016) Learning Complex Sequential Tasks from Demonstration: Uni-Manual and Bi-Manual Case Studies

    (2016/2017) Multi-Arm Coordination Strategies and Data-Driven Self-Collision Avoidance:

  • For a detailed publication list, check my Google Scholar profile.
  • I am also passionate about teaching machine learning concepts and algorithms. Throughout my PhD I've been the head teaching assistant for graduate-level courses: Advanced Machine Learning and Machine Learning Programming for which I co-developed ML_toolbox : A Machine learning toolbox in MATLAB, containing algorithms for non-linear dimensionality reduction, clustering, classification and regression along with examples and tutorials. I am the main architect and developer of the syllabus for Machine Learning Programming .
  • I am a firm believer in code benchmarking and experiment replication. For this reason I make all of my code available online either on my personal github account or in LASA's github account
  • Main Organizer of the Tutorial on Dynamical System (DS)-based Learning from Demonstration (LfD). A 3 hour long tutorial that introduces students to techniques used to (1) program robots through human demonstration by using DS (2) modulate DS for obstacle avoidance or surface following and (3) DS-based impedance/force control strategies. Website found here .


Hobbies

  • Traveling, eating and drinking wine.


Media Coverage

  • (2017) Top 5 Finalist for the KUKA Innovation Award 2017



Publications




Last update: 11/03/08