Collaborative Research Center 1320 funded by DFG: Everyday Activity Science and Engineering (EASE) is the study of the design, realization, and analysis of information processing models that enable robotic agents (and humans) to master complex human-scale manipulation tasks that are mundane and routine.In the subproject NEEM (Narrative-Enabled Episodic Memory) we investigate representation, management, reasoning, and usage. For this, we will develop an embodied knowledge acquisition, representation, and management framework. Furthermore, we will investigate a physically embodied query answering service for knowledge completion. This will boost information processing for robots by exploiting episodic memory systems. Then, this will allow the acquisition of commonsense and naive physics knowledge as a big data analytic problem. The project started in July 2017.
The project EU-funded project Factory-in-a-day aims at improving the competitiveness of European manufacturing SMEs by removing the primary obstacle for robot automation: installation time and installation cost. This project started in October 2013. My main task in Factory-in-a-day is in the development of techniques for natural demonstrations using human-robot-co-manipulation. In this regard, our semantic-based reasoning approach is able to integrate different input sensors, such as the joint encoders of a robot, skin sensors (tactile and proximity) and visual information from the cameras of the robot (first view perspective).
RoboCub@Home is the largest international annual competition for autonomous service robots and is part of the RoboCup initiative. Team leader of the first TUM team to compete. October 2016 - July 2017.
Laura Bassi Price with this award Technische Universität München (TUM) promotes women in science. The title of my research project is "Exploiting semantic representations to infer human activities from different input sources". Funded by the government of Bavaria and TUM, Germany from January 2016 - January 2017.
German-Korean Partnership Programme (GEnKO-DAAD): The name of the project was "Machine Learning for the Generation of Flexible Motion Trajectories for Robot Manipulators". Within the project, we studied the generation of motions for robot arms and manipulators that are most likely to be appropriate given a particular situation and real-world task constraints, and we consequently apply these motions to control humanoid robots. This project was performed during July 2011-April 2013.
DFG Cluster of Excellence Cognition for Technical Systems (CoTeSys):This project was financed under the German Excellence Initiative from 2006 until October 2014. CoTeSys investigated cognition for technical systems such as vehicles, robots, and factories. Technical systems that are cognitive will be much easier to interact and cooperate with, and will be more robust, flexible, and efficient. I was involved in the sub-project of "Cognitive Models of Everyday Manipulation Tasks". My work was meanly focused on obtaining models of human everyday activities like setting the table. These models describe the arm movement in common task such as the reaching movement.
IPN - SIP "Computational Modeling and Simulation of physical and biological systems". This project was founded from January to December 2008 by the Instituto Politécnico Nacional (IPN), Mexico. The main goal of this project was to model and simulate thermodynamics systems, mechanical systems and biological systems using non-linear techniques. My contribution in this project was to analyze of the thermodynamics, mechanical and biological system through non-linear techniques such as: Lyapunov exponent, fractal dimension, Poincare maps, among others.