Regularized Deep Signed Distance Fields for Reactive Motion Generation

Authors: Puze Liu, Kuo Zhang, Davide Tateo, Snehal Jauhri, Jan Peters and Georgia Chalvatzaki Abstract Autonomous robots should operate in real-world dynamic environments and collaborate with humans in tight spaces. A key component for allowing robots to leave structured lab and manufacturing settings is their ability to evaluate online and real-time collisions with the worldContinue reading “Regularized Deep Signed Distance Fields for Reactive Motion Generation”

Robot Learning of Mobile Manipulation with Reachability Behavior Priors

Authors: Snehal Jauhri, Jan Peters and Georgia Chalvatzaki Our Contributions We propose to use a hybrid action-space Reinforcement Learning algorithm for effectively tackling the need for discrete and continuous action decisions in Mobile Manipulation We learn a reachability behavioral prior for Mobile Manipulation that can speed up the learning process, and incentivize the agent toContinue reading “Robot Learning of Mobile Manipulation with Reachability Behavior Priors”

Making robots useful parts of our society

Professorship for Dr. Georgia Chalvatzaki Since February, Georgia Chalvatzaki has been assistant professor for “Intelligent Robotic Systems for Assistance” at the Department of Computer Science. Chalvatzaki has been leading the iROSA research group since 2021 as part of the Emmy Noether Programme of the German Research Foundation. Previously, the 33-year-old researcher was a postdoctoral researcherContinue reading “Making robots useful parts of our society”

Co-Chair in IEEE WIE-RAS

Georgia will be serving as a co-chair of the IEEE RAS Women in Engineering group, along with Chair Karinne Ramirez Amaro and co-Chair Daniel Leidner. The Women in Engineering – RAS (WIE-RAS) group was formed by the Member Activities Board (MAB) to inspire, engage and advance women in Robotics and Automation. The WIE committee organizesContinue reading “Co-Chair in IEEE WIE-RAS”

Master Thesis: Discovering neural parts in objects with invertible NNs for robot grasping

In this thesis, we will investigate the use of 3D primitive representations in objects using Invertible Neural Networks (INNs). Through INNs we can learn the implicit surface function of the objects and their mesh. Apart from  extracting the object’s shape, we can parse the object into semantically interpretable parts. In our work our main focusContinue reading “Master Thesis: Discovering neural parts in objects with invertible NNs for robot grasping”

Talk @ UofT on accelerating Robot Skill Learning

My talk on “Accelerating Robot Skill Learning with Demonstrations and Models”, that I gave a few days ago at the AI in Robotics Seminar at the University of Toronto is now available online. In this talk I go through our recent works “Contextual Latent-Movements Off-Policy Optimization for Robotic Manipulation Skills” and “Model Predictive Actor-Critic: AcceleratingContinue reading “Talk @ UofT on accelerating Robot Skill Learning”

hessian.AI Connectom fund

iROSA research group has received the hessian.AI Connectom fund, which promotes interdisciplinary research in the hessian.AI ecosystem. This grant will allow researches from iROSA to work along researches from the Ubiquitous Knowledge Processing lab, led Prof. Dr. Gurevych. Our project will investigate synergies between Robot Learning and Natural Language Processing towards Learning Long-Horizon Tasks byContinue reading “hessian.AI Connectom fund”

AI Newcomer 2021

AI Newcomer 2021 of the category technical and engineering science is Dr. Georgia Chalvatzaki! “AI advances robotic research for developing intelligent agents that interact safely and assist humans” – Georgia Chalvatzaki Article in German by TU Darmstadt press news: https://www.tu-darmstadt.de/universitaet/aktuelles_meldungen/einzelansicht_313024.de.jsp KICamp21 @GeorgiaChal https://t.co/8loRXjRlCn