Josip Josifovski

prof_pic.jpg

Office: 1.103

Schleißheimer Straße 90A,

85748 Garching, Germany

Hey there,

Welcome to my personal website! I’m Josip, and I’m currently based in Munich, where I’m a PhD candidate at the Technical University of Munich and a research assistant at the Chair for Robotics, Artificial Intelligence, and Real-Time Systems.

Before this, I earned a master’s degree in Intelligent Adaptive Systems from the University of Hamburg and a bachelor’s degree in Informatics and Computer Engineering from the Ss. Cyril and Methodius University in Skopje.

My research interests lie at the intersection of robotics and machine learning. Specifically, I focus on simulation-based continual robot learning models and their subsequent transfer to the real world.

news

Nov 09, 2024 Our workshop paper on Learning a Risk-Averse Locomotion Policy from Uncertainty Estimates was presented at the CoRL 2024 LocoLearn Workshop in Munich, Germany.
Jul 10, 2024 Our paper State Representations as Incentives for Reinforcement Learning Agents: A Sim2Real Analysis on Robotic Grasping was accepted at the IEEE SMC 2024 conference in Sarawak, Malaysia.
Jul 01, 2024 Our paper Continual Domain Randomization was accepted at IROS2024 in Abu Dhabi. Code and videos are available at https://continual-dr.github.io/
Jun 14, 2024 I participated at the RPL Summer School organized py the KTH Division of Robotics, Perception and Learning in Stockholm, Sweden
Jun 04, 2024 I gave a talk on “Simulation-based Continual Robot Learning – Challenges and Opportunities” on invitation from the L3S research center at Leibniz Universität Hannover
Apr 11, 2024 I was part of the technical committee of the Workshop on Human-aligned Reinforcement Learning for Autonomous Agents and Robots (HARL) in the scope of ICRA2024 in Yokohama, Japan
Apr 05, 2024 Our article Visuo-Haptic Object Perception for Robots: An Overview was listed among the Top 10 Downloaded Articles 2023 of the Autonomous Robots Journal from Springer Nature.
Mar 23, 2024 Our new preprint Continual Domain Randomization is out.
Oct 30, 2023 We held a talk on the Aspects of Sim2Real Transfer for Industrial Robotics: A Perspective from Robust Control and Continual Reinforcement Learning on invitation from ROS Germany
Jul 11, 2023 I took part in the very exciting ten-day Reinforcement Learning Summer School in Barcelona, Spain.