Speakers

Dongheui Lee is Professor of Autonomous Systems at Institute of Computer Tech, Faculty of Electrical Engineering and Information Technology, TU Wien. She is also leading a Human-Centered Assistive Robotics group at the German Aerospace Center (DLR). Her research interests include human motion understanding, human robot interaction, machine learning in robotics, and assistive robotics. Prior to her appointment at TU Wien, she was Assistant Professor and Associate Professor at Technical University of Munich and Project Assistant Professor at the University of Tokyo. She obtained a PhD degree (2007) from the department of Mechano-Informatics, University of Tokyo in Japan. She was awarded a Carl von Linde Fellowship at the TUM Institute for Advanced Study and a Helmholtz professorship prize. She has served as Senior Editor and a founding member of IEEE Robotics and Automation Letters (RA-L) and Associate Editor for the IEEE Transactions on Robotics. 

Talks:  Collaborative robot programming for factory of the future 

Manufacturing factories have been transitioning from conventional factory automation, where robots execute exactly known repetitive tasks without uncertainties, to the factory of the future, employing digitalization, flexible layouts, collaborative robots, etc. One of challenges in industrial robots for industry 4.0 is intuitive interfaces for robot programming and adaptation to a systematically changing environment. Robot programming by human demonstrations can provide an efficient way to learn new skills through human guidance, which can reduce time and cost to program the robot. Robot learning architectures can provide a comprehensive framework for learning, recognition and reproduction of manufacturing skills. In this talk, I will introduce our recent research on robot learning from demonstrations which could be applied to industrial tasks. Especially effective kinesthetic teaching method, learning conditional skills and contact rich skills will be discussed.

Jan Seyler studied Scientific Computing in Heidelberg – a specialization that combines mathematics, physics and computer science. He worked on his doctorate at Daimler and the University of Erlangen-Nuremberg on the topic of “Formal Analysis of the Timing Behavior of Ethernet for In-Car Communication”. The proud father of a son has been working at Festo since 2015. He started as an embedded programmer, then helped build the Semantic Data Platform for Festo products. In 2018, he was one of the people in charge of the Festo AI Competence Team, and since 2020, he has headed the Control Engineering and Artificial Intelligence department in Festo Research and Advanced Engineering. Jan is also a lecturer for IoT and AI at the DHBW in Stuttgart and the University of Applied Sciences in Esslingen. 

Talks: The Path to Autonomous Systems: Recent Advances and Future Challenges of Robotic AI in Industrial Automation 

In this session, the Head of Advanced Development AI, Robotics and Control Engineering at Festo, will discuss "The Path to Autonomous Systems: Recent Advances and Future Challenges of Robotic AI in Industrial Automation". The talk will delve into the latest breakthroughs that have transformed the field of industrial automation, such as novel machine learning algorithms, advanced control systems, and their integration into autonomous robots. It will also address looming obstacles that confront the further adoption of AI-driven robotics, including issues of reliability, safety, and interpretability. The speaker will illuminate the practical implications of these advancements and challenges for 'Future Factories', underscoring the potential of AI and robotics to revolutionize manufacturing processes, enhance efficiency, and ultimately reshape the industrial landscape. This talk aims to provoke a forward-thinking dialogue on the journey to fully autonomous industrial systems and the future of work. 

Here is the short bio.

Talks: Update soon ...

Aleš Ude received the diploma degree in applied mathematics from the University of Ljubljana, Slovenia, and the Dr.Eng. degree from the University of Karlsruhe, Germany, in 1990 and 1995, respectively. He is currently the Head of the Department of Automatics, Biocybernetics, and Robotics, Jožef Stefan Institute, and a professor at the Faculty of Electrical Engineering, Ljubljana. He is also associated with the ATR Computational Neuroscience Laboratory, Kyoto, Japan. His research interests include robot learning, programming by demonstration, reconfigurable robotic systems, and humanoid robotics. He has been a coordinator and/or principal investigator of numerous national and international projects in these areas. 

Talks: Exploiting Environmental Constraints: A Hierarchical Framework for Learning Robotic Contact Policies

There are many tasks where a robot needs to move in a tight contact with the environment. It is often assumed that such tasks are difficult to learn because the robot needs to both move correctly and apply correct wrenches to successfully perform the desired task in a possibly unknown environment. In this talk I will present a novel hierarchical framework for learning robotic contact policies. It consists of three layers that include a controller for following space constraints, a discovery mechanism to identify the correct set of motion primitives for the desired task, and a reinforcement learning algorithm to identify the optimal sequence of motion primitives to perform the task. The main advantage of the proposed approach is a fast learning rate which is due to the ability of the approach to exploit environmental constraints during the learning process. 

Here is the short bio.

Talks: will be updated in August

Dr. Miao Li is an associate professor at Wuhan University in China. He received the Bachelor and Master’s degree in Mechanical Engineering from Huazhong University of Science and Technology (HUST), China in 2008 and 2011 respectively, and PhD in École Polytechnique Fédérale de Lausanne (EPFL) in Switzerland, 2016. Miao received the 2018 EPFL ABB Award for his PhD thesis titled Dynamic Grasp Adaptation – From Humans to Robots. He has co-chaired the IEEE RAS Technical Committee on Collaborative Automation for Flexible Manufacturing. His research is in the area of robot learning, object grasping and manipulation and human-robot interaction.Miao Li is also a co-founder of several start-ups working on intelligent industry robots for real-world problems. 

Talk: Robust Grasping of Objects - From Hundreds to Millions 

Robotic grasping is a long standing research topic but remains largely unsolved towards achieving human-level dexterity and graspability. Tremendous progress has been made in recent years, with the goal to move robotic grasping towards the real-world applications. In this talk, I will review these progress of robotic grasping from a practical and industry-oriented perspective, ranging from perception, grasp planning and control to the extrinsic sensors and robots including robotic hands. Subsequently, the limits and existing hurtles of current grasping pipeline is discussed, taking into account the transferability to the real-world grasping tasks. Finally, for the case of grasping in manufacturing and logistics, the typical working scenarios are depicted.

João Cavalcanti Santos is an Assistant Professor of robotics at the University of Montpellier, France. He received the B.Eng. and M.Sc. degrees in mechanical engineering from the University of S ̃ao Paulo, Brazil, in 2015 and 2017, respectively. He received the Ph.D. degree in 2020 from LIRMM, Montpellier, France, where he participated in the design and control of a cable-driven parallel robot in the European H2020 project Hephaestus. From 2020 to 2022, he was a Posdoctoral Fellow with INSERM in Montpellier, France, developing mechatronic and control solutions for surgical robots. His main research interests include robot design and control, numerical optimization, and model predictive control.

Talks: Machine Learning as a Tool for Dealing with Non-expert Users and Unstructured Environments

Efficiency and productivity in industrial manufacturing are increasingly related to the perception and control of systems that can be hardly dealt with classical approaches. Numerous recent robotic applications attempt to take into account the interactions with non-expert users and unstructured environments. This talk is an overview of recent results obtained at LIRMM (Montpellier, France) applying machine learning in this context. I will present a zero-shot learning tactile recognition strategy and an intuitive robotic programming approach designed for non-expert users based on gestures. Additionally, the advantages that can be obtained coupling machine learning and model predictive control are discussed.

Javier Alonso-Mora is an Associate Professor at the Delft University of Technology, where he leads the Autonomous Multi-robots Lab. He received his Ph.D. degree in robotics from ETH Zurich, in partnership with Disney Research Zurich, and he was a Postdoctoral Associate at the Computer Science and Artificial Intelligence Lab (CSAIL) of the Massachusetts Institute of Technology. His research focuses on navigation, motion planning, and control of autonomous mobile robots, with a special emphasis on multi-robot systems, mobile manipulation, on-demand transportation, and robots that interact with other robots and humans in dynamic and uncertain environments. He currently serves as associate editor for IEEE Transactions on Robotics and for Springer Autonomous Robots. He is the recipient of a talent scheme VENI award from the Netherlands Organisation for Scientific Research (2017), the ICRA Best Paper Award on Multi-robot Systems (2019) and an ERC Starting Grant (2021).