Recent advances in Deep Learning (DL) have led to a number of spectacular applications, ranging from self-driving cars, and (autonomous) robots that outperform humans in various tasks, to building algorithms that can understand and answer questions by fusing information from many modalities. By integrating the ability of DL and deep reinforcement learning (DRL) to learn complex behaviours, one can efficiently train robots that can interact with all the objects around them.
However, the application of DL in robotics is not trivial and leads to specific learning, reasoning and embodiment problems and research questions that are typically not addressed by the computer vision and machine learning communities. Therefore, DL itself is an important area to be investigated, rather than only focussing on its applications.
The first objective pursued through this workshop is to show and present how using artificial intelligence (AI) and DL in robotics can highly improve people’s lives. In addition, after the pandemic situation that has unfolded worldwide over the past few months, with uncertainties and the need to try to maximize all the resources in different sectors, especially in healthcare, it is crucial to raise awareness of the multiple and flexible solutions that robotics can provide. The second objective of the workshop is to show the importance of having an open DL toolkit for the robotics community, a fact that has been identified as an important goal of the European Union (EU) research in robotics.
While this workshop will focus on the design of an open toolkit for DL, the discussions will not be restricted to DL, but we will initiate fruitful discussions to have further open toolkits for various robotic methods.
DL models are becoming more and more complex, requiring vast amounts of computation power and energy. These requirements are becoming especially limiting in many robotics applications, where significant energy and computation power constraints exist.
In summary, the need for open toolkits in robotics, such as a DL toolkit that contains easy to train and deploy, real-time, lightweight, ROS-compliant DL models for robotics, is a must. This workshop aims to gather experts to share their experiences in terms of opportunities and challenges in using further open toolkits in robotics.
We believe the more researchers with access to open tools and data required to develop AI-based systems, the more innovations we will have.
Deep Learning for Robotics
Deep robot active perception and cognition
Deep robot decision making
Assistant Professor & Director of Robot Learning Lab
University of Freiburg
Abhinav Valada is an Assistant Professor and Director of the Robot Learning Lab at the University of Freiburg, Germany. He is a member of the Department of Computer Science, the BrainLinks-BrainTools center and a founding member of the ELLIS unit Freiburg. Abhinav is co-chair of the IEEE Robotics and Automation Society Technical Committee on Robot Learning and a Scholar of the ELLIS Society. He received his PhD with distinction from the University of Freiburg and his MS in Robotics from The Robotics Institute of Carnegie Mellon University. He co-founded and served as the Director of Operations of Platypus LLC, a company developing autonomous robotic boats, and has previously worked at the National Robotics Engineering Center and the Field Robotics Center of Carnegie Mellon University. Abhinav Valada's research lies at the intersection of robotics, machine learning and computer vision with a focus on tackling fundamental robot perception, state estimation and planning problems using learning approaches in order to enable robots to reliably operate in complex and diverse domains. His Robot Learning group has developed several innovative techniques for multimodal sensor fusion, state estimation and scene understanding that have defined the state of the art and ranked at the top of benchmarks.
Alexandros Iosifidis is an Associate Professor at Aarhus University, Denmark. He leads the Machine Learning & Computational Intelligence group at the Department of Electrical and Computer Engineering. He is also leading the Machine Intelligence research area of the Centre for Digitalisation, Big Data and Data Analytics (DIGIT) at Aarhus University. He is a Senior Member of the Institute of Electrical and Electronics Engineers (IEEE) and he served as an Officer of the Finnish IEEE Signal Processing-Circuits and Systems Chapter from 2016 to 2018. As of 2020 he is a member of the Technical Area Committee on Visual Information Processing of the European Association of Signal Processing (EURASIP). He is currently serving as Associate Editor in Chief for the Neurocomputing journal, covering the research area of Neural Networks. He contributed to the organization of several international conferences as an Area Chair or Technical Program Committee Chair, including IEEE ICIP (2018-2021), EUSIPCO (2019,2021), and IEEE ICASSP (2019). He has contributed to more than twenty R&D projects financed by EU, Finnish, and Danish funding agencies and companies. He has co-authored 85+ articles in international journals and 100+ papers in international conferences/workshops in topics of his expertise. He received EURASIP Early Career Award 2021 for contributions to Statistical Machine Learning and Artificial Neural Networks.
Francisco Martin Rico
Rey Juan Carlos University
Francisco is an associate professor at Rey Juan Carlos University (Madrid, Spain) and leader of the Intelligent Robotics Lab. He is an expert in ROS/ROS2 development and teaching, leading and collaborating with projects like PlanSys2, Nav2 Behavior Trees, or rclcpp, among many others. His research interests are Artificial Intelligence, Mobile Robotics, Cognitive Architectures, and related technologies. He has carried out research stays at the robotics labs in Carnegie Mellon (Pittsburgh, PA), University of Essex (Colchester, UK), and CAE-List (Paris, Fr).
Delft University of Technology (TUD)
Laura Ferranti received her M.Sc. degree in Control Engineering from the University of Rome "Tor Vergata'', Rome, Italy, in 2012, and her PhD from Delft University of Technology, Delft, The Netherlands, in 2017. She is currently an assistant professor in the Cognitive Robotics (CoR) Department, Delft University of Technology, where she coordinates the Reliable Robot Control (R2C) Lab . She is the recipient of an NWO Veni Grant from The Netherlands Organisation for Scientific Research (2020), and of the Best Paper Award in Multi-robot Systems at ICRA 2019. Her research interests include numerical optimization, model predictive control, reinforcement learning, and cyber security with application in automotive, flight control, maritime transportation, and robotics.
Founder of AGROINTELLI and the commercial ag-robot Robotti. With 20 years of experience in developing and implementing automation and robotic technologies, intelligent weed management strategies and integration of sensor technology for sustainable intensification of plant production. Honorary Professor in technology and intelligent solutions for sustainable soil management at Aarhus University.
Roel Pieters received his Ph.D. degree in The Netherlands at Eindhoven University of Technology in 2013. From 2013 till 2017 has was a post-doctoral researcher in ETH Zurich, Switzerland (3 years) and Aalto University, Finland (1 year). Currently, he works at the unit of Automation Technology and Mechanical Engineering, Tampere University, Finland, as associate professor in the field of cognitive and collaborative robotics. His research interests are cognition, perception and autonomy for human-robot interaction, applied in industrial and domestic settings. His research has led to two spin-offs and won several design and best paper awards and he is (co-)responsible for Tampere University's robotics major and Tampere Robolab.
Associate Professor Department of Electrical Engineering and Information Technology - D.I.E.T.I.
University of Naples Federico II
Silvia Rossi is Associate Professor at Università di Napoli Federico II. She is the leader of the PRISCA lab (prisca.unina.it). Her research expertise includes AI and Multi-agent Systems, Human-Robot Interaction, Cognitive Architectures, Behaviour-based Robotics, User Profiling and Recommender Systems. She is currently principal investigator of the national project BRILLO - Bartending Robot for Interactive Long-Lasting Operations (2019-2022) and is Principal Investigator of the CHIST-ERA IV - COHERENT project - COllaborative HiErarchical Robotic ExplaNaTions. Prof. Silvia Rossi was coordinator of the UPA4SAR “User Profiling and Adaptation for Socially Assistive Robotics” (Italian Ministry of Education, University, and Research under program PRIN 2015) and she is currently coordinator of H2020-MSCA-ITN PERSEO - European Training Network on Personalized Robotics as Service Oriented Applications (2021-2024) which aims to build personal robots which are capable of tailor their behaviours with respect to the users’ needs in the edutainment and healthcare contexts. She is associate editor for the International Journal of Social Robotics, Intelligent Service Robotics, Pattern Recognition Letters, and IEEE Robotics and Automation Letters (RA-L). Prof. Rossi is also very active in the Social Robotics community, as Conference Organiser, Session Chair and Program Chair member of different events such as ICSR, HRI and RO-MAN. She is General Chair of the 31th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN 2022).
Stefania received a BSc in Computer Science and a MSc in Robotics at the ETH Zürich (Switzerland) in 2011. Since 2012 she's working at Cyberbotics Ltd. contributing with several major improvements to the Webots robot simulator functionality and developing simulation models in Webots. She also worked at the development of the robotbenchmark.net web simulation platform and led the technical development in various projects to create custom Webots simulation scenarios and interfaces for agricultural and industrial applications.
16:00 - 16:05
Francesco Ferro, Sofia Battilana
16:55 - 17:00
Deep Learning and AI Applications
in the Webots Robot Simulator
16:05 - 16:10
Robotic grasping in Agile Production
Roel S. Pieters
17:00 - 17:05
Deep Learning models for efficient
video-based action recognition
16:10 - 16:15
Learning Efficient Representations for Perception, Tracking, and Localization
17:05 - 17:10
Using Open Deep Learning Toolkits
Francisco Martin Rico
16:15 - 16:20
How to benefit from learning in predictive control
17:10 - 17:15
European Training Network on Personalized Robotics as Service Oriented applications
16:20 - 16:25
Business perspectives and applications of OpenDr for AGROINTELLI
17:15 - 17:45
Stefania Pedrazzi, Alexandros Iosifidis, Francisco Martin Rico, Silvia Rossi
16:25 - 16:55
Jens Kober, Roel S. Pieters, Abhinav Valada,
17:45 - 18:00
If you haven't registered yet to attend IROS, click in the button below.