Keynote Speakers

Short bio: Cosimo Della Santina is Assistant Professor at TU Delft, and Research Scientist at the German Aerospace Institute (DLR). He received his PhD in robotics (cum laude, 2019) from University of Pisa. He was then a visiting PhD student and a postdoc (2017 to 2019) at the Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT), and a postdoc (2020) at the department of Informatics, Technical University of Munich (TUM). Cosimo has been awarded with euRobotics Georges Giralt Ph.D. Award (2020), and the “Fabrizio Flacco” Young Author Award of the RAS Italian chapter (2019). He also has been a finalist of the European Embedded Control Institute PhD award (2020). His main research interests include (i) Modelling for control and model based control of soft robots, (ii) Combining machine learning and model based strategies with application to mechanical systems, (iii) Soft robotic hands/prostheses. Website

Title of the talk: Developing a Motor Brain for Continuum Soft Robots: the Model Based Way

Abstract: Leveraging the capabilities provided by their continuously deformable bodies, continuum soft robots promise to have a disruptive impact on several fields of science, industry, and society. In the past decade, substantial progress has been made in the development of soft robotic bodies. But soft robotic systems are still in need of a low level artificial brain that can robustly manage the intelligence embedded in their complex mechanical structures. In this talk, I will discuss the model based view to this grand challenge within the soft robotic field. I will show how simplified models can be combined with nonlinear control theory, leading to the execution of tasks that are precise and dynamic. I will also discuss how the model based view can be integrated with data driven techniques, towards higher levels of motor performance.

Short bio:  Manolo Garabini graduated in Mechanical Engineering and recieved the Ph.D. degree in Robotics from the University of Pisa where he is employed as Assistant Professor. His main research interests are in the design, planning and control of soft and adaptive robots, from single joints, to end-effectors (hands, grippers, feet), to complex multi-dof systems. A part of his activity has been devoted to theoretically demonstrate the effectiveness of soft and adaptive robots in high performance, high efficiency and resilient tasks via analytical and numerical optimization tools. He contributed to the realization of modular Variable Stiffness Actuators. He contributed in the design of the joints and the lower body of the humanoid robot WALK-MAN and partecipated at the DARPA Robotics Challenge and at a field test in Amatrice, Italy after a disastrous earthquake event. Recently he contributed to the development of an efficient and effective compliance planning algorithms for interaction under uncertainties. Currently, he is the Principal Ivestigator in the THING H2020 EU Research Project for the University of Pisa and he is the coordinator of the NI H2020 EU Research Project. He is co-founder of qbrobotics s.r.l. and XStar Motion s.r.l. Website

Title of the talk: Towards robotic environmental monitoring of habitats

Abstract: Global warming and pollution are threatening the survival of one million over the eight million species on the planet. The European answer to these threats is contained in the European Green Deal that recognizes the paramount importance of environmental monitoring, which today is entirely executed by human operators. Natural Intelligence H2020 project aims to serve the European Green Deal with robots able to accomplish monitoring of natural habitats.

The NI approach is composed of three interconnected components: environment, body, and mind. The environment, central for the NI research agenda, will provide on one side, requirements for the technologies composing the body and the mind, and on the other side the field against which such technologies will be validated.

The field validation will be carried out through the testing of three integrators on four habitats: dunes, grasslands, forests, and screes. The whole process will generate metrics, protocols, and testbeds to benchmark the technologies developed within the project.

Short bio: Matteo Saveriano received the Bachelor and Master degrees from Università degli Studi di Napoli "Federico II" in 2008 and 2011 respectively, and a Ph.D. from the Technical University of Munich in 2017. After his Ph.D., he was a post-doctoral researcher at the German Aerospace Center (DLR) and at the University of Innsbruck. He is currently a tenure-track assistant professor at the Department of Computer Science and at the Digital Science Center of the University of Innsbruck. His research is at the intersection between learning and control and attempts to integrate cognitive robots into smart factories and social Environments through the embodiment of AI solutions, inspired by human behavior, into robotic devices. Website

Title of the talk: Learn To Be Stable: Imitation Learning with Dynamical Systems

Abstract: Imitation learning, which is the capability of learning new skills by imitating other people’s actions, is a big driver in the development of sensory-motor system in human beings. In robotics, imitation learning arises as a prominent approach to rapidly acquire new skills without explicitly programming them. This talk presents data-driven approaches to learn stable robotic skills from human demonstrations. The key idea is to represent the motion as a parameterized dynamical system and to learn the parameters while preserving the stability of the system. We then discuss several useful properties of the dynamical system formulation and show how to exploit them for constrained and reactive motion planning. The last part of the talk presents on-going research on learning periodic orbits evolving on Riemannian manifolds.

Short bio: Maximo A. Roa is a Senior Scientific Researcher at the Institute of Robotics and Mechatronics in the German Aerospace Center - DLR. He heads the group of Robotic Planning and Manipulation, focused on development and implementation of locomotion and manipulation skills at different levels for industrial, service and humanoid robots. His research interests also include development of mechatronic devices, torque-based control, and space robotics. He received his PhD in 2009 from Universitat Politecnica de Catalunya, and also holds the Project Management Professional (PMP) Certification since 2016. Dr. Roa is an IEEE Senior Member, and served as co-chair of the IEEE-RAS Technical Committee on Mobile Manipulation from 2013 until 2019. He is also member of ASME, IAU, and PMI. Website

Title of the talk: Compliant grasping: exploiting mechanical intelligence and environmental constraints

Abstract: Robotic grasping is still a challenge due to the large variation of object properties found in real world scenarios. To robustify grasping applications, especially in the logistic domain, we developed the CLASH hand. The main feature of this compliant end effector is its variable stiffness, which allows it to naturally adapt to the object weight and properties, while being able to withstand collisions with the environment. Embedded ToF and tactile sensors, among others, provide the information required to quickly recover from potential failures, and to continue operation even in the case of problems in the motors or tendons. The hand can thus pick very delicate and light objects, such as a strawberry, or heavy and rigid objects, such as a melon. An automatic manipulation pipeline is also presented, to provide autonomous exploitation of the hand properties and environmental constraints in challenging settings. Open problems in the robotic manipulation domain will be highlighted during the talk.

Following Franka's mission of making Robotics accessible for everyone, our Academia Product Manager Mohamadreza Sabaghian will speak about Advanced Intelligent Mechatronics. He is going to give an introduction on "The Reference Platform for AI & Robotics" with illustrative examples of how the platform can be used by researchers in different disciplines. Website