10 July 2023
IV Tutorial & Workshop on
Variable Impedance Learning and Control: From the Foundations to the Future Perspectives
at 2023 Robotics: Science and Systems (RSS)
Daegu, Republic of Korea
Welcome!
This is the website of our hybrid tutorial/workshop "Variable Impedance Robotic Skills: From the Foundations to the Future Perspectives".
During the first part (half-day), a tutorial-like event will be organized. Young students and researchers will have the opportunity to listen to a few introductory talks about the topics of the event, as well as to do hands-on activities. These practical activities include the use of simulation environments and the implementation of standard control algorithms and techniques, creating favorable circumstances for the participants to obtain/enhance their technical skills and intuitions on the topic. The participation of the audience will be constantly encouraged during the talks and hands-on sessions.
On the second part (half-day), we will follow a more traditional workshop scheme. Talks will be given by renowned researchers in the area, who will give a broad overview of the state of the art, current challenges, and future perspectives on the main topics of the event. To stimulate interaction, we will organize a spotlight talk session during the workshop to encourage the participation of young researchers also in this part of the event, promoting discussions between the speakers and the audience. In both the tutorial as well as in the workshop part of the event, we will also allocate adequate time for questions and discussions to make the workshop as interactive as possible. At the end of the workshop, a guided discussion panel will take place with open questions from the audience to all the workshop speakers and participants.
Context
Robots interacting with humans and their surroundings are becoming more and more present every year, and therefore, it is of utmost importance to provide them with safety features and robustness. This safety can be achieved through passive mechanisms, but these are limited in their performance. Instead, active control strategies are a more general and flexible approach that allows to better adapt the robot’s behavior to the environment and the task requirements.
Impedance control is a common active approach that enables robots to behave in a more human-like manner by adjusting the relation between force and velocity. Variable impedance control (VIC), has thus gained popularity in dealing with the changes in the environment, the interaction with humans and the increasing complexity of tasks. Applications of VIC have shown significant improvements over previous methods in human-robot interaction, soft robotics, manipulation of deformable objects, or prosthetics control. Nevertheless, inferring a variable impedance profile in certain tasks without ad-hoc implementations can be a challenging problem, not only because of the presence of external interactions of unknown nature, but also because the robustness of the controller needs to be ensured. Latest trends in VIC also use optimal control tools such as model predictive control and data-driven machine learning techniques, to learn and implement VIC methods that can better represent and adapt to the underlying nature of a task.
This proposal aims to be the fourth event on the topic of Variable Impedance Learning and Control. The first one was organized at IROS’18, followed by IROS’21 and RSS’22. All of them were very successful with about 90+/-20 attendees, and the format allowed for very fruitful discussions on the topic between academics and students. In this RSS'23, we propose a similar format to that of the previous edition, at RSS'22, with a combined - and interactive - format. Introducing this topic of physical interaction control to junior researchers and students in a tutorial-like way. The very basic theoretical foundations on this topic will be presented, followed by hands-on activities, as described in the next section. This half-day tutorial will give this junior audience the basic background needed to better understand the second part of the workshop, where different experts will be brought together to discuss the current challenges and perspectives of this field in robotics. The main intended audience of this second-half part of the workshop is more senior researchers and students that already work on this topic, as the talks will be more detailed and focused. Special attention was given to providing a diverse spectrum of prestigious speakers, from different seniority, gender, ethnicity, as well as geographic location, as detailed in the next sections.
Discussion Topics
Variable impedance control (VIC);
Physical human-robot cooperation and human impedance;
Learning and optimal control applied to physical interaction;
Variable impedance strategies for mobile robots;
Benchmarking of impedance controllers;
VIC from geometry awareness and manifold learning perspective;
The Invited Speakers
Akhil S. Anand
Norwegian University of Science and Tecnology, Norway
Antonio Bicchi
University of Pisa, Italy
Luca Carlone
Massachusetts Institute of Tecnology, USA
Youngjin Choi
Hanyang University,
Republic of Korea
Dongheui Lee
Technische Universität Wien, Austria
Luka Peternel
Delft University of Technology,
The Netherlands
Maria Pozzi
University of Siena,
Italy
Alberto San Miguel
Eurecat & Universitat Politècnica de Catalunya, Spain
Cara G. Welker
University of Colorado, Boulder, USA