Speakers
In white, tutorial speakers. In grey, workshop speakers.
M.Sc. Anand, Akhil S.
Bio: Akhil S. Anand is a Postdoc at the Department of Engineering Cybernetics at the Norwegian University of Science and Technology (NTNU). He received his Ph.D. from NTNU, Norway in 2023, M.Sc. in Mechatronics from the University of Siegen, Germany in 2018, and B.Tech in Mechanical Engineering from the Indian Institute of Technology Patna (IITP), India in 2013. His Ph.D. research was in the area of robot control and reinforcement learning. During his Ph.D., Akhil has worked on a wide range of topics including model-based reinforcement learning, compliant control for robotic manipulators, dynamics movement primitives, and model predictive control. His research interest includes data-driven control, reinforcement learning, and robotics.
Talk title: Learning Transferable Variable Impedance Learning Skills with Sampling-based MPC
Talk abstract: Adaptive compliance through varying muscle stiffness is a critical aspect of human dexterity in manipulation tasks. Similarly, incorporating compliance in robot motor control is essential for robots to perform force interaction tasks with human-like dexterity. One prevalent approach for compliant robot control is variable impedance learning control. However, learning the variable impedance profile for a high degree of freedom robotic system in complex tasks is challenging. Reinforcement learning (RL) can be employed to learn such skills, but it requires a vast amount of data, and the resulting control policies may not be easily transferable to different tasks. Sampling-based model predictive control (MPC) schemes can be useful in obtaining globally optimal control policies in such scenarios. Nonetheless, a major challenge is to obtain an accurate model of the system dynamics for the MPC scheme to optimize the policy. This talk will focus on developing a variable impedance learning control scheme using sampling-based MPC schemes that can be easily transferred across multiple tasks.
Prof. Bicchi, Antonio
Bio: Antonio Bicchi is Senior Scientist at the Italian Institute of Technology in Genoa and the Chair of Robotics at the University of Pisa. He graduated from the University of Bologna in 1988 and was a postdoc scholar at M.I.T. Artificial Intelligence lab. He teaches Robotics and Control Systems in the Department of Information Engineering (DII) of the University of Pisa. He leads the Robotics Group at the Research Center "E. Piaggio'' of the University of Pisa since 1990. He is the head of the SoftRobotics Lab for Human Cooperation and Rehabilitation at IIT in Genoa. Since 2013 he serves ad Adjunct Professor at the School of Biological and Health Systems Engineering of Arizona State University.
From January, 2023, he is the Editor in Chief of the International Journal of Robotics Research (IJRR), the first scientific journal in Robotics. He has been the founding Editor-in-Chief of the IEEE Robotics and Automation Letters (2015-2019), which rapidly became the top Robotics journal by number of submissions. He has organized the first WorldHaptics Conference (2005), today the premier conference in the field. He is a founder and President of the Italian Institute of Robotics and Intelligent Machines (I-RIM) (since 2019).
His main research interests are in Robotics, Haptics, and Control Systems. He has published more than 500 papers on international journals, books, and refereed conferences. For his fundamental research on human and robot hands the European Research Council awarded him with several grants, including an Advanced Grant in 2012, an ongoing Synergy Grant in 2019, and three Proof-of-Concept grants. He is the scientific coordinator of the JOiiNT Lab, an advanced tech transfer lab with leading-edge industries in Bergamo, Italy. He is the recipient of several awards and honors.
Talk title: Modeling, Planning and Learning Interaction with Soft and Variable Stiffness Robots
Talk abstract: In animals and in humans, the mechanical impedance of their limbs changes not only in dependence of the task, but also during different phases of the execution of a task. Part of this variability is intentionally controlled, by either co-activating muscles or by changing the arm posture, or both.
In robots, impedance can be varied by varying controller gains, stiffness of hardware parts, and arm postures. The choice of impedance profiles to be applied can be planned off-line, or varied in real time based on feedback from the environmental interaction. Planning and control of variable impedance can use insight from human observations, from mathematical optimization methods, or from learning.
In this talk I will review the basics of human and robot variable impedance, and discuss how this impact applications ranging from industrial and service robotics to prosthetics and rehabilitation.
Dr. Carlone, Luca
Bio: Luca Carlone is the Leonardo Career Development Associate Professor in the Department of Aeronautics and Astronautics at the Massachusetts Institute of Technology, and a Principal Investigator in the Laboratory for Information & Decision Systems (LIDS). He received his PhD from the Polytechnic University of Turin in 2012. He joined LIDS as a postdoctoral associate (2015) and later as a Research Scientist (2016), after spending two years as a postdoctoral fellow at the Georgia Institute of Technology (2013-2015). His research interests include nonlinear estimation, numerical and distributed optimization, and probabilistic inference, applied to sensing, perception, and decision-making in single and multi-robot systems. His work includes seminal results on certifiably correct algorithms for localization and mapping, as well as approaches for visual-inertial navigation and distributed mapping. He is a recipient of the Best Student Paper Award at IROS 2021, the Best Paper Award in Robot Vision at ICRA 2020, a 2020 Honorable Mention from the IEEE Robotics and Automation Letters, a Track Best Paper award at the 2021 IEEE Aerospace Conference, the 2017 and the 2022 Transactions on Robotics King-Sun Fu Memorial Best Paper Award, the Best Paper Award at WAFR 2016, the Best Student Paper Award at the 2018 Symposium on VLSI Circuits, and he was best paper finalist at RSS 2015, RSS 2021, and WACV 2023. He is also a recipient of the AIAA Aeronautics and Astronautics Advising Award (2022), the NSF CAREER Award (2021), the RSS Early Career Award (2020), the Google Daydream (2019), the Amazon Research Award (2020, 2022), and the MIT AeroAstro Vickie Kerrebrock Faculty Award (2020). He is an IEEE senior member and an AIAA associate fellow. At MIT, he teaches “Robotics: Science and Systems,” the introduction to robotics for MIT undergraduates, and he created the graduate-level course “Visual Navigation for Autonomous Vehicles”, which covers mathematical foundations and fast C++ implementations of spatial perception algorithms for drones and autonomous vehicles.
Talk title: Dynamic Grasping with a “Soft” Drone: Theory, Experiments, and Future Challenges
Talk abstract: Rigid grippers used in existing aerial manipulators require precise positioning to achieve successful grasps and transmit large contact forces that may destabilize the drone. This limits the speed during grasping and prevents "dynamic grasping", where the drone attempts to grasp an object while moving. On the other hand, biological systems (e.g., birds) rely on compliant and soft parts to dampen contact forces and compensate for grasping inaccuracy, enabling impressive feats. This talk discusses recent progress in developing a “soft” drone - a quadrotor where traditional (i.e., rigid) landing gears are replaced with a soft tendon-actuated gripper to enable aggressive grasping. I present our algorithmic approach to control and trajectory optimization, as well as the development of a physical prototype. I conclude the talk by discussing recent progress on aggressive aerial manipulation with onboard perception and discuss future challenges.
Prof. Choi, Youngjin
Bio: Youngjin Choi received his B.S. degree in Precision Mechanical Engineering from Hanyang University, Seoul, Korea, in 1994, and M.S. and Ph.D. degrees in Mechanical Engineering from POSTECH, Pohang, Korea, in 1996 and 2002, respectively. Since 2005, he has been a professor in the Department of Robotics Engineering at Hanyang University, Ansan, Korea. From 2002 to 2005, he was a senior research scientist at the Intelligent Robotics Research Center of the Korea Institute of Science and Technology (KIST). From 2011 to 2012, he was a visiting researcher at the University of Central Florida, USA. From 2010 to 2014, he was an associate editor of the IEEE Transactions on Robotics. From 2016 to 2018, he was an associate editor of the IEEE Robotics and Automation Letters. From 2018 to 2022, he was a senior editor of the IEEE Robotics and Automation Letters. Since 2023, he has been a senior editor of the Intelligent Service Robotics. His research interests include control theory, Lie group robotics, and dual-arm manipulation.
Talk title: Design of impedance and admittance in terms of exponential coordinates on SO(3) or SE(3)
Talk abstract: For the impedance control on SO(3) or SE(3), the desired trajectory is generated according to the time progress in terms of the exponential coordinates. For this purpose, we compute it using the combination of the path and the scaling function (chosen as one of the third-order polynomial, fifth-order, trapezoidal, S-curve, and so on.) satisfying both the initial and terminal conditions on exponential coordinates. The desired exponential coordinates as functions of time are converted into the desired homogeneous transformation, desired twist, and desired acceleration for implementation of the robot control. Now we can find the twist error in body form, and also the velocity error in exponential coordinates can be defined, and further its time derivative. Ultimately, we define the impedance using exponential coordinates and a wrench. The control scheme can be designed for implementing the desired impedance using the reference acceleration in the Lie group and the reference velocity. On the other hand, admittance is also suggested in terms of exponential coordinates, although it is still ongoing work.
Prof. Lee, Dongheui
Bio: Dongheui Lee is Full Professor of Autonomous Systems at 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 (2009-2022), Project Assistant Professor at the University of Tokyo (2007-2009), and a research scientist at the Korea Institute of Science and Technology (KIST) (2001-2004). She obtained a PhD degree (2007) from University of Tokyo in Japan and B.S. (2001) and M.S. (2003) degrees from Kyung Hee University, Korea. 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.
Talk title: Variable Impedance Control, Learning, and Sensing
Talk abstract: TBD
Dr Peternel, Luka
Bio: Luka Peternel received a PhD in robotics from the Faculty of Electrical Engineering, University of Ljubljana, Slovenia in 2015. He conducted his PhD studies at the Department for Automation, Biocybernetics and Robotics, Jožef Stefan Institute in Ljubljana from 2011 to 2015, and at the Department of Brain-Robot Interface, ATR Computational Neuroscience Laboratories in Kyoto, Japan in 2013 and 2014. He was with the Human-Robot Interfaces and Physical Interaction Lab, Advanced Robotics, Italian Institute of Technology in Genoa, Italy from 2015 to 2018. Since 2019, he is an Assistant Professor at the Department of Cognitive Robotics, Delft University of Technology in the Netherlands.
Talk title: Teaching robots physical interaction skills through teleimpedance
Talk abstract: The tutorial will present methods that enable operators to teach physical interaction skills to remote robots. First, there will be a quick recap of teleoperation which is the basis for remote robot control. After that, we will examine the teleimpedance principle which enables the operator to command the impedance of the remote robot in real-time through interfaces. We will look at different types of hand- and foot-operated impedance-command interfaces and discuss their pros and cons when applying teleimpedance to different tasks/scenarios. We will learn about the coupling effect between commanded impedance and force feedback and discuss where it can be beneficial or detrimental to task performance. Finally, an overview of how teleimpedance can be used for teaching robots to execute complex tasks in unstructured and unpredictable environments will be given. Here we will also examine the advantages of learning impedance directly through teleimpedance compared to inferring it indirectly from kinaesthetic demonstrations.
Dr. Pozzi, Maria
Bio: Maria Pozzi is a Researcher at University of Siena (Italy) and Affiliated Researcher at Istituto Italiano di Tecnologia (IIT), Genova. She received her B.S. (Computer and Information Engineering, 2013), M.S. (Computer and Automation Engineering, 2015), and Ph.D. (Information Engineering and Science, 2019), all cum laude from the University of Siena. In 2021, she co-edited the IEEE RAM SI on “Emerging Paradigms for Robotic Manipulation: from the Lab to the Productive World”, she was selected as one of the RSS Pioneers, and she was invited speaker at the IFRR Global Robotics Colloquium on The Future of Robotic Manipulation. Her research interests include: robotic grasping, simulation of soft robots and haptic interfaces for collaborative robotics. www3.diism.unisi.it/~pozzi/
Talk title: Softness and Stiffness in Robotic Hands: review and perspectives
Talk abstract: This talk will summarize recent results in the design and development of soft-rigid grippers for grasping objects in unstructured scenarios.
M. Sc. San Miguel, Alberto
Bio: Alberto San Miguel Tello received the B.Sc. degree in Industrial Engineering from University of Zaragoza, Spain, the M.Sc degree in Automatic Control and Robotics from Universitat Politècnica de Catalunya (UPC). He is currently pursuing his Ph.D. in Advanced Control Techniques for Physical Interaction Control in the Institut de Robòtica i Informàtica Industrial (IRII). His research interests include compliant control, controller design and human-robot interaction.
Talk title: Safety and Adaptation in compliant Physical Interaction Control
Talk abstract: Although robotic platforms have been used for a wide range of purposes, recent advances in robot autonomy raise the opportunity of bringing them closer to humans. This implies that, under any circumstance, robots have to remain safe –i.e. not harm humans, the environment or themselves– while embedding the required adaptation means to deal with the unstructured nature of anthropic domains. Hence, initial solutions delivered reactive behaviours to avoid collisions, which is not suitable for those tasks where the robot is required to initiate, maintain or regulate contact over physical interaction with a human, an environment or both. For those scenarios, compliant control architectures have been developed, allowing robots to actively react against external forces and adapt their behaviour according to the task. But, although these solutions are a-priori conceived as safe, there still exist sources of hazard which need to be considered into their design. Hence, this talk goes through the state-of-art of compliant control solutions focusing on how safety is guaranteed and its consequences on adaptation mechanisms.
Dr. Welker, Cara G.
Bio: Cara Gonzalez Welker (Member, IEEE) received a B.S. in Biomedical and Chemical Engineering from Vanderbilt University in 2014, an M.S. in Mechanical Engineering in 2017 and Ph.D. in Bioengineering in 2021, both from Stanford University. She then performed postdoctoral training at the University of Michigan. She is currently an Assistant Professor in the Mechanical Engineering Department and Biomedical Engineering program at the University of Colorado Boulder. Her research interests include robotics, biomechanics, haptics, and assistive devices.
Talk title: Multi-activity Data-Driven Variable Impedance Control for Powered Knee-Ankle Prostheses
Talk abstract: The majority of impedance controllers designed for powered prostheses utilize a finite state machine with discrete impedance parameter sets, which can take multiple hours to tune for each individual participant in multi-activity controllers. I will present a framework for combining phase variable control with varying impedance parameters in order to provide a tuning-free, continuous solution for lower-limb prosthesis control. In this approach, convex optimization is used to determine variable impedance parameter trajectories across phase, given input data including joint kinematics and kinetics. We demonstrate the real-time application of this controller for biomimetic locomotion and improved outcomes in experiments with above-knee amputees in activities including sitting, standing, and walking at various speeds and inclines.
