Keynote Speakers

Alessandro De Luca
Sapienza Università di Roma

Title: Control of soft joint robots for safe physical HRI

Abstract: In the early days, joint flexibility in industrial robots equipped with compliant transmissions was seen mainly as a negative effect to be milden as much as possible. Stiffening control laws were used to remove static deflections and suppress vibrations during execution of dynamic trajectories. This control approach led eventually to complete cancellation of the nonlinear fourth-order dynamics based on feedback linearization. The next step was the development of torque-controlled robots, in which the presence of joint elasticity was masked by the use of joint torque sensors and low-level feedback loops for the approximate recovery of a rigid dynamics. This allowed a seamless transfer of control results from the rigid case, e.g., impedance control to handle safe human-robot interaction and contacts with the environment. Indeed, if joint compliance is included on purpose, like in SEA- and VSA-based robots, it seems quite naïve to pursue its removal by feedback. The control challenge is to take advantage of the natural dynamics to get better performance with reduced effort. To this end, I will present a framework based on the principle of feedback equivalence, which was recently applied to a number of control tasks in compliant robots. The goal is to introduce the least possible modification of the original fourth-order dynamics, while matching a desired target behavior via nonlinear state feedback. The concept will be illustrated through a few simple examples: exact cancellation of gravity on robot links, injection of viscous damping in the link dynamics, and imposition of a generalized impedance model for interaction control.

Biography: Alessandro De Luca is Professor of Robotics and Automation and Director of the Master in Control Engineering at DIAG, Sapienza University of Rome. He has been the first Editor-in-Chief of the IEEE Transactions on Robotics (2004-08), RAS Vice-President for Publication Activities in 2012-13, General Chair of ICRA 2007, and Program Chair of ICRA 2016. He received three conference awards (Best paper at ICRA 1998 and BioRob 2012, Best application paper at IROS 2008), the Helmholtz Humboldt Research Award in 2005, the IEEE-RAS Distinguished Service Award in 2009, and the IEEE George Saridis Leadership Award in Robotics and Automation in 2019. He is an IEEE Fellow, class of 2007. His research interests cover modeling, motion planning, and control of robotic systems (flexible manipulators, kinematically redundant arms, underactuated robots, wheeled mobile robots), as well as physical human-robot interaction. He was the scientific coordinator of the FP7 project SAPHARI – Safe and Autonomous Physical Human-Aware Robot Interaction (2011-15). More info at

Robin Murphy
Texas A&M University, Center for Robot-Assisted Search and Rescue

Title: Robots for Unstructured and Extreme Environments

Abstract: Since 2001, land, aerial, and marine robots have assisted responders in saving lives, reducing suffering, and accelerating economic recovery. However, disasters present major design challenges for robots as the environment is usually unstructured, and the robots, as well as the operators, are working under extreme conditions. The design process for robots intended for these applications is made even more difficult by the lack of data on unstructured, extreme environments and the absence of formal methods to characterize the work envelope or predict system performance. This talk will summarize our work over the past 20 years which includes deployments to 28 events in five countries, including the 9/11 World Trade Center, the Japan tsunami, and Hurricane Harvey. The work has led to a set of metrics for characterizing unstructured environments which can be used for robot design or to select a robot for a particular mission at a disaster. The analysis also describes how robots fail in the field and offers a comprehensive taxonomy of navigational and mission risks. Human-robot interaction is an overlooked influence on successful robot performance and our work has also explored the difference between operating robots in normal and emergency conditions. Extensive video illustrating the lessons learned to date will be shown.

Biography: Dr. Robin R. Murphy is the Raytheon Professor of Computer Science and Engineering at Texas A&M University, a founding director of the Center for Robot-Assisted Search and Rescue, and an IEEE fellow. She helped found the fields of disaster robotics and human-robot interaction, concentrating on developing human-centered AI for ground, air, and marine robots. Her work is captured in over 150 scientific publications including the award-winning book Disaster Robotics and a TED talk as well as a textbook Introduction to AI Robotics (second edition 2019). Murphy has deployed robots to over 28 disasters in five countries including the 9/11 World Trade Center, Hurricane Katrina, 2 mine disasters, Fukushima, the Syrian boat refugee crisis, Hurricane Harvey, and the Kilauea volcanic eruption. Murphy’s contributions to disaster robotics have been recognized with the ACM Eugene L. Lawler Award for Humanitarian Contributions, the AUVSI Foundation’s Al Aube Award, and the Motohiro Kisoi Award for Rescue Engineering Education.

Martin Riedmiller

Title: Robots that learn from scratch

Abstract: Being able to autonomously learn ‘from scratch’ - i.e. with a minimum amount of prior knowledge - is a key ability of intelligent systems. This credo is the driving motivation behind our research on reinforcement learning methods for the control of dynamical systems. While we have seen tremendous progress in the area of deep reinforcement learning in the last couple of years, its direct application to real systems still remains a challenge. Key requirements for agents mastering the real world are data-efficiency and reliability of learning, since data-collection in real environments, e.g. on real robots, is time intensive and often expensive. I will highlight two main areas of progress that we consider crucial for progress towards this goal - improved off-policy learning methods from large data sets and better exploration. I will give examples of simulated and real robots that, by following these principles, can learn increasingly complex tasks from scratch.

Biography: Martin Riedmiller is a research scientist and team-lead at DeepMind, London. Before joining DeepMind fulltime in spring 2015, he held several professor positions in machine learning and neuro-informatics from 2002 to 2015 at Dortmund, Osnabrück and Freiburg University. From 1998 to 2009 he lead the robot soccer team ‘Brainstormers’ that participated in the internationally renowned RoboCup competitions. As an early proof of the power of neural reinforcement learning techniques, the Brainstormers won the world championships for five times in both simulation and real robot leagues. He has contributed over 20 years in the fields of reinforcement learning, neural networks and learning control systems. He is author and co-author of some early and ground-lying work on efficient and robust supervised learning and reinforcement learning algorithms, including work on one of the first deep reinforcement learning systems.

Koichi Suzumori
Tokyo Institute of Technology

Title: Soft Robotics as E-kagen Science

Abstract: In this presentation, I will discuss three topics on soft robotics.
  1. Since 1986, I have been developing various types of soft actuators; they include pneumatic rubber actuators, thin artificial muscles, functional rubber surfaces. I will be discussing them and their applications to medical robots, soft power support suits, musculo-skeletal robots, and Giacometti robots.
  2. Last year, the MEXT KAKENHI project on soft robots was initiated in Japan with a budget of 1.2 billion yen and a research period of five years. Approximately 20 research groups participate in this project that I will now introduce.
  3. I think soft robotics is a value changer in robotics. Soft robots are considered “bad robots” from the viewpoints of traditional robotics that seek power and accuracy. However, soft robots realize safety, adaptability, and compliance easily, which are important properties in several new robot applications. I will discuss my opinions on the significance of soft robotics with the help of a Japanese word “E-kagen”, which has two contrasting meanings. On the positive side, it could mean suitable, adaptable, and flexible; on the negative side, loose, imprecise, and arbitrary. It is very interesting that these two opposite meanings correspond to the good and poor aspects of soft robots.
Biography: Koichi Suzumori received his Ph.D. degree in mechanical engineering from Yokohama National University in 1990. He worked for Toshiba R&D Center from 1984 to 2001, and for Micromachine Center, Tokyo, from 1999 to 2001. He was then a Professor at Okayama University from 2001 to 2014. Since 2014, he has been a Professor at Tokyo Institute of Technology. He has developed various types of new actuators and applied them to new robots including soft robots, micro robots, and tough robots. He established a start-up venture company, s-muscle Co., Ltd., in 2016, which puts his soft thin artificial muscles into practical uses.