2nd Workshop on Assistive Robotic Systems: Physical Human-Robot Shared Autonomy (pHR-SA)
Outline and Objectives
Shared autonomy (SA) in robotics is defined by the seamless adaptation of a robot autonomy level based on its understanding of the surrounding environment and, more importantly, of the accompanying agents’ (e.g., humans or other robots) state, ability, intentions, and actions, towards accomplishing a common goal. The novel concept of physical Human-Robot Shared Autonomy (pHR-SA) encompasses all SA applications that involve physical contact between humans and robots.
This physical contact could be direct when it occurs firsthand between humans and robots, or indirect when is mediated via a third item.
In particular, we are interested in those applications that integrate and combine human users' inputs with automated physical assistance and/or support from the robot. Indeed, despite the need for better working conditions in many fields, ranging from industry to healthcare, the potential of robots to facilitate human activities through physical contact is still unexploited.
The development of pHR-SA approaches poses several unresolved challenges, including the ability of robots to accurately detect and interpret human kinodynamics, musculoskeletal physiology, and psychosocial behaviour, to adapt to dynamic and unstructured environments and changing task requirements, and to interact with humans in an intuitive and seamless manner. To address these challenges, researchers are investigating a wide range of techniques and approaches such as human model-informed interaction planning, physiology- and cognitive-aware robot intelligence, multi-modal sensor fusion, and Interactive Machine Learning (IML). By empowering robots with these tools, their ability to understand and respond to human behavior will be enhanced, thus affording them the versatility to perform shared tasks with humans in direct or indirect physical contact. In addition, the advancement of intelligent physically interactive robots requires them to learn and adapt to the unique characteristics, preferences, and requirements of individual human users. This calls for implementing personalized models, adaptive control algorithms, human-centered strategies, and online learning and optimization techniques to enable robots to provide user-specific assistance.
While wearable robots (e.g., exoskeleton, supernumerary limbs, or prosthesis) are physically supporting humans, robotic partners endowed with pHR-SA will co-work with them (e.g., co-carry, co-manipulate, co-assemble, co-walk) sharing the task efforts and duties through variable levels of autonomy considering the human state, ability, intentions, and actions. The term ``robotic partners'' are stand-alone robotic platforms that can both carry out tasks autonomously and in collaboration with a human operator.
This workshop will address the latest research on pHR-SA whose main goal is to embrace and exploit human-robot physical contact to provide real-world solutions that go beyond sole spatial planning and motion generation and maximize the potential of robots as personal assistants and collaborators in human society.
In particular, the workshop will specifically focus on the challenges and opportunities on this topic, attempting to answer the following questions:
1. How to estimate the human state, ability, intentions, and actions aiming to perform pHR-SA?
2. How robot physical contact can be exploited to provide humans with assistance and/or support?
3. How to adapt the robot autonomy level during physical contact with humans?
To advance research on those questions, the workshop aims to bring together researchers who introduced and investigated different strategies for pHR-SA. By providing a platform for top researchers to share their work, we aim to generate a fruitful discussion and inspire new perspectives toward the extension and application of robotic assistive and collaborative devices.
Program
The workshop will take place on Monday 13th of May, 2024. Japan Standard Time (JST).
| Time | Description |
|---|---|
| 09.00 – 09.30 | Welcome and Introduction by the organizers |
| 09.30 – 10.00 | Learning assistance from physical human-robot interaction by Marcia O'Malley |
| 10.00 – 10.30 | Collaborative Control and Learning in Human-Robot Interaction by Sami Haddadin |
| 10.30 – 11.00 | Steps Toward an Empathic Collaboration Between Humans and Robots by Jesus M. Gómez de Gabriel and Cristina Urdiales |
| 11.00 – 11.30 | Coffee Break and Poster/Demo Session |
| 11.30 – 12.00 | Human Intention Reading Assistive Robots by Dongheui Lee |
| 12.00 – 12.30 | Passivity-based Control Strategies for Safe and Transparent pHR-SA by Jee-Hwan Ryu |
| 13.00 – 14.00 | Lunch Break |
| 14.00 – 14.30 | Extended Abstracts Presentation |
| 14.30 – 15.00 | A Shared Autonomy Approach to Personalisable Human-Robot Interaction by Arash Ajoudani |
| 15.00 – 15.30 | Coffee Break |
| 15.30 – 16.00 | Machine Learning for Collaborative Robotics: Co-Adaptation at the Intersection of Language, Vision and Control by Heni Ben Amor |
| 16.00 – 16.30 | Learning assistance from physical human-robot interaction devices by Dylan Losey |
| 16.30 – 17.00 | Panel Discussion |
Invited Speakers
Dr. Arash Ajoudani
Human-Robot Interfaces and Interaction Laboratory, Istituto Italiano di Tecnologia, Italy.
Email: arash.ajoudani@iit.it
A Shared Autonomy Approach to Personalisable Human-Robot Interaction
Prof. Heni Ben Amor
Interactive Robotics Laboratory, School of Computing and Augmented Intelligence, Arizona State University, USA.
Email: hbenamor@asu.edu
Machine Learning for Collaborative Robotics: Co-Adaptation at the Intersection of Language, Vision and Control
Prof. Jesus M. Gómez de Gabriel
and Prof. Cristina Urdiales
Robotics and Mechatronics Group, Systems Engineering and Automation Department and Department of Electronic Technology, University of Malaga, Spain.
Email: jmgomez@uma.es, acurdiales@uma.es
Steps Toward an Empathic Collaboration Between Humans and Robots
Prof. Sami Haddadin
Munich Institute of Robotics and Machine Intelligence, Technical University of Munich, Germany.
Email: haddadin@tum.de
Collaborative Control and Learning in Human-Robot Interaction
Prof. Dongheui Lee
Institute of Computer Engineering, Faculty of Electrical Engineering and Information Technology, Technical University of Wien, Austria.
Email: dongheui.lee@tuwien.ac.at
Human Intention Reading Assistive Robots
Prof. Dylan Losey
Collaborative Robotics Laboratory, Mechanical Engineering Department, Virginia Tech, USA.
Email: losey@vt.edu
Learning assistance from physical human-robot interaction
Prof. Marcia O'Malley
Mechatronics and Haptic Interfaces Laboratory, Mechanical Engineering Department, Rice University, USA.
Email: omalleym@rice.edu
Towards robots that teach and learn through physical human-robot interaction
Prof. Jee-Hwan Ryu
Interactive Robotic Systems Laboratory, Department of Civil and Environmental Engineering, Korea Advanced Institute of Science and Technology, Republic of Korea.
Email: jhryu@kaist.ac.kr
Passivity-based Control Strategies for Safe and Transparent pHR-SA
Organizers
Dr. Marta Lorenzini
is a Postdoctoral Researcher at the Human-Robot Interfaces and Interaction lab at Istituto Italiano di Tecnologia (IIT). She received her B.S., M.S., and Ph.D. in the Department of Electronics, Information, and Bioengineering from Politecnico di Milano, Milano, Italy in 2014, 2016, and 2020, respectively. She is currently involved in the Horizon-2020 project SOPHIA and ERC project Ergo-Lean and is also active in a technology transfer initiative with several industrial partners, the JOiiNT lab at Kilometro Rosso Innovation District. She was the winner of the Solution Award 2019 (Premio Innovazione Robotica at MECSPE2019), the KUKA Innovation Award 2018, and the IEEE Italy Section 2021 Ph.D. Thesis Award by ABB - New Challenges for Energy and Industry. She is currently the chair of the IEEE RAS Young Reviewers Program. Her research interests include human ergonomics estimation and assessment, assistive robotics, physical human-robot interaction, and feedback interfaces.
Email: marta.lorenzini@iit.it
Dr. Juan M. Gandarias
is an Assistant Professor in the Robotics and Mechatronics Group, Systems Engineering and Automation Department, University of Malaga, Spain. He received his B.S., M.S., and Ph.D. in Mechatronics from the University of Malaga in 2015, 2017, and 2020, respectively. He was a post-doctoral researcher at the Human-Robot Interfaces and Interaction Lab, Istituto Italiano di Tecnologia (IIT), Italy from 2020 to 2023. He was involved in the Horizon-2020 project SOPHIA and the ERC project Ergo-Lean. He has contributed to several Spanish and European projects related to search-and-rescue, physical robotic assistance, and human-robot collaboration in Industrial environments. He has served as a reviewer for high-impact journals and conferences such as IEEE RAM, RA-L, ICRA, IROS, ToH, etc. His research interests include HRC, human modeling, and haptic perception.
Email: jmgandarias@uma.es
Prof. Mahdi Tavakoli
is a Professor in the Department of Electrical and Computer Engineering, the University of Alberta, Canada. He received his BSc and MSc degrees in Electrical Engineering from Ferdowsi University and K.N. Toosi University, Iran, in 1996 and 1999, respectively. He received his PhD degree in Electrical and Computer Engineering from the University of Western Ontario, Canada, in 2005. In 2006, he was a post-doctoral researcher at Canadian Surgical Technologies and Advanced Robotics (CSTAR), Canada. In 2007-2008, he was an NSERC Post-Doctoral Fellow at Harvard University, USA. Dr. Tavakoli’s research interests broadly involve the areas of robotics and systems control. Specifically, his research focuses on haptics and teleoperation control, medical robotics, and image-guided surgery. Dr. Tavakoli is the lead author of Haptics for Teleoperated Surgical Robotic Systems (World Scientific, 2008). He is a Senior Member of IEEE and an Associate Editor for IEEE Robotics and Automation Letters, Journal of Medical Robotics Research, IET Control Theory & Applications, and Mechatronics.
Email: mahdi.tavakoli@ualberta.ca
Prof. Wansoo Kim
is an assistant professor with the Robotics Department, Hanyang University ERICA, Republic of Korea. He received his B.S. degree in mechanical engineering from Hanyang University ERICA campus, Korea in 2008 and his Ph.D. degree in mechanical engineering from Hanyang University, Korea in 2015 (Integrated MS/Ph.D. program). He was a post-doctoral researcher at the Human-Robot Interfaces and Interaction Lab, Istituto Italiano di Tecnologia (IIT), Italy from 2016 to 2021. He has developed several exoskeleton systems and collaborative robots (Cobot) and conducted research on the control of the powered exoskeleton robot and ergonomics collaboration control with Cobot through the physical human-robot interaction (pHRI) knowledge. He was involved in a Horizon-2020 project SOPHIA (No. 871237) and a European Research Council project Ergo-lean (No. 850932). He has contributed to several projects in the field of exoskeleton robots in Korean projects (Development of Wearable Robot for Industrial Labor Support, etc.) He was the winner of the Solution Award 2019, the winner of KUKA Innovation Award 2018, the HYU Best Ph.D. paper award 2015, and the ICCAS best presentation award 2014. His research interests are in Physical human-robot interaction (pHRI), human-robot collaboration, Shared Control, Ergonomics, Human modeling, Feedback devices, and powered exoskeleton robot.
Email: wansookim@hanyang.ac.kr
Sponsorship
This workshop will be supported by the European Union’s Horizon 2020 research and innovation program under grant agreement No. 871237 (SOPHIA), the European Union's NextGenerationEU framework of the project "Robotics and AI for Socio-economic Empowerment" (RAISE), the National Research Foundation of Korea (NRF) grant funded by the Korea government (Ministry of Science and ICT) No. 2022R1C1C1008306, the BRIC LABORIUS Project, and the Spanish Project PID2021-127221OB-I00.
