keynotes

Satoshi Tadokoro

Graduate School of Information Sciences, Tohoku University

Title: Search in Rubble Piles - ImPACT Tough Robotics Challenge

Abstract

Large-scale disasters sometimes destroy artificial structures. Victims are buried in rubble piles and wait for search and rescue. Robotics is expected to support humanitarian activities where risks and difficulties are beyond human capacity. RoboCup has significantly activated this research area. This keynote speech presents some efforts to create advanced robotic systems for gathering information in debris. Active Scope Camera is a serpentine robot searching in debris that crawls and levitates in few-cm gaps, with visual, auditory, and haptic senses for navigation and victim search. Cyber Rescue Canine is a digitally empowered rescue dog wearing a suit to monitor its behavior and conditions and navigate its action remotely. We will discuss how robotics can help mitigate disaster damages in the future.

Bio

Satoshi Tadokoro graduated from the University of Tokyo in 1984. He was an associate professor at Kobe University from 1993 to 2005 and has been a Professor at Tohoku University since 2005. He was a Vice/Deputy Dean of the Graduate School of Information Sciences in 2012-2014 and has been the Director of Tough Cyberphysical AI Research Center since 2019 at Tohoku University. He has been the President of the International Rescue System Institute since 2002 and was the President of IEEE Robotics and Automation Society from 2016 to 2017. He served as the Program Manager of the Ministry of Education's DDT Project on rescue robotics in 2002-2007 and was the Project Manager of Japan Cabinet Office ImPACT Tough Robotics Challenge Project on disaster robotics in 2014-19, having 62 international PIs and 300 researchers that created Cyber Rescue Canine, Dragon Firefighter, etc. His research team at Tohoku University has developed various rescue robots, two of which are called Quince and Active Scope Camera are widely recognized for their contribution to disaster response, including missions in the nuclear reactor buildings of the Fukushima-Daiichi Nuclear Power Station. IEEE Fellow, RSJ Fellow, JSME Fellow, and SICE Fellow.

Angelica Lim

Rosie Lab, School of Computing Science at Simon Fraser University

Title: Social Signals in the Wild: Multimodal Machine Learning for Human-Robot Interaction

Abstract

Science fiction has long promised us interfaces and robots that interact with us as smoothly as humans do - Rosie the Robot from The Jetsons, C-3PO from Star Wars, and Samantha from Her. Today, interactive robots and voice user interfaces are moving us closer to effortless, human-like interactions in the real world. In this talk, I will discuss the opportunities and challenges in creating technologies that can analyze, detect and generate non-verbal communication, including gestures, gaze, auditory signals, and facial expressions. Specifically, I will discuss how we might allow robots to understand human social signals (including emotions, mental states, and attitudes) across cultures as well as in recognize and generate expressions with diversity in mind.

Bio

Dr. Angelica Lim is the Director of the Rosie Lab (www.rosielab.ca), and an Assistant Professor of Professional Practice in the School of Computing Science at Simon Fraser University, Canada. Previously, she led the Emotion and Expressivity teams for the Pepper humanoid robot at SoftBank Robotics. She received her B.Sc. in Computing Science (Artificial Intelligence Specialization) from SFU and a Ph.D. and Masters in Computer Science (Intelligence Science) from Kyoto University, Japan. She has been featured on the BBC, TEDx, hosted a TV documentary on robotics, and was recently featured in Forbes 20 Leading Women in AI.

Manukid Parnichkun

Driverless Car Technologies

Abstract

Driverless car was widely known for the first time from DARPA Grand Challenge in 2004 which was a competition of driverless cars in dessert area. The competition was evolved to DARPA Urban Challenge in 2007 which was a competition in urban area. Since then researches and developments of driverless cars have been conducted extensively for commercialization purposes for examples; driverless car by Google, electrical car with driver assisting functions by Tesla. Today most of car manufacturers research and develop driverless car actively. In Thailand, Thai Robotics Society started its activity on driverless car since 2005. Thailand Intelligent Vehicle Challenge was organized by the society during 2007-2009. The competition became more challenged with the platform of bicycle in BicyRobo Thailand Championship organized during 2010-2012.

This talk will present the key devices and control algorithms behind driverless car technologies. Technologies used by Google car and Tesla will be firstly presented and compared. In the latter part of the talk, the control algorithms used for speed control, heading control, waypoints tracking, and obstacles avoidance of driverless car, unmanned bicycle, and autonomous forklift developed at Asian Institute of Technology (AIT) will be presented.

Bio

Manukid Parnichkun is currently a professor at Mechatronics program, Asian Institute of Technology. He received B.Eng. from Mechanical Engineering, Chulalongkorn University in 1991, M.Eng. and Ph.D. from Precision Machinery Engineering, the University of Tokyo in 1993 and 1996 respectively. He joined Asian Institute of Technology as an assistant professor in 1996. He was promoted to Associate Professor in 2001, and professor in 2016. He supervised and graduated 23 doctoral students, and 194 master students. He was the founding committee of the Thai Robotics Society (TRS) and later became editor-in-chief of the society journal. He was elected to be the president of the Thai Robotics Society during 2003-2005. He organized and chaired several conferences and robot competitions. His research interests are Mechatronics, Robotics, Control, and Measurement.

Mary-Anne Williams

Michael J Crouch Chair in Innovation
School of Management and Governance
UNSW Business School
University of New South Wales

Emotional and Social Intelligence in Human-Robot Collaboration

Abstract

Social intelligence is critical for collaboration. A robot without empathy and social skills is challenging for humans to work with. Likewise, effective human-robot collaboration requires that humans empathise with robots and use social skills to achieve goals. Robots today can undertake an impressive range of complex tasks autonomously. However, all too often critical aspects of human cognition, human behaviours and the human experience are ignored in robot design and development. Robots deployed as helpers and co-workers have serious behavioural problems. They cannot empathise or show compassion, and their persuasive powers are severely limited. They treat people like obstacles to avoid or as random meaningless objects. This limits the value and benefits robots can generate in human workplaces and significantly diminishes the opportunities for future robot applications. In contrast, humans typically undertake considerable training to work with robots where they learn to empathise with a robot to understand its capabilities and weaknesses.

Imagine a robot that understood human's limited attention, human bias or the kinds of poor decisions we can make when we are stressed. Such a robot might adopt behaviours that did not create unnecessary distractions or exacerbate stressful situations. Robots in human environments will not be self-contained - they will need additional resources and help to complete their tasks. Humans are typically happy to help but not repeatedly unless the effort is reciprocated.

In this talk, I will discuss the importance of emotional and social intelligence for robots with examples. Emotional intelligence comes from awareness of self and others. Social intelligence is critical for cooperation and collaboration; power and influence; safety, privacy, security and trust. We know from the recent revolution in psychology and important work in human-robot interaction that robots can make situations more dangerous if they do not take into account the systematic errors in human information processing and judgement. Human-robot collaboration with emotional and social intelligence has the potential to create breakthrough insights that will allow us to reimagine how humans and robots can collaborate for the benefit of business and society.

Bio

Mary-Anne Williams is the Michael J Crouch Chair in Innovation at UNSW where she collaborates with business, government and societal organisations to grow entrepreneurship and accelerate innovation in Australia. Prior to her appointment to this role, Mary-Anne spent 18 years as founder and director of the Innovation and Enterprise Research Lab (The Magic Lab) in the Australian Artificial Intelligence Institute creating Australia's leading social robotics research group. Her work in robotics commenced when she began to apply her AI work to robots, and it was dramatically accelerated by Claude Sammut who helped her create her first robot soccer team in 2001. By 2012 Mary-Anne was working with Willow Garage and bought the first PR2 to Australia. From 2017 to 2019 she led her team to become Social Robotics World Champions at RoboCup 2019. Mary-Anne has broken new ground in her innovative collaborations with industry including leading Australia's largest Social Robotics project with the Commonwealth Bank of Australia.

Mary-Anne has a PhD in Computer Science (University of Sydney) and a Master of Laws (University of Edinburgh). She is a Fellow at Stanford University, the Australian Academy of Technological Sciences and Engineering, the Australian Computer Society and the Association for the Advancement of Artificial Intelligence (AAAI). Mary-Anne is a leading authority on AI with transdisciplinary strengths in Human-Robot Interaction, Social Robotics, Disruptive Innovation, Entrepreneurship, Ethics and Law. She has received multiple awards including the 2019 Australasian Distinguished Artificial Intelligence Contribution Award from the Australian Computer Society; two Google Faculty Machine Learning Awards in 2019 and 2021; and an IBM Faculty Award in 2008. She is a member of the Editorial Boards for AAAI/MIT Press; the Information Systems Journal; and the International Journal of Social Robotics. She was Chair of the International Conference on Social Robotics in 2014; Review Editor for Artificial Intelligence Journal; and served on the ACM Eugene L. Lawler Award Committee for Humanitarian Contributions within Computer Science and Informatics. Mary-Anne was Conference Chair for the 2021 Australasian Joint Conference on Artificial Intelligence and invited speaker for the Australian government at World Expo in Dubai in 2022.