|Member Login

Event

22nd May 2018

ICRA2018 Forum: Social Robotics

Overview


ICRA2018 Forum: Social Robotics


Social robotics is an emerging field. As new generations of robots are developed that participate in our lives and exist in public spaces, we need to consider the impact of these technologies and how we can harness their benefits. Social robots must collaborate with people and prove themselves as capable partners. They must make good teammates, learn from us or teach us, as well as communicate with and understand us. The goal of this workshop is to explore where social robotics is heading and how we can best navigate the multi-disciplinary challenges such robots will present.

There will be three Forum sessions on Tuesday 22nd May 2018 at ICRA 2018 (21-25 May 2018) each 1h 15mins long. Each session will comprise presentations by three to four speakers, followed by a 15-minute interactive panel discussion with questions and comments from the audience.

Program


22nd May 2018

Time

Venue

Description

10am

P6 Brisbane Convention & Exhibition Centre

10am

SESSION 1: Applications of Social Robots

Chair: Sue Keay, Australian Centre for Robotic Vision

10:00am-10:15am

Speaker: Maya Cakmak, University of Washington

Programming Robots through Interaction

10:15am-10:30am

Speaker: Janet Wiles, The University of Queensland

10:30am-11:00am

MORNING TEA

MORNING TEA

11:00am-11:15am

Speaker: Angelica Lim, Simon Fraser University

Multimodal Perception for Social Robots

11:15am-11:30am

Speaker: Nicole Robinson, QUT

Social Robots to Deliver Behaviour Change Programs

11:30am-12:00pm

PANEL DISCUSSION

Social Robots - is there a limit to their application?

12:00pm

SESSION 2: Social Robots at Home and Work

Chair: Elizabeth Croft, Monash University, Melbourne

12:00pm-12:15pm

Speaker: Elizabeth Croft, Monash University

Social Work: Collaborative behaviours that measurably improve human-robot interaction

12:15pm-12:30pm

Speaker: Rachid Alami, CNRS

A Joint Action approach to assistant and teammate robots

12:30pm-12:45pm

Speaker: Dana Kulic, Waterloo University

Untrained Users Supervising Autonomous Systems

12:45pm-2:00pm

LUNCH

LUNCH

2:00pm-2:30pm

PANEL DISCUSSION

Social Robots at work and home

2:30pm

SESSION 3: Social Robots and Social Intelligence

Chair: Mary-Anne Williams, The Magic Lab, UTS, Sydney

2:30pm-2:45pm

Speaker: Amit Pandey, Chief Scientist Softbank Robotics

The Social Robotics Revolution: Where we are and how far to go?

2:45pm-3:00pm

Speaker: Harry Surden, Stanford University

Social Robotics and Law

3:00pm-3:30pm

AFTERNOON TEA

AFTERNOON TEA

3:30pm-3:45pm

Speakers: Xun Wang, CommBank and Mary-Anne Williams, MagicLab, UTS

Social Robots disrupting Human-Centric Business Environments

3:45pm-4:15pm

PANEL DISCUSSION

Social robots and social intelligence

Speakers


Nicole Robinson

Nicole Robinson

Social Robots to Deliver Behaviour Change Programs

Abstract: This talk will discuss work related to designing and implementing a social robot as a psychotherapist to talk to people about health behaviour change. This includes the process of creating a new psychotherapeutic intervention that could be delivered by a social robot, and testing the intervention on an adult and adolescent sample, including discussing the advantages and challenges of running social robot research in a healthcare context.

Bio: Nicole Robinson is a Research Fellow at Queensland University of Technology. Her research interests involves understanding and replicating complex behaviours into agents and robotic systems using human-like decision making, reasoning and approaches to goals and tasks. She has previously conducted research in the healthcare field, including the translation of a psychotherapeutic program to be delivered by a social robot.

Dr Rachid Alami

Dr Rachid Alami

A Joint Action approach to assistant and teammate robots

Abstract: This talk addresses some key decisional issues that are necessary for a cognitive robot which shares space and tasks with a human.  We adopt a constructive approach based on the identification and the effective implementation of individual and collaborative skills inspired from the Joint Action Concepts. The system is comprehensive since it aims at dealing with a complete set of abilities articulated so that the robot controller is effectively able to conduct in a flexible manner a human-robot collaborative problem solving and task achievement. These abilities include geometric reasoning and situation assessment based essentially on perspective-taking and affordances, management and exploitation of each agent (human and robot) knowledge in a separate cognitive model, human-aware task planning and interleaved execution of shared plans.

Bio: Dr. Rachid Alami is Senior Scientist at CNRS. He received an engineer diploma in computer science in 1978 from ENSEEIHT, a Ph.D in Robotics in 1983 from Institut National Polytechnique and an Habilitation HDR in 1996 from Paul Sabatier University. He contributed and took important responsibilities in several national, European and international research and/or collaborative projects (EUREKA: FAMOS, AMR and I-ARES projects, ESPRIT: MARTHA, PROMotion, ECLA, IST: COMETS, IST FP6 projects COGNIRON, URUS, PHRIENDS, FP7 projects CHRIS, SAPHARI, ARCAS, SPENCER, H2020 Projects MUMMER  France: ARA, VAP-RISP for planetary rovers, PROMIP, ANR projects).

His main research contributions fall in the fields of Robot Decisional and Control Architectures, Task and motion planning, multi-robot cooperation, and human-robot interaction. Rachid Alami is currently the head of the Robotics and Interactions group at LAAS.

Dana Kulic

Dana Kulic

Untrained Users Supervising Autonomous Systems

Abstract: In many industrial settings, current robots are capable of autonomous operation in controlled environments.  However, supervising and configuring such systems is still the job of human workers, who typically require high expertise in robotics to successfully configure such systems.  How can untrained users effectively direct autonomous systems?  In this talk, I will describe an approach for interactive task specification, that allows untrained users to configure autonomous mobile robots in warehousing environments, iteratively improving the specification and learning about user preferences.  I will describe metrics for assessing specification performance and results of initial user studies.

Bio: Dana Kulić received the combined B.A.Sc. and M.Eng. degrees in electromechanical engineering, and the Ph.D. degree in mechanical engineering from the University of British Columbia, Canada, in 1998 and 2005, respectively. From 2006 to 2009, she was a JSPS Postdoctoral Fellow and a Project Assistant Professor at the Nakamura Laboratory at the University of Tokyo. She is currently an Associate Professor at the Electrical and Computer Engineering Department at the University of Waterloo, Canada. In 2014, she was awarded Ontario’s Early Researcher award for her work on rehabilitation and human-robot interaction. Her research interests include human motion analysis, robot learning, humanoid robots, and human-machine interaction.

Angelica Lim

Angelica Lim

Multimodal Perception for Social Robots

Abstract: Humanoid robots are now being deployed “into the wild” in homes, shops and health facilities. Perceiving and understanding human social behaviours used between humans and humanoids, such as gestures, intentions and emotions is a challenging task. In this talk, I will describe some ways we have used multimodal sensor fusion techniques and cross-modal analysis (eg. RGB, RGB-D, sound) to perceive these behaviours, towards natural and intuitive human-robot interaction.

Bio: Angelica Lim is an Assistant Professor of Professional Practice in Computing Science at Simon Fraser University (SFU) in Canada, who has worked on social robots for over 10 years in France, Japan and Canada. She leads the SFU Rosie Lab, focusing on building robots with social intelligence and empathy, particularly using affective and developmental robotics paradigms. Previously, she spent 4 years as a Software Engineering Manager at SoftBank Robotics, where she led the emotion and expressivity team for Pepper the humanoid robot. 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. She received her B.Sc. in Computing Science from SFU and a Ph.D. and Masters from Kyoto University, Japan.

Amit Pandey, Chief Scientist, SoftBank Robotics Europe

Amit Pandey, Chief Scientist, SoftBank Robotics Europe

The Social Robotics Revolution: Where we are and how far to go?

Bio: Dr. Amit Kumar Pandey is Head Principal Scientist (Chief Scientist) at SoftBank Robotics Europe (formerly Aldebaran Robotics), Paris, France, also serving as the scientific coordinator (R&D) of its various collaborative projects. Earlier for 6 years he worked as researcher in Robotics and AI at LAAS-CNRS (French National Center for Scientific Research), Toulouse, France. His Ph.D. thesis in Robotics (title: Towards Socially Intelligent Robots in Human Centered Environment), is the second prize winner (tie) of the prestigious Georges Giralt Award for the best Ph.D. Thesis in Robotics in Europe, awarded by euRobotics (the European Union Robotics Community). His current research interest includes Socially Intelligent Robots, Human Robot Interaction (HRI), Robot’s Cognitive Architecture, Lifelong Learning and Robots in Education. On these aspects, he has been actively contributing as principal investigator, researcher, and industrial scientific coordinator in various national and European Union (EU) projects, as well as involved in their design and proposal.

Abstract: 
Never before in the history of robotics, robots have been so close to us, in our society. We are ‘evolving’, so as our society, lifestyle and the needs. AI has been with us for decades, and now embodied in robots, penetrating more in our day-to-day life. All these are converging towards creating a smarter eco-system of living, where social robots will coexist with us in harmony, for a smarter, healthier, safer and happier life. Such robots are supposed to be socially intelligent and behave in socially expected and accepted manners. The talk will reinforce that social robots have a range of potential societal applications and hence impacting the education needs and job opportunities as well. The talk will begin with illustrating some of the social robots and highlight what does it mean to develop a socially intelligent robot, and the associated R&D challenges. This will be followed by some use cases and the market analysis. The talk will conclude with some open challenges ahead, including social and ethical issues and emphasize on the greater need of a bigger and multi-disciplinary effort and eco-system of different stakeholders including policy makers.

Xun Wang, Lead Robotics Research Engineer, Commonwealth Bank Australia

Xun Wang, Lead Robotics Research Engineer, Commonwealth Bank Australia

Social Robots disrupting Human-Centric Business Environments

Bio: Xun Wang is the lead robotics research engineer at Innovation Lab, Commonwealth Bank of Australia. Previously, he was a Chancellor Postdoctoral Research Fellow at University of Technology Sydney (UTS) working on Human Robot Interaction and robotics software development for PR2/ROS platform. Xun received his Ph.D for a study in risk modelling and management in intelligent agents 2013. He was a core member of UTS Unleashed! robot soccer team from 2008 to 2013. Prior to his Ph.D study, Xun has worked as a software engineer in various industries for a decade.

Abstract:

The Magic Lab social robotics team at UTS and the Commonwealth Bank established a corporate-academic partnership in 2015 aimed at helping Australian industry understand and leverage the disruptive nature of social robot technology in human-centric business environments. Together UTS and CBA have been designing and executing human-robot interaction experiments to create customer experiences that excite and delight in a number of industries including retail, healthcare, transportation, and education. In this talk we will describe our new insights as well as the risks and challenges ahead for deploying social robots in real word applications in Australia.

Sue Keay

Sue Keay

Australian Centre for Robotic Vision

Forum Chair & speaker

An experienced R&D leader with a focus on disruptive technologies, Dr Sue Keay runs the world’s first robotic vision research centre. Her background in commercialisation helps successfully bridge the gap between ideas and implementation. Sue recently developed a successful $1.5m R&D project supported by the Queensland government to explore the vision capabilities of Softbank’s social robot, Pepper. Sue has a PhD in Earth Sciences from the Australian National University and was an ARC post-doctoral fellow at The University of Queensland, before escaping the lab and moving into research management and commercialisation where she has demonstrated national leadership. With interests in entrepreneurship and disruptive technologies, she is a graduate of the Australian Institute of Company Directors and serves on the Board of the CRC for Optimising Resource Extraction and the Advisory Board of Brisbane.AI. She is currently completing her MBA with UQ Business School.

In 2017, Sue was named as one of the first Superstars of STEM by Science & Technology Australia, announced by the Minister for Industry, Innovation and Science, Senator the Hon Arthur Sinodinos AO. As part of the program, Sue hopes to inspire others to consider a career in STEM.

Elizabeth Croft

Elizabeth Croft

Social Work: Collaborative behaviours that measurably improve human-robot interaction

Forum co-chair & speaker

Abstract
Over the last decade, there has a been a significant research investment in humanoid and human-friendly robotics platforms. New safety standards have been developed, particularly ISO 10218:2011 aimed at human-robot collaboration. Interaction studies related to these developments have gained prominence. In the recent paper on the ten Science Robotics Grand Challenges the need for “Social interaction that understands human social dynamics and moral norms and that can be truly integrated with our social life showing empathy and natural social behaviors” was listed. A key enabler for this challenge is the development of human-robot collaboration modalities that permit shared understanding of tasks, intentions, and responsibilities necessary for working and living together. This talk will discuss HRI techniques for prototyping and evaluating collaborative interactions, and examples of multi-modal methods, including visual and haptic channels, for supporting shared understanding in everyday interactions.

Bio: Professor Elizabeth A. Croft (B.A.Sc UBC ’88, M.A.Sc Waterloo ’92, Ph.D. Toronto ’95) is the Dean of Engineering at Monash University since January 1, 2018.  From 2013-2017 she was Associate Dean for the Faculty of Applied Science at the University of British Columbia (UBC).  As a professor of Mechanical Engineering at UBC she was Director of the Collaborative Advanced Robotics and Intelligent Systems (CARIS) Laboratory. She leads research on human-robot interaction, to develop robot behaviours, motions and control strategies to promote safe, effective and helpful human-robot collaborations with applications ranging from manufacturing to healthcare and assistive technology. She held the NSERC Chair for Women in Science and Engineering (BC/Yukon) from 2010-2015 and the Marshall Bauder Professorship in Engineering Economics, Business and Management Training from 2015-2017. Her recognitions include a Peter Wall Early Career Scholar award, an NSERC Accelerator award, and WXN’s top 100 most powerful women in Canada. She is a Fellow of the Canadian Academy of Engineers, Engineers Canada, and the American Society of Mechanical Engineers.

Mary-Anne Williams

Mary-Anne Williams

University of Technology Sydney

Forum co-chair & speaker

Mary-Anne Williams is Director of the Innovation and Enterprise Research Laboratory (The Magic Lab) at UTS. Mary-Anne has a Masters of Laws and a PhD in Knowledge Representation and Reasoning with transdisciplinary strengths in AI, disruptive innovation, design thinking, data analytics, IP law and privacy law. Mary-Anne is a Faculty Fellow at Stanford University and a Guest Professor at the University of Science and Technology China where she gives intensive courses on disruptive innovation. Mary-Anne chaired the Australian Research Council’s Excellence in Research for Australia Committee that undertook a national evaluation of Mathematics, Information and Computing Sciences in 2012.

Mary-Anne has a passion for design led research and innovation.  She works with her research team in the Magic Lab to bring science fiction to reality; the research goal is to design autonomous technologies that can learn to delight and adapt in novel situations as they collaborate with people to achieve shared goals.

Maya Cakmak

Maya Cakmak

Programming Robots through Interaction

Abstract: Robots that can assist humans in everyday tasks have the potential to improve people’s quality of life and bring independence to persons with disabilities. A key challenge in realizing such robots is programming them to meet the unique and changing needs of users and to robustly function in their unique environments. Most research in robotics targets this challenge by attempting to develop universal or adaptive robotic capabilities. This approach has had limited success because it is extremely difficult to anticipate all possible scenarios and use-cases for general-purpose robots. Instead, my research aims to develop robots that can be programmed in-context and by end-users after they are deployed. To that end, my students and I have been developing new techniques and tools that allow intuitive and rapid programming of robots to do useful tasks leveraging natural human-robot interactions. In this talk I will introduce some of these techniques and tools, demonstrate their capabilities, and discuss some of the challenges in making them work in the hands of potential users and deploy them in the real world.

Bio: Maya Cakmak is an Assistant Professor at the University of Washington, Computer Science & Engineering Department, where she directs the Human-Centered Robotics lab. She received her PhD in Robotics from the Georgia Institute of Technology in 2012, after which she spent a year as a post-doctoral research fellow at Willow Garage, one of the most influential robotics companies. Her research interests are in human-robot interaction, end-user programming, and assistive robotics. Her work aims to develop robots that can be programmed and controlled by a diverse group of users with unique needs and preferences to do useful tasks. Maya’s work has been published at major Robotics and AI conferences and journals, demonstrated live in various venues and has been featured in numerous media outlets. Tools that she and her students developed are currently being used by robotics companies like Savioke and Fetch Robotics. She received an NSF CAREER award in 2016 and a Sloan Research Fellowship in 2018.

 

Harry Surden

Harry Surden

Social Robotics and Law

Abstract: Robots, including self-driving vehicles and drones, have increasingly started to operate in public spaces.   Previously, robots had largely been confined to specialized spaces, such as factories or laboratories, populated by trained individuals.   Today, they are beginning to share physical spaces with untrained lay-persons, including ordinary adults and children.
Given the impact on the broader population,  lawmakers and policymakers are beginning to become involved in shaping the rules and regulations surrounding such social-robotic interactions.   When should government become involved in regulating robotics in public spaces?   How should they become involved?   When should they show restraint in regulating?   This talk will highlight several key emerging themes of interest in the legal regulation of robots as they interact with the lay populace.

Janet Wiles

Janet Wiles

Professor of Complex and Intelligent Systems, University of Queensland

Bio: Janet Wiles holds a Ph.D. from the University of Sydney, and is Professor of Complex and Intelligent Systems at the University of Queensland. Her research group studies fundamental issues in how information is transmitted, received, processed and understood in biological and artificial systems. Her research interests include complex systems in biology and neuroscience, artificial and natural intelligence, language, and social robotics. www.itee.uq.edu.au/research/co-innovation

Abstract
To support natural communication, social robots need to act in real time, which for human conversation involves responses in as little as 200 milliseconds, and within the peripersonal space of interlocutors. This is a challenge for contemporary social robots, requiring safe and robust interaction. The talk will present ongoing work in the co-design of social robots: the Opie project, which is developing Indigenous Language Robots with a remote community, and the Florence project, designing technologies to support communication for people living with dementia in the community. The aim of these projects is to create solutions to everyday needs, and through this design practice, develop methodologies for working with (and not for) communities.

Contact


Sue Keay

Sue Keay

Australian Centre for Robotic Vision

E: sue.keay@qut.edu.au

+61 408 778 667

Australian Centre for Robotic Vision
2 George Street Brisbane, 4001
+61 7 3138 7549