ACRA 2021 Committee

Honorary Chair

• Elizabeth Croft, Monash University

General Chair

• Elahe Abdi, Monash University

Technical Program Chair

• Dana Kulic, Monash University

Technical Program Co-Chair

• Denny Oetomo, University of Melbourne
• Jonathan Roberts, Queensland University of Technology
• Will Brown, Queensland University of Technology
• Sarath Kodagoda, University of Technology Sydney

Program Chair

• TJ Chin, University of Adelaide

Program Co-Chair

• Leimin Tian, Monash University
• Pauline Pounds, University of Queensland

Publicity Chair & Webmaster

• Wesley Chan, Monash University

Publicity Co-Chair

• Dana Rezazadegan, Swinburne University of Technology

Industry Chair

• Saeid Nahavandi, Deakin University

Industry Co-Chairs

• Chao Chen, Monash University
• Tirthankar Bandyopadhyay, CSIRO

Finance Chair

• Teresa Vidal Calleja, University of Technology Sydney

Finance Co-Chair

• Hoam Chung, Monash University

Local Arrangements Chair

• Michael Burke, Monash University

Local Arrangements Co-Chair

• Pamela Carreno-Medrano, Monash University

John Michael McCarthy – Distinguished Professor, University of California, Irvine, US

Plenary topic: Design and Construction of Mechanical Walking Robots

Abstract:

The leg mechanism of a mechanical walking robot as well as the wing mechanism of a mechanical flying robot can be viewed as a linkage that draws a desired foot trajectory or wing-tip trajectory.   Engineers and mathematicians have studied curve-drawing linkages for practical as well as theoretical purposes ever since James Watt used a straight-line linkage to construct an effective double-acting steam engine.  Recent mathematical results prove that such a linkage exists for every algebraic curve, and this talk presents an overview of techniques to design these linkages.

One interesting result is that the equations for kinematic synthesis rapidly expand beyond the ability of current computers to solve completely.  However, in this talk we show that strategies exist for the design and construction of interesting and useful leg mechanisms that yield practical mechanical walking robots.

Bio:

J. Michael McCarthy is a Distinguished Professor in Mechanical and Aerospace Engineering in the Henry Samueli School of Engineering at the University of California, Irvine. He is the past Director of the Center for Engineering Science in Design at the University of California, Irvine. He has been a Visiting Professor at Massachusetts Institute of Technology and at Stanford University teaching graduate courses in Kinematic Synthesis of Mechanisms.

For over 20 years he has focused on developing engineering leadership through student design and execution of major engineering projects. He introduced project engineering courses for graduate students, seniors and for freshman at UCI and provided course materials for racecar engineering courses in local high schools, including a Summer Program for Racecar Engineering.  He organized the UCI Energy Invitational racecar energy time trial and the UCI Rescue Robotics competition for local High School engineering teams.  He has received a number of research and teaching awards including the 2021 Henry Samueli School of Engineering Innovation in Teaching Award.

Wafa Johal – Lecturer, University of New South Wales, Australia

Keynote topic: Robots for learning but not robotics

Abstract: 

As of late, there have been an increasing number of robotics-based tools used in the classroom to teach robotics and programming to school children. From DYI kits, to plug-and-play solutions, teachers and educators seem to have a plethora of choices to introduce these topics to K-12 students. The use of robots in classrooms however, is still confined to extracurricular/optional activities often run by technophile teachers. Robots present the advantage of being embodied intelligent agents, who can enhance learning through various ways by bridging physical and digital student experiences.

In this talk, I will present our work in aiming to democratize the use of robots in the classroom by designing and implementing a versatile and classroom friendly robot. I will introduce the Robots for Learning initiative and present our latest work with the Cellulo robots, a swarm of tangible robots that have already been used by +400 students.

Bio:

Dr Wafa Johal is a Senior Lecturer in Computer Sciences at the Faculty of Engineering and Information Technology at the University of Melbourne. Previously, she was Lecturer at the University of New South Wales, Sydney. From 2015 to 2019, she was a researcher at the Computer Human Interaction Lab for Learning and Instruction and the Mobots Group at EPFL, Switzerland.

Her research aims at creating acceptable and useful assistive robot interactions using social signal sensing, affective and cognitive reasoning and natural expressivity. Her latest work has investigated the use of tangible robots in education and rehabilitation, as well as the use of social robots for learning. She is an Associate Editor of RA-L (IROS and ICRA) for the Human-Robot Interaction track and the recipient of a Discovery Early Career Researcher Award (DECRA 2021) funded by the Australian Research Council.

Mary-Anne Williams – Professor, University of New South Wales, Australia

Plenary topic: Emotional and Social Intelligence for Robots working with Humans

Abstract

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. They treat people like obstacles to avoid or as random objects. This limits the value and benefits robots can generate in human workplaces and significantly diminishes the opportunities for future robot applications.

Imagine a robot that could help humans remain calm in dangerous high-risk situations or a robot able to exploit social concepts like reciprocity to get the help and resources it needs from a human to complete a task.

In this talk, I will discuss the importance of emotional and social intelligence for robots. Emotional intelligence comes from awareness of self and others. Social intelligence is critical for cooperation and collaboration; power and influence; privacy 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 interaction 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:

Prof Mary-Anne Williams is the Michael J Crouch Chair for Innovation at UNSW where she collaborate to grow entrepreneurship and accelerate innovative thinking in Australia. Prior to taking up this exciting role Prof. Williams spent 18 years as founder and director of the Innovation and Enterprise Research Lab (The Magic Lab), Australian Artificial Intelligence Institute at UTS. The Magic Lab was a pioneer with unique transdisciplinary capabilities in key areas of innovation and enterprise. It specialised in technology-enabled innovation and build solutions using AI, Design Thinking, Experimentation, and Analytics. Her industry and government partners included South Western Sydney Local Health District, IBM, Google, Disrupt, Linkedin, bigtincan, Willow Garage (now Savioke), Amazon, Visual Risk, CBA, Denmark’s National Bank, Samsung, Sony, and Softbank.

Minas Liarokapis – Senior Lecturer, University of Auckland, New Zealand

Keynote topic: Making Humans and Robots More Dexterous

Abstract: 

This talk will focus on robotic and bionic technologies that have been developed by the New Dexterity (www.newdexterity.org) research group at the University of Auckland and on how they can make humans and robots more dexterous. The talk will include our recent progress on the design, modelling, and development of:

i) dexterous and versatile robotic grippers, hands, and manipulators, ii) exoskeleton and prosthetic systems, iii) teleoperation, telemanipulation, and human-to-robot skill transfer schemes, iv) all-terrain vehicles that facilitate interaction with the environment and navigation of uneven terrains, v) humanoid robots that can be used for the execution of complex everyday life tasks.

A variety of examples and experimental results will be provided, focusing on the application of these technologies in various environments (household, industrial automation, search and rescue, house construction, infrastructure inspection etc.). The talk will also provide an in-depth discussion of the underlying problems and challenges.

Bio:

Dr. Minas Liarokapis is a Senior Lecturer in the Department of Mechanical and Mechatronics Engineering at the University of Auckland and Director of the New Dexterity research group. Previously, he was a Postdoctoral Associate in the GRAB Lab at Yale University. He is a Senior Member of IEEE and serves as an Associate Editor for many IEEE robotics conferences and journals. He is the founder of the Robotics NZ and the OpenBionics initiative and a co-founder of HandCorpus and OpenRobotHardware.

Dr. Liarokapis is interested in providing robotics solutions to everyday life problems, modelling, designing, developing, and controlling novel robotics and bionics devices. His research has been funded by several industry partners in Germany, USA, and Japan, as well as by the University of Auckland Faculty Research Development Fund, the Center for Automation and Robotics Engineering Science, and the IEEE Robotics and Automation Special Interest Group on Humanitarian Technology (RAS-SIGHT).

Simon Lucey – Professor, University of Adelaide, Australia

Plenary topic: Learning in 3D using ONLY 2D labels

Abstract: 

Machine vision has made tremendous progress over the last decade with respect to perception. Much of this progress can be attributed to two factors: the ability of deep neural networks (DNNs) to reliably learn a direct relationship between images and labels; and access to a plentiful number of images with corresponding labels. But how to obtain 3D labels is an open problem for the robotics and vision community. In this talk, I will discuss recent efforts my group has been taking to train a geometric reasoning system using solely 2D supervision. By inferring the 3D shape solely from 2D labels we can ensure that all geometric variation in the training images is learned. This innovation sets the ground work for training the next generation of reliable geometric reasoning AIs needed to solve emerging needs in: autonomous transport, disaster relief, and endangered species preservation.

Bio:

Simon Lucey (Ph.D.) is a professor at the University of Adelaide, where he is the Director of the Australian Institute of Machine Learning (AIML). Prior to this he was an associate professor at Carnegie Mellon University's Robotics Institute (RI) in Pittsburgh USA. From 2017- 2020, he was a principal scientist at the autonomous vehicle company Argo AI and spent time at the CSIRO (2009-2014). He has received various career awards including an ARC Future

Fellowship (2009-2013). Simon’s research interests span computer vision, machine learning, and robotics. He enjoys drawing inspiration from AI researchers of the past to attempt to unlock computational and mathematic models that underlie the processes of visual perception.

Call for Papers

Dear robotics community,

We would like to cordially invite members of industry and academia to participate and/or submit a paper to the 2021 Australasian Conference on Robotics and Automation (ACRA). This year ACRA is being jointly organised by the Australian Robotics and Automation Association (ARAA) and Monash University Robotics. The conference will take place in Melbourne, with the event hosted at Monash Clayton campus. The conference will happen between 6-8 December 2021.

ACRA is the premier Australasian conference on robotics and automation. With Melbourne as a major hub for robotics, ACRA 2021 will continue to bring together researchers, engineers, academics, students, practitioners, organisations and industries to discuss the current state of the art of research and advancement of technology in areas of Robotics and Automation, including (but not limited to):

• Mechatronics systems and design
• Vision for robotics
• Field robotics
• Aerial robotics
• Underwater and marine robotics
• SLAM
• Agricultural robotics
• Industrial robots and automation
• Service robotics
• Control systems
• Motion and path planning
• Healthcare robots
• Soft robotics
• Smart materials
• Machine learning for robotics
• Human-machine interaction
• Robotics perception

Submissions must be original, unpublished work containing new and interesting results that demonstrate current research in areas relevant to Robotics and Automation. All full papers submitted to ACRA 2021 will undergo a peer-review process. Each manuscript will be reviewed by at least two reviewers who will give detailed comments. If the submission is accepted, the authors will be required to submit a revised (“camera-ready”) version that takes into account this feedback. All papers are reviewed using a single-blind review process.

Important Dates:

• Submission of full papers by: 20th September 2021 Extended deadline: 27th September 2021
• Notification of acceptance by: 1st November 2021
• Camera ready submission by: 15th November 2021
• Conference running: 6th – 8th December 2021

Paper Format:

ACRA papers must be 6-10 pages in length (including text, references, figures and acknowledgements). Papers that do not follow these guidelines may be rejected without review.

Paper Templates:

Please use this link to download the following files:

L^aT_eX: style file: acra.sty, template: acra.tex, bibtex: named.bst
Microsoft Word | Star/OpenOffice: template: acra.rtf or acra.odt.

Submission portal:

To make your submission, please use this portal.

Best Regards,

Dr Elahe Abdi (General Chair) – elahe.abdi@monash.edu

Prof Dana Kulic (Technical Program Chair) – dana.kulic@monash.edu

Call for Late Breaking Results Posters

You are cordially invited to contribute Late Breaking Results posters to the 2021 Australasian Conference on Robotics and Automation (ACRA 2021). 

The Late-Breaking Reports provides authors with the opportunity to present early-stage results and new ideas of their most recent theoretical and experimental research.

Submission Format:

Prospective poster presenters should submit a one-page abstract by November 14 2021 through the submission portal. The abstract should include background and motivation, methods, results, and references. Accepted submissions will be presented at the conference as posters but will not be published in the conference proceedings.

Important Dates:

• Submission opens: 1st November 2021
• Deadline for submissions of Late Breaking Results (abstracts): 14th November 2021
• Notification of acceptance: 22th November 2021
• Deadline for final submissions of Late Breaking Results (posters): 30th November 2021

Paper Templates:

Please use this link to download the following files:

L^aT_eX: style file: acra.sty, template: acra.tex, bibtex: named.bst
Microsoft Word | Star/OpenOffice: template: acra.rtf or acra.odt.

Submission portal:

To make your submission, please use this portal.

Registration

The registration will have three categories this year:

• A ‘paper fee’ (200 AUD) – this is associated with a paper, not an individual. Click here to register and please include your ‘Submission Paper ID’ as a reference.
• No poster fee is associated with the posters, but the poster presenter still needs to register their attendance to the Poster Sessions. Click here to register and please include your ‘Submission Poster ID’ as a reference.
• Participant registration ($0 – FREE) – for all authors and the general community. Register via this link

For the full program please check this page (all times are in AEDT – Melbourne GMT+11).

Here is the program overview:

ISBN: 978-0-6455655-0-8 ISSN: 1448-2053

For paper proceedings:

• please click on ACRA2021Papers to download a packaged zip file with all the papers.
• please click here to download each paper individually.

Gold Sponsor

Silver Sponsor

In-Kind Sponsor