Workshop@HAI 2023

The Importance of Human Factors for Trusted Human-Robot Collaborations

December 04, 2023, Gothenburg, Sweden.


Workshop at the International Conference on Human-Agent Interaction (HAI 2023)

Location: Svea building, room 240. Chalmers, Lindholmen Campus.

Address: Forskningsgången 4, 41756 Göteborg

Date: December 04, 2023

Take a look at the AGENDA of this workshop

The next generation of robots is expected to work collaboratively with humans in natural (dynamic) settings. For this, it is important to properly study and model human factors, so that the AI and Robotic models can include them to enable robust Human-Robot Collaborations. This will enable safe and trustworthy hybrid decision-making approaches — Responsible AI — thereby streamlining robust collaborations (as per human-centred expectations). This interdisciplinary workshop will focus on the intersection of Cognitive Human Factors, Interpretable \& Explainable AI methods, Social Interaction, and Human-Centred Robotics to stimulate novel long-range avenues for innovative human-centred collaborative methods in real-world contexts.

Please follow this link to register for this workshop: https://hai-conference.net/hai2023/registration/

Workshop Organizers

  • Karinne Ramirez-Amaro, Associate Professor, Chalmers, SWE.
  • Ilaria Torre, Assistant Professor, Chalmers, SWE.
  • Maximilian Diehl, PhD student, Chalmers, SWE.
  • Emmanuel Dean, Associate Professor, Chalmers, SWE.

This workshop is funded by the project CHAIR X-AI, Network on Human-Centered Collaborative Autonomy

Goals of this workshop

This interdisciplinary workshop will focus on investigating the importance of studying cognitive human factors, particularly within the intersection between AI for Robotics and the Autonomous Systems domain to stimulate novel long-range avenues for innovative human-centred collaborative methods in real-world contexts. This workshop will encourage diverse research discussions and knowledge exchange to address the following topics:

  • Including the centrality of “humans” and their “needs” as prime significance in the technical design and implementation of the next generation of AI methods.
  • Identifying challenges and research gaps to obtain trusted Human-Robot Collaborations.
  • Exchanging insights on innovative cognitive human factors focusing on explainable AI methods to enable safe, trusted, and inclusive Human-Machine Interactions.

Within this workshop, we will bring together top established senior researchers as well as young and emerging talents to discuss and suggest new research ideas within the areas of Robotics, Machine Learning (ML), Explainable AI (XAI), Cognitive Vision, Social Interaction, and Human-Centred Design. Another important goal of this workshop is to expand the understanding of complex dynamics of multimodal interaction in collaborative teams which can potentially derive in novel interdisciplinary concepts.

Invited Speakers

Agenda

8:30 – 9:00Registration
Conference registration opens at 08:30.
Location: Svea building, room 204, Lindholmen.
9:00 – 9:10 Welcome by organizers
9:15 – 9:45Tetsunari Inamura, Professor
Brain Science Institute, Tamagawa University, JAPAN
Title: Building Trust in Assistive Robotics: Integrating VR and Digital Twins for Enhanced Self-Efficacy
10:00 – 10:30Coffee break + posters
10:30 – 11:00Niki Kousi, Managing Director
EIT Manufacturing
Title: Towards Seamless human-robot Collaboration: Integrating Multimodal Interaction
11:15 – 11:45Spotlight talks (7) — 3 min
List of Accepted Extended Abstracts
12:00-13:00Lunch break
13:15 – 13:45Volker Krueger, Professor
Lund University
Title: Robot Skills for Scalable Manufacturing Lines
14:00 – 15:00Poster session + Coffee break
15:00 – 15:30Mehul Bhatt, Professor
Örebro University
Title: What are the technical/engineering implications of achieving ethical-legal trustworthiness with autonomous vehicles?
15:45 – 16:45Panel discussion + general discussion
16:50 – 17:00Closing remarks by organizers

Talk’s information

Tetsunari Inamura,

Tamagawa University, Japan

Title: Building Trust in Assistive Robotics: Integrating VR and Digital Twins for Enhanced Self-Efficacy

Abstract: In the field of intelligent robotics, developing physical support devices and rehabilitation systems for nursing care is a rapidly growing application area. Traditional research in this domain predominantly focused on physical support quality and enhancement of motion performance. However, the next generation of assistive AI robots demands an integrated approach encompassing physical and cognitive support. Addressing this significant challenge, my research project emphasizes not just improving physical motion performance, but also enhancing users’ psychological belief in their own capabilities, centering on the concept of self-efficacy. This presentation explores how manipulating assistive robot control parameters and creating virtual experiences of success in Virtual Reality (VR) can substantially enhance users’ self-efficacy. The talk also discusses the integration of VR with digital twin technology, laying a technological foundation for efficient human-robot cooperation. This approach aims to build a trustful system where virtual experiences are leveraged to empower users, blending the boundaries between physical and virtual assistive interventions.

Biography: Tetsunari Inamura received his B.E., M.E., and Ph.D. degrees from the University of Tokyo, Japan, in 1995, 1997, and 2000, respectively, focusing on realizing a human-robot interaction system for personal robots. He was a Researcher of the CREST Program, Japanese Science and Technology Cooperation, from 2000 to 2003, and then joined the Department of Mechano-Informatics, School of Information Science and Technology, University of Tokyo, as a Lecturer at JSK lab., from 2003 to 2006. He was an Associate Professor with the Principles of Informatics Research Division, National Institute of Informatics, and an Associate Professor with the Department of Informatics, School of Multidisciplinary Sciences, The Graduate University for Advanced Studies, SOKENDAI, Japan, from 2006 to 2023. He is now a professor at the Advanced Intelligence & Robotics Research Center, Brain Science Institute, Tamagawa University, Japan. His research interests are multifaceted, learning from human demonstration, symbol emergence in social robots, quality evaluation of human-robot interaction, human-robot interaction using virtual reality, and affective computing for assistive robots. He has recently been appointed as a co-chair of the IEEE RAS Technical Committee on Cognitive Robotics, underlining his commitment to advancing the field of cognitive robotics. Furthermore, he is well known for organizing the RoboCup@Home simulation competition, an initiative that promotes the development of cognitive human-robot interaction systems.


Niki Kousi,

EIT Manufacturing CLC South East, Greece

Title: Towards Seamless human-robot Collaboration: Integrating Multimodal Interaction

Abstract: Product customization and even personalization is the global trend driving the development of modern production systems. This in turn creates the need to deploy flexible and reconfigurable assembly systems. While robots have very well proven their flexibility and efficiency in mass production and are recognized as the production resource of the future, their adoption in lower volume, diverse environments is heavily constrained. To this extent new types of factories exploiting the capabilities of multiple resources such as human operators and mobile and/or stationary robot assistants are emerging.

This presentation will provide an overview of the current industrial challenges as well as the enabling technologies towards the adoption of seamless human robot collaborative scenarios in the manufacturing industry. The integration of Artificial Intelligence based tools with smart robotic control methods enhanced with safety measures will be explored. Finally, the role of EIT Manufacturing Knowledge and Innovation Community, funded and supported of the European Institute of Innovation and Technology, in boosting the industry adoption of new innovations and the upskilling of the factory workforce will be highlighted.

Biography: Dr. Niki KOUSI is serving as Managing Director of EIT Manufacturing Co-Location Center South East, located in Athens, Greece and supported by the European Institute of Innovation and Technology (EIT). Previously, Dr. Kousi served as Project Manager and Coordinator in numerous industry driven international projects focusing on development and implementation of manufacturing innovation / business strategies. This has been accomplished in cooperation with universities, industry and research institutes and in the context of European R&D&I projects. She has been leading teams of professional staff engaging a broad array of stakeholders in industrial innovation projects as well as private cooperation with industry. She holds a Mechanical and Aeronautics Engineer diploma and a Doctor of Philosophy focusing on cutting edge enabling technologies for flexible and hybrid manufacturing systems. She was Finalist of the Innovation Radar Prize (2019) organized by European Commission, under the category Woman Led Innovation.


Title: Towards Seamless human-robot collaboration: Integrating Multimodal Interaction

Volker Krueger,

Lund University, Sweden.

Title: Robot Skills for Scalable Manufacturing Lines

Abstract: For producing companies it is challenging to scale production resources according to customer demand. A solution could be production lines where manufacturing resources are dynamically added when needed. One classic solution for this can be to use mobile robotic manipulators. However, for this to work it must be possible to quickly program and deploy them, and ideally, they should be integrated into the manufacturing process.

In this talk, I will present some results from our recent EU project Scalable 4.0 where we explored the use of such technology for engine assembly at PSA (Peugeot-Citroen) and for packaging at an SME. The robots are based on robot skills and the skills are defined based on SOPs. I will explain how we model these skills, how, e..g, piston insertion can be learned with Reinforcement Learning, and how user-priors and potentially contradicting objectives (e.g. speed vs. safety) can be taken into account during learning.


Mehul Bhatt

Professor at Örebro University, Sweden.

CoDesign Lab EU

Title: What are the technical/engineering implications of achieving ethical-legal trustworthiness with autonomous vehicles?

Abstract:

Popular perceptions aside, it is no longer a secret that much remains to be desired of the “intelligence” of self-driving cars for their trustworthy -safe, legal, and socially compliant- deployment in public life. How do we go about improving the driving intelligence of autonomous vehicles? What is presently missing per se? What are some possible or desirable baselines of “intelligence” in driving performance, for instance, from the viewpoint of decision-making in safety-critical situations? Why and how do we standardise and evaluate automated driving software performance with respect to performance baselines such that human-centred design expectations, as well as envisaged licensing and regulatory norms may be fulfilled?

In this talk, I will elaborate upon the aforesaid context and present possible directions and solution methodologies. This will be done in the backdrop of a case-study focussing on designing “computational visual commonsense” aimed at enabling self-driving vehicles to form an explainable “space-time mental model” of the dynamic environment typically encountered in everyday driving. The case-study will seek to raise matters pertaining to technological capabilities, as well as normative ethical & legal imperatives in the pursuit of self-driving vehicles. I argue that in addition to a critical emphasis on technological solutions, industrial and academic efforts in autonomous driving also need to emancipate an interdisciplinary mindset encompassing (Spatial) Cognition, AI, and Interaction Design. This is needed to better appreciate the nuances, complexity, and spectrum of diverse human-centred design challenges in fully autonomous driving in the real world.

Biography: Mehul Bhatt is a Professor of Computer Science within the School of Science and Technology at Orebro University (Sweden). His basic research focusses on formal, cognitive, and computational foundations for AI technologies with a principal emphasis on knowledge representation, semantics, integration of commonsense reasoning & learning, explainability, and spatial representation and reasoning. Mehul Bhatt steers CoDesign Lab (www.codesign-lab.org), an initiative aimed at addressing the confluence of Cognition, Artificial Intelligence, Interaction, and Design Science for the development of human-centred cognitive assistive technologies and interaction systems. He pursues ongoing research in Cognitive Vision and Spatial Reasoning (www.codesign-lab.org/cognitive-vision), and also directs the research and consulting group DesignSpace (www.design-space.org) that develops AI-driven techniques for building architecture design.

Mehul Bhatt obtained a bachelors in economics (India), masters in information technology (Australia), and a PhD in computer science (Australia). He has been a recipient of an Alexander von Humboldt Fellowship, a German Academic Exchange Service award (DAAD), and an Australian Post-graduate Award (APA). He was the University of Bremen nominee for the German Research Foundation (DFG) Award: Heinz Maier-Leibnitz-Preis 2014. Prior to Örebro University, Mehul Bhatt was Professor at the University of Bremen (Germany). Further details are available via:  www.mehulbhatt.org.


Call for abstracts

We solicit submissions in the form of extended abstracts (2 pages). Submissions describing work in progress that authors would like to discuss with the workshop participants are encouraged and welcome. Abstracts should follow the same guidelines as the HAI poster papers.

The workshop does not have official proceedings, but the submitted papers will be posted on the workshop website if the authors agree.

Each submitted paper will receive at least two reviews, based on which an acceptance decision will be made.

Papers should be submitted via this form. Please note that email submissions will not be accepted.

Submission Deadline (extended): Oct. 26, November 03, 2023

Notification of acceptance: November 10, 2023


List of accepted abstracts

We accepted a total of six extended abstracts for this workshop.

Below is the information about these abstracts as well as the PDF file of the abstracts whose authors gave consent to share the content of their abstracts.

Acknowledgements

This workshop is supported by the Chalmers AI Research Centre (CHAIR).