Tuesday June 27, 2023 -  Swansea, Wales (in presence only)

Engineering Interactive Systems Embedding AI Technologies 

Deadline for submissions: Friday June 2, 2023 23:59 AoE 

Workshop date: Monday June 27th, 2023

Submission system: easychair

Follow up workshop at EICS 2024 - More information here 

Draft Program of the workshop 

9.00 Registration

9.30 Welcome and introduction to the workshop

9.45 Short talks session 1 (15 mn each 10mn presentation and 5 mn questions)

Max Pascher, Kirill Kronhardt, Jan Freienstein and Jens Gerken   Exploring AI-enhanced Shared Control for an Assistive Robotic Arm

Alan Dix Hidden Figures: Architectural challenges to expose parameters lost in code

David Navarre and Philippe Palanque Should I Engineer My Interactive System with AI Technologies? Benefits and Limitations

10.30 Coffee break

11.00 short talks session 2 (15 mn each 10mn presentation and 5 mn questions)

Benedikt Severin, Ole Werger and Marc Hesenius Not What I Was Trained For – Out-Of-Distribution-Tests for Interactive Ais

Bárbara Ramalho, Eduardo Silva, Filipe Soares, João Gonçalves, Rui Carreira and Alberto Gil The role of human-machine collaboration in the quality control of ceramic tableware with visual and acoustics inspection

Lucio Davide Spano Explaining through the Right Reasoning Style: Lessons Learnt

Alba Bisante, Emanuele Panizzi, Stefano Zeppieri, Enrico Bassetti and Venkata Srikanth Varma Datla An approach to leverage Artificial Intelligence for car-parking related mobile applications

Pranjal Jain, Nicholas Micallef and Julian Hough Explaining AI Models Tangibly: A New Dimension in XAI 

12.30 Lunch Break

13.30 Interactive discussion on topics identification for the afternoon (up to four topics)

13.45 First interactive session (Topic 1 and 2)

15.00 Coffee Break

15.30 Second interactive session (Topic 3 and 4)

16.45 Wrap-up session and future plans

17.00 End of workshop 

Download here the list of papers

List of participants

Introduction

Automation is pervasive in interactive systems, as argued in [4]. While automation varies in nature and objectives, it is present in every layer of interactive systems architectures, from hardware input device driver level (e.g., mouse acceleration [1]), to interaction technique level (e.g., multimodal fusion such as finger clustering [2] or more sophisticated ones such as the bubble cursor [3] integrating both input and output automation) as well as at the interactive application level (e.g., a SPAM filter in a client email application).


Technologies coming from the AI domain (e.g., machine learning) claim and argue for more complex automation targeting the ultimate goal of autonomous systems, as demonstrated by the thriving autonomous driving application domain as depicted in J3016 standard [4]. Even though having larger automation might induce larger failures (known as the lumberjack analogy [16]), integrating such AI-related technologies can be performed at various levels, from micro to macro, requiring different (and maybe conflicting) engineering approaches.


Besides, due to their black-box nature, AI technologies bring issues at the operation level, i.e., when users are interacting with an interactive application embedding them [5]. In order to address this issue, a recent contribution [5] has demonstrated the potential benefit of opening up that box and adding explanations but usability issues remain, as demonstrated in the active domain of recommender systems [17].


At the engineering level, different issues appear depending on the type of AI-related technologies used and the type of interactions provided to the users of such systems. Indeed, beyond explanations, issues related to display/visualization [18] and control/command arise [19].


Goals and Objectives

The main goal of this workshop is to offer a platform for scientists who are interested in the design, development, evaluation, and use of interactive systems involving AI technologies.

The first objective is to identify and gather information about knowledge and practice in the workshop’s domain:

· Get an overview of current practices in R&D practices (methods/notations/tools) to engineer usable interactive systems embedding AI technologies, as well as lessons learned and recommendations;

· Get an overview of current practices in R&D practices (methods/notations/tools) to architect usable interactive systems embedding AI technologies, as well as lessons learned and recommendations;

· Identify a systematic approach for describing AI technologies and assessing their impact on properties such as users’ UX and systems’ usability;

· Understand how the multiple stakeholders involved in interactive systems design and development identify properties, how they describe them, and how they assess their relative importance when they embed AI technologies (going beyond the classical UX and usability but also addressing performance, dependability, safety, ...).

 

The second objective is to elicit the main gaps in AI technologies which hinders their exploitation in the design and development of interactive systems, especially if a user-centered design process is followed.

Post-workshop publications 

Workshop attendees will be offered the opportunity to revise and extend their submission, which will, after reviewing, be included in the post-workshop proceedings to be published by Springer in the LNCS series. 

How to Contribute?

Submit your contribution by sending us an email to: an easychair link will be provide soon 


Template: Springer Lecture Notes in Computer Science proceedings 

Contributions should be submitted in a PDF document of 2-6 pages in length (references excluded). Upon acceptance, at least one author will be required to register to the EICS conference and attend (physically) the workshop. Notifications will be sent to the authors according to the dates indicated below.

Do you have any questions about the workshop? Contact us at  palanque@irit.fr 


 Important dates