ASIMOV 2021

ASIMOV Adaptive Social Interaction and MOVement for assistive and rehabilitation robotics will be held the 12th of November in conjunction with the Thirteenth International Conference on Social Robotics, 10-13 November 2021, Singapore.

abstract

Endowing robots with learning and online behavioral adaptation abilities is a key objective for enabling natural and efficient human robot interaction, especially in the areas of assistive and rehabilitation robotics. Nevertheless, as one of Asimov's novels pointed out in The Complete Robot (1982), if a robot, such as Lenny, is given the ability to learn, it will inevitably make mistakes before adapting itself. One of the critical issues is thus to design robot learning abilities that lead to a behavior that meets three criteria at the same time: efficiency, acceptability and security for the human. The ASIMOV workshop will constitute a unique opportunity to gather roboticists and computer scientists to present a variety of current approaches aiming at endowing social robots with learning abilities, enhanced cognitive and social abilities, and discuss their potential to meet these criteria. This will permit to analyze the current state of the art and of its possible real-world applications in assistive and rehabilitation robotics

SCIENTIFIC CONTEXT

Isaac Asimov, the famous Russian-American science-fiction writer (but also scientific, biochemical popularizer) was a sort of soothsayer. Never before, the robots for which he formulated the famous Three Laws of Robotics (which should prevent robots from harming humans) and which appear in so many of his stories and novels (the Robot Cycle) have been so present in reality. Robots got out of the industry's cages and have started to find wide applicability in many different fields, spanning from entertainment to education and assistance where they operate in strict contact with human beings. Social robots are receiving more success in the above-mentioned fields since their social and human-like behavior based on the adaptation with respect to the environment and to human emotions and movements during collaborative activities bring people to interact with them close to the way they would interact with human beings. Despite the recognized potential and usefulness of social robots for assistive purposes, people are still worried about their utilization. Hence, when designing social robots behavior and structure, it is of paramount importance to consider all the aspects that can affect their acceptability, from ethical aspects to physical and psychological safety to security aspect related to privacy violation, etc. Additionally, it is necessary to enhance the ability to adapt on the fly to the users' behavior, needs and motivations. Creating robotic systems capable of correctly modeling and recognizing human behavior and intention and of adapting their behavior to the user under the above-mentioned constraints and the ASIMOV's laws is a very critical task, especially in the domain of assistive and social robotics and when working with vulnerable user populations.

OBJECTIVES

The workshop's main goal is to figure out how we can design and control robots whose behavior during interaction with humans shall adapt in a way that is:

• efficient for the assigned task;

• natural, understandable and acceptable for the human;

• safe and secure in terms of human physical and psychological integrity.

The workshop will constitute an opportunity to present a variety of current approaches aiming at endowing social assistive robots with learning abilities, and discuss their acceptability and efficiency with respect to these criteria.

Target Audience

This workshop is intended as a forum for a broad audience, which spans from social and assistive robotics, adaptation and personalization in Social HRI, innovative technologies for education and robot-assisted clinical applications. The workshop should be a place to exchange opinions, to discuss innovative ideas and to get hints and suggestions on ongoing research, therefore contributing to tackle unresolved issues. The proposed topic brings together researchers working on user behavior and intention detection, human-robot interaction, social and assistive robotics, control interfaces, learning, and ethical and safety issues in human-machine interaction, among others. A large scientific community is involved in such research fields.

news

• ASIMOV Recording Link: https://cloud.isir.upmc.fr/owncloud/index.php/s/ZUskhlhCOE8Anr4

• Prof. Agnieszka Wykowska Italian Institute of Technology (Genoa, Italy) has been confirmed as an invited speaker. The title of the talk is "Is endowing robots with social signals always beneficial? "

• Dr. Shruti Chandra University of Waterloo has been confirmed as an invited speaker. The title of the talk is "Child-Robot Interaction: Learning and Playing with Social Robot".

• Selected papers will be invited to submit an extended/revised version to a high impact Journal Special Issue.

• The Workshop will be held on 12th November 2021.