Publications

"Interacting with a Social Robot Affects Visual Perception of Space", the paper presented at HRI 2020 International Conference on Human-Robot Interaction, has been awarded with a Honorable Mention

 Human partners are very effective at coordinating in space and time. Such ability is particular remarkable considering that visual perception of space is a complex inferential process, which is affected by individual prior experience (e.g. the history of previous stimuli). As a result, two partners might perceive differently the same stimulus. Yet, they find a way to align their perception, as demonstrated by the high degree of coordination observed in sports or even in everyday gestures as shaking hands. Robots would need a similar ability to align with their partner's perception. However, to date there is no knowledge of how the inferential mechanism supporting visual perception operates during social interaction. In the current work, we use a humanoid robot to address this question. We replicate a standard protocol for the quantification of perceptual inference in a HRI setting. Participants estimated the length of a set of segments presented by the humanoid robot iCub. The robot behaved in one condition as a mechanical arm driven by a computer and in another condition as an interactive, social partner. Even if the stimuli presented were the same in the two conditions, length perception was different when the robot was judged as an interactive agent rather than a mechanical tool. When playing with the social robot, participants relied significantly less on stimulus history. This result suggests that the brain changes optimization strategies during interaction and lay the foundations to design humanaware robot visual perception.

Publications

  • Workshop Paper

    2020 Sciutti A., Sandini G., HCI - Human Centered Interaction
    SIGCHI Italy (ACM SIGCHI Italian Chapter)
    Download full-text here

    Future AI specialists should ideally be faced from the start of their career with the most critical challenge in developing technology designed for humans: the humans. The complexity of human cognition as a whole and of its social component in particular needs to be accounted for, if the developer aims at creating AI systems able to help and engage users effectively and for more than a few days. In our proposal we suggest 5 topics that according to us should be part of any syllabus used for teaching HCI skills to designers of AI interactive systems - and potentially also for those adopted in the context of HRI. This would help developers in creating technology considerate of humans, respectful of our needs and intrinsically caring of our wellbeing in the interaction.

  • Workshop Paper

    2020 Vannucci F., Di Cesare G., Rea F., Sandini G., Sciutti A., Expressive handovers: neural and behavioral effects of different attitudes in humanoid actions
    IEEE International Conference on Robotics and Automation

    Interacting with others requires the ability to evaluate their attitudes based on how actions are performed. Even a simple everyday act as handing over an object acquires a different meaning if it is performed gently or harshly. Concerning human-robot interaction, it is important to be aware of the impact that robot motion features might have in the partner’s interpretation of their actions. The challenge we address in this research is to endow the iCub humanoid robot with the capacity to communicate intuitively positive and negative attitudes in its own actions.
    Download full-text here

  • Conference Paper

    2019 Tanevska A., Rea F., Sandini G., Canamero L., Sciutti A., Eager to Learn vs. Quick to Complain? How a socially adaptive robot architecture performs with different robot personalities.
    IEEE International Conference on Systems, Man, and Cybernetics
    Download full-text here - Open Access Version 

    Robots that are aware of our needs (perceptual, motor or social) and adapt to them have the potential of creating a personalized and effective human-like interaction.  In this paper we explore how the very same adaptive architecture would be affected by different sets of parameters, i.e. by implementing the same adaptive framework with different robot personalities.

  • Conference Paper

    2019 Goyal G., Noceti N., Sciutti A., Odone F., The role of ego vision in view-invariant action recognition.
    The 4th International Workshop on egocentric perception, interaction and computing at CVPR 2019 Long Beach, CA
    Download full-text here

    A crucial step for machines to establish shared perception with their human partners is to understand how to map action understanding across different visual perspectives. In this extended abstract we explore affinities and differences between ego and allo (or third-person) vision and we leverage transfer learning in Convolutional Neural Networks to demonstrate capabilities and limitations of an implicitly learnt view-invariant representation for action recognition.

Talks

Currently the ideas behind the project
have been presented in the following talks:

  • Keynote at the AIR project kick-out meeting - Skӧvde, Sweden, 19-20 March 2019. Title: “Robot & Humans: from mutual understanding to interaction and trust

  • Keynote at the Cognitive Science Arena 2019 - Bressanone, Italy, 15-16 February 2019. Title: “Future challenges in cognitive science: The new frontier of human robot interaction

  • Invited talk at The 1st International Symposium on Symbiotic Intelligent Ststems (SISReC) - Osaka, Japan, 25 January 2019. Title:"Intutitive understanding between humans and robots".

  • Invited talk at the series of events "Disegni, Invenzioni e Macchine"  ("Drawings, Inventions and Machines") at Palazzo Ducale, Genoa, Italy, 16th January 2019. Title: "Robots that help humans...to understand themselves" (Robot che aiutano… a comprendere l'uomo, in Italian).

  • Presentation "wHiSPER - Investigating Human Shared Perception with Robots" to the ISCIT (Istituto Superiore di Studi in Tecnologie dell'Informazione e della Comunicazione) students, Genoa, Italy, December 7, 2018.

  • Invited talk at the Festival Dell’Eccellenza al Femminile – Genoa, Italy, 20 November 2018. Title: “Communication in the robot era” (“Comunicazione al tempo dei robot”, in Italian).

  • Invited talk at the SICSA Workshop on Cyber Physical Systems – Edinburgh, UK, 16 November 2018. Title: “Mutual understanding for better human-robot interaction”.

  • Keynote at the World Usability Day – Turin, Italy, 8 November 2018. Title: “More Humane Robots” (“Robot piu’ umani”, in Italian).

  • Invited Talk at Skövde University, Skövde, Sweden - October 23, 2018. Title: “Action and Perception in HRI”.

  • Keynote at the workshop BODIS: The utility of body, interaction and self learning at IROS 2018 - Madrid, Spain, October 2018.

ERC Starting Grant
Principal Investigator: Alessandra Sciutti
Period: 3/2019- 2/2024. G.A: 804388

The content of this website is the sole responsibility of the authors. The European Commission or its services cannot be held responsible for any use that may be made of the information it contains.