Social affordance spaces as navigation goals in human-aware robot navigation for gaze-based immersive telepresence robots: a museum use case

Millan-Norman, Samuel, Silva Mendoza, Steven, Yan, Desiree, Kucukyilmaz, Ayse, Ramirez Gomez, Argenis, Romero Cano, Victor ORCID: https://orcid.org/0000-0003-2910-5116 and Hernandez Vega, Juan ORCID: https://orcid.org/0000-0002-9593-6789 2026. Social affordance spaces as navigation goals in human-aware robot navigation for gaze-based immersive telepresence robots: a museum use case. Presented at: IEEE Telepresence 2026, Bristol, UK, 9-13 November. IEEE,

Full text not available from this repository. (Request a copy)

Abstract

Immersive telepresence robots are mobile service robots equipped with a 360 degree camera that streams to an operator located in a remote environment using a virtual reality head mounted display. These robots offer the opportunity to enhance the operator's sense of presence while enabling them to navigate and interact within remote crowded spaces, such as museums or universities. Using gaze-based interactions, users drive the robots through remote environments by transmitting intricate low-level user commands, such as velocity. This mode of operation requires specialised training to ensure the robot’s safe manoeuvrability and minimal interference with individuals in its vicinity. However, in scenarios such as remote visits to museums, it is impractical to expect users (i.e. remote visitors) to possess or acquire the expertise to manoeuvre an immersive telepresence robot proficiently. In this paper, we propose a novel immersive telepresence framework capable of handling high-level user commands (e.g. destinations) through gaze-based interactions to lead a robot that semi-autonomously navigates a social space in a socially acceptable manner towards a social affordance space defined as a goal region. Through a user study with 16 participants, we evaluate our proposed framework for moving an immersive telepresence robot in a simulated crowded museum-like environment to reach an exhibit. Results highlight the proficiency of our framework in moving through the robot's environment in a more socially acceptable manner, and reducing the effort, mental demand and perceived workload on remote operators compared to transmitting low-level user commands.

Item Type:	Conference or Workshop Item - published (Paper)
Status:	In Press
Schools:	Schools > Computational & Mathematical Sciences Schools > Computer Science & Informatics
Publisher:	IEEE
Related URLs:	Organisation
Date of First Compliant Deposit:	28 September 2026
Date of Acceptance:	27 July 2026
Last Modified:	29 Sep 2026 11:01
URI:	https://orca.cardiff.ac.uk/id/eprint/189849

Actions (repository staff only)

Edit Item