Publication

From percepts to semantics: a multi-modal saliency map to support social robots’ attention

Journal Article (2025)

Journal

ACM Transactions on Human-Robot Interaction

Pages

1-19

Volume

14

Number

4

Doc link

https://doi.org/10.1145/3737891

File

Download the digital copy of the doc pdf document

Authors

Abstract

In social robots, visual attention expresses awareness of the scenario components and dynamics. As in humans, their attention focus should be driven by a combination of different attention mechanisms. In this paper, we introduce multi-modal saliency maps, i.e.

spatial representations of saliency in the world that dynamically integrate multiple sources of attention depending on the different contexts of use. We provide the mathematical formulation of the model and an open-source software implementation. Finally, we introduce initial exploration of its potential in exemplary scenarios of social situations with humans, as well as to evaluate its implementation.

Categories

intelligent robots, service robots, social aspects of automation.

Author keywords

Visual attention, Saliency, Robot gaze, Human-robot interaction

Scientific reference

L. Ferrini, A. Andriella, R. Ros and S. Lemaignan. From percepts to semantics: a multi-modal saliency map to support social robots’ attention. ACM Transactions on Human-Robot Interaction, 14(4): 1-19, 2025.