Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jan 2;15(1):113.
doi: 10.1038/s41598-024-84071-2.

SAILOR: perceptual anchoring for robotic cognitive architectures

Miguel Á González-Santamarta  1 , Francisco J Rodrıguez-Lera  2 , Vicente Matellan-Olivera  2 , Virginia Riego Del Castillo  2 , Lidia Sánchez-González  2
Affiliations

SAILOR: perceptual anchoring for robotic cognitive architectures

Miguel Á González-Santamarta et al. Sci Rep. .

Abstract

Symbolic anchoring is an important topic in robotics, as it enables robots to obtain symbolic knowledge from the perceptual information acquired through their sensors and maintain the link between that knowledge and the sensory data. In cognitive-based robots, this process of transforming sub-symbolic data generated by sensors to obtain and maintain symbolic knowledge is still an open problem. To address this issue, this paper presents SAILOR, a framework for symbolic anchoring integrated into ROS 2. SAILOR aims to maintain the link between symbolic data and perceptual data in real robots over time. It provides a semantic world modeling approach using two deep learning-based sub-symbolic robotic skills: object recognition and matching function. The object recognition skill allows the robot to recognize and identify objects in its environment, while the matching function enables the robot to decide if new perceptual data corresponds to existing symbolic data. This paper describes the proposed method and the development of the framework, as well as its integration in MERLIN2 (a hybrid cognitive architecture fully functional in robots running ROS 2) and the validation of SAILOR using public datasets and a real-world scenario.

PubMed Disclaimer

Conflict of interest statement

Declarations. Competing interests: The authors declare no competing interests. Ethics approval: The authors confirm that they have complied with the publication ethics and state that this work is original and has not been used for publication anywhere before.

Figures

Figure 1
Figure 1
Example of SAILOR during time. The first row represents the current anchors of SAILORS while the second row represents the detection obtained from YOLOv8. Each anchor is given a symbolic name, which are person-0, person-1, chair-0 and chair-1.
Figure 2
Figure 2
SAILOR’s framework. It is composed of a symbolic layer, an anchoring layer, and a perceptual layers.
Algorithm 1
Algorithm 1
SAILOR’s symbolic anchoring algorithm.
Algorithm 2
Algorithm 2
Create matching table algorithm.
Figure 3
Figure 3
Neural network used to implement the matching function of SAILOR. It is divided into three components: ResNet Siamese, which produces the similarity between two images as a feature vector; PerceptAnchor Network, which encodes each pair of percept-anchor; and Binary Classifier, which classifies each encoded pair as reacquired or acquired.
Figure 4
Figure 4
MERLIN2 architecture showing SAILOR as a robot skill.
Figure 5
Figure 5
Rosgraph of SAILOR, which includes YOLOv8 and camera nodes.
Algorithm 3
Algorithm 3
Create dataset algorithm.
Figure 6
Figure 6
Real-world robot and environment used in experimentation. The robot used is TIAGo, a service robot with a differential mobile base, equipped with a LiDAR, and a torso, equipped with an RGB-D camera, speakers and microphone. The real-world environment is the apartment Leon@Home Testbed of the Robotics Group of the University of León.
See this image and copyright information in PMC

References

    1. Ye, P., Wang, T. & Wang, F.-Y. A survey of cognitive architectures in the past 20 years. IEEE Trans. Cybern.48, 3280–3290 (2018). - PubMed
    1. Kotseruba, I. & Tsotsos, J. K. 40 years of cognitive architectures: Core cognitive abilities and practical applications. Artif. Intell. Rev.53, 17–94 (2020).
    1. Kotseruba, I., Gonzalez, O. J. A. & Tsotsos, J. K. A review of 40 years of cognitive architecture research: Focus on perception, attention, learning and applications. arXiv preprint arXiv:1610.08602 1–74 (2016).
    1. Fox, M. & Long, D. Pddl2. 1: An extension to pddl for expressing temporal planning domains. J. Artif. Intell. Res.20, 61–124 (2003).
    1. Quigley, M. et al. Ros: An open-source robot operating system. In ICRA Workshop on Open Source Software. Vol. 3. 5 (2009).

LinkOut - more resources