Social Navigation Using Soar Cognitive architecture as high-level controller for mobile robots

Master thesis (2025)

Authors

B. Essabri Mechanical Engineering

Contributors

F. Zamani Khalili Robot Dynamics (mentor)
Carlos Corbato Robot Dynamics (mentor)
J. Sijs Learning & Autonomous Control (graduation committee member)
Faculty
Mechanical Engineering
More Info
expand_more

Published Date

18-02-2025

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Mechanical Engineering

Abstract

This paper presents a Soar-based system for social navigation in mobile robots, where the Soar cognitive architecture serves as a high-level controller to dynamically adapt the navigation behavior of a lower-level motion controller based on environmental and social cues. The navigation behavior configured in this work is the maximum allowed speed, enabling safe and
socially appropriate navigation around humans. Soar’s symbolic reasoning and procedural logic provide a scalable and flexible framework for high-level control in complex environments. The research focuses on human-following within social navigation, with experimental results demonstrating the system’s effectiveness and adherence to social norms. However, limitations in navigation performance and simulation realism highlight opportunities for future work to enhance Soar’s application in complex, real-world scenarios.

Files

Social_navigation_using_Soar_P... (pdf)
(pdf | 2.03 Mb)
Unknown license