Predictive World Models for Social Navigation

Goodluck Oguzie, Anikó Ekárt, Luis J. Manso

Research output: Chapter in Book/Published conference outputConference publication


As robots begin to coexist with humans, the need for efficient and safe social robot navigation becomes increasingly pressing. In this paper we investigate how world models can enhance the effectiveness of reinforcement learning in social navigation tasks. We introduce three approaches that leverage predictive world models, which are then benchmarked against state-of-the-art algorithms. For a comprehensive and reliable evaluation, we employed multiple metrics during the training and testing phases. The key novelty of our approach consists in the integration and evaluation of predictive world models within the context of social navigation, as well as in the models themselves. Based on a diverse set of performance metrics, the experimental results provide evidence that predictive world models help improve reinforcement learning techniques for social navigation.
Original languageEnglish
Title of host publicationAdvances in Computational Intelligence Systems, Contributions Presented at the 22nd UK Workshop on Computational Intelligence
EditorsNitin Naik, Paul Jenkins, Paul Grace, Longzhi Yang, Shaligram Prajapat
Number of pages13
ISBN (Electronic)978-3-031-47508-5
ISBN (Print)978-3-031-47507-8
Publication statusPublished - 1 Feb 2024
EventThe 22nd UK Workship on Computational Intelligence - Aston University, Birmingham, United Kingdom
Duration: 6 Sept 20238 Sept 2023

Publication series

NameAdvances in Intelligent Systems and Computing (AISC)
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365


ConferenceThe 22nd UK Workship on Computational Intelligence
Abbreviated titleUKCI 2023
Country/TerritoryUnited Kingdom
Internet address

Bibliographical note

This version of the paper has been accepted for publication, after peer review and is subject to Springer Nature’s AM terms of use [], but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at:


Dive into the research topics of 'Predictive World Models for Social Navigation'. Together they form a unique fingerprint.

Cite this