A Neuro-Symbolic Approach for Enhanced Human Motion Prediction

Mghames, Sariah, Castri, Luca, Hanheide, Marc and Bellotto, Nicola (2023) A Neuro-Symbolic Approach for Enhanced Human Motion Prediction. In: International Joint Conference on Neural Networks (IJCNN), 18-23 June 2023, Queensland, Australia.

Full content URL: https://doi.org/10.48550/arXiv.2304.11740

A Neuro-Symbolic Approach for Enhanced Human Motion Prediction
Published manuscript
ijcnn23.pdf - Whole Document
Available under License Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International.

Item Type:Conference or Workshop contribution (Other)
Item Status:Live Archive


Reasoning on the context of human beings is crucial for many real-world applications especially for those deploying autonomous systems (e.g. robots). In this paper, we present a new approach for context reasoning to further advance the field of human motion prediction. We therefore propose a neuro-symbolic approach for human motion prediction (NeuroSyM), which weights differently the interactions in the neighbourhood by leveraging an intuitive technique for spatial representation called Qualitative Trajectory Calculus (QTC).
The proposed approach is experimentally tested on medium and long term time horizons using two architectures from the state of art, one of which is a baseline for human motion prediction and the other is a baseline for generic multivariate time-series prediction. Six datasets of challenging crowded scenarios, collected from both fixed and mobile cameras, were used for testing. Experimental results show that the NeuroSyM approach outperforms in most cases the baseline architectures in terms of prediction accuracy.

Keywords:neuro-symbolic, context-aware motion prediction, human motion prediction, qualitative interactions
Subjects:G Mathematical and Computer Sciences > G700 Artificial Intelligence
H Engineering > H671 Robotics
G Mathematical and Computer Sciences > G760 Machine Learning
Divisions:COLLEGE OF HEALTH AND SCIENCE > School of Computer Science
Related URLs:
ID Code:54568
Deposited On:16 Jun 2023 14:56

Repository Staff Only: item control page