figshare
Browse

Qualitative Prediction of Multi-Agent Spatial Interactions

Version 2 2024-10-23, 11:08
Version 1 2024-03-13, 12:59
conference contribution
posted on 2024-10-23, 11:08 authored by Sariah Mghames, Luca Castri, Marc HanheideMarc Hanheide, Nicola BellottoNicola Bellotto

Deploying service robots in our daily life, whether in restaurants, warehouses or hospitals, calls for the need to reason on the interactions happening in dense and dynamic scenes. In this paper, we present and benchmark three new approaches to model and predict multi-agent interactions in dense scenes, including the use of an intuitive qualitative representation. The proposed solutions take into account static and dynamic context to predict individual interactions. They exploit an input- and a temporal-attention mechanism, and are tested on medium and long-term time horizons. The first two approaches integrate different relations from the so-called Qualitative Trajectory Calculus (QTC) within a state-of-the-art deep neural network to create a symbol-driven neural architecture for predicting spatial interactions. The third approach implements a purely data-driven network for motion prediction, the output of which is post-processed to predict QTC spatial interactions. Experimental results on a popular robot dataset of challenging crowded scenarios show that the purely data-driven prediction approach generally outperforms the other two. The three approaches were further evaluated on a different but related human scenarios to assess their generalisation capability.

History

School affiliated with

  • School of Computer Science (Research Outputs)

Publication Title

Proceedings of IEEE RO-MAN 2023

Publisher

IEEE

Date Submitted

2023-08-03

Date Accepted

2023-06-02

Date of First Publication

2023-01-01

Date of Final Publication

2023-01-01

Event Name

32nd IEEE International Conference on Robot and Human Interactive Communication

Event Dates

28-31 August, 2023

Date Document First Uploaded

2023-07-14

ePrints ID

55466

Usage metrics

    University of Lincoln (Research Outputs)

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC