Логіко-графова інтерпретація сцени в трансформерному ядрі автономного дрона

Назарій Лопух; Петро Жук; Адріан Торський

doi:10.15407/fmmit2025.40.130

Назарій Лопух Інститут прикладних проблем механіки і математики ім. Я. С. Підстригача НАН України
Петро Жук Інститут прикладних проблем механіки і математики ім. Я. С. Підстригача НАН України
Адріан Торський Інститут прикладних проблем механіки і математики ім. Я. С. Підстригача НАН України

DOI: https://doi.org/10.15407/fmmit2025.40.130

Abstract

This paper presents the concept of an intelligent drone equipped with a semantic core designed to construct logical-graph representations of the environment based on sensory data. The main objective is to develop an adaptive system capable not only of object recognition but also of forming causal, spatial, and functional relationships between objects to enable logical reasoning. The proposed approach integrates reinforcement learning techniques with graph-based semantics within a transformer architecture, thus ensuring autonomous operation and behavioral flexibility in partially observable environments.

References

Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L., Gomez A. N., Kaiser Ł., Polosukhin I. Attention is All You Need // Advances in Neural Information Processing Systems. - 2017. - Vol. 30.

Battaglia P., Hamrick J., Bapst V. et al. Relational inductive biases, deep learning, and graph networks // arXiv preprint. - 2018. - arXiv:1806.01261. - 21 p.

Pearl J. Causality: Models, Reasoning and Inference. - 2nd ed. - Cambridge: Cambridge University Press, 2009. - 432 p. https://doi.org/10.1017/CBO9780511803161

Marcus G. The Next Decade in AI: Why Common Sense Matters // arXiv preprint. - 2020. - arXiv:2002.06177. - 12 p.

Kipf T. N., Welling M. Semi-Supervised Classification with Graph Convolutional Networks // Proc. Int. Conf. on Learning Representations (ICLR). - 2017.

Hamilton W. L., Ying R., Leskovec J. Representation learning on graphs: Methods and applications // IEEE Data Engineering Bulletin. - 2017. - Vol. 40, No. 3. - P. 52-74.

Chen Y., Dai X., Liu M. et al. A Survey on Vision Transformer // arXiv preprint. - 2021. - arXiv:2012.12556. - 30 p.

Brachman R. J., Levesque H. J. Knowledge Representation and Reasoning. - San Francisco: Morgan Kaufmann, 2004. - 381 p. https://doi.org/10.1016/B978-155860932-7/50099-6

Zellers R., Bisk Y., Farhadi A., Choi Y. From Recognition to Cognition: Visual Commonsense Reasoning // Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). - 2019. - P. 6720-6731. https://doi.org/10.1109/CVPR.2019.00688

Logical-Graph Interpretation of Scene in the Transformer Core of an Autonomous Drone

Abstract

References