Integrating Neural And Symbolic AI For Robust Generalized Planning In Robotics

Dr. Arjun Malhotra; Meenal Sinha

Open Access

Integrating Neural And Symbolic AI For Robust Generalized Planning In Robotics

pdf

Dr. Arjun Malhotra ¹ Meenal Sinha ¹

⁴ Department of Artificial Intelligence, Indian Institute of Science, Bengaluru, India

⁴ Department of Robotics and Intelligent Systems, Indian Institute of Technology Bombay, Mumbai, India

Abstract

The integration of neural and symbolic Artificial Intelligence (AI) offers a promising pathway toward achieving robust and generalized planning in robotics. While neural networks excel at perception and pattern recognition, symbolic AI contributes structured reasoning and interpretability. This paper explores a hybrid approach that combines neural perception modules with symbolic planning frameworks to enable robots to operate effectively in dynamic and partially observable environments. The study reviews recent advancements in neurosymbolic architectures for task generalization, real-time decision-making, and cross-domain adaptability. Emphasis is placed on bridging the gap between low-level sensory data and high-level abstract reasoning to support flexible, explainable, and scalable robotic behavior. The findings highlight the potential of integrated neural-symbolic systems to advance autonomous robotics in complex, real-world applications.

How to Cite

Dr. Arjun Malhotra, & Meenal Sinha. (2025). Integrating Neural And Symbolic AI For Robust Generalized Planning In Robotics. Frontiers in Emerging Artificial Intelligence and Machine Learning, 2(04), 8–13. Retrieved from https://irjernet.com/index.php/feaiml/article/view/76

⬇ Endnote/Zotero/Mendeley (RIS) ⬇ BibTeX

References

📄 Capitanelli, A., & Mastrogiovanni, F. (2023). A framework for neurosymbolic robot action planning using large language models. arXiv preprint arxiv.org, 9.

📄 Silver, T., Liang, Y., Weller, H., et al. (2025). VisualPredicator: Learning abstract world models with neuro-symbolic predicates for robot planning. ICLR Spotlight openreview.net.

📄 Ugur, E., Ahmetoglu, A., Nagai, Y., et al. (2025). Neuro-Symbolic Robotics: An overview of architectures integrating neural networks and symbolic systems. Submitted/recent arxiv.org, 15.

📄 Manhaeve, R., Dumančić, S., Kimmig, A., Demeester, T., & De Raedt, L. (2018). DeepProbLog: neural probabilistic logic programming. NeurIPS researchgate.net, 1.

📄 Silver, T., & colleagues. (2023). Learning Neuro-Symbolic Skills for Bilevel Planning. Proceedings of Machine Learning Research smythos.com, 15.

📄 Anonymous Authors. (2023). Neurosymbolic reinforcement learning and planning: A survey. arXiv preprint openreview.net, 3.

📄 Anonymous Authors. (2021). A survey on neural-symbolic learning systems. ScienceDirect sciencedirect.com.

📄 Kwon, M., Kim, Y., & Kim, Y. J. (2024). Fast and accurate task planning using neuro-symbolic language models and multi-level goal decomposition. arXiv preprint arxiv.org, 1.

📄 English, W., Simon, D., Jha, S., & Ewetz, R. (2024). NSP: A neuro-symbolic natural language navigational planner. arXiv preprint arxiv.org, 13.

📄 Anonymous Authors. (2023). A case for neuro-symbolic AI in constrained task planning. Proceedings of ACM SACMAT ’23 frontiersin.org, 7.

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors retain the copyright of their articles published in this journal. All articles are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are properly cited.