A Systematic Review of Physical Artificial Intelligence (Physical AI): Concepts, Applications, Challenges, and Future Directions

Renny Sari Dewi; Afif Nurul Kawakib; Maghfiroh Nur Laili; Anannda Lailatul Fauziah; Salsabilla Rahma Sabrina; Rafidah Latifah Hana

doi:10.59934/jaiea.v4i3.1101

Authors

Renny Sari Dewi Universitas Negeri Surabaya
Afif Nurul Kawakib Universitas Negeri Surabaya
Maghfiroh Nur Laili Universitas Negeri Surabaya
Anannda Lailatul Fauziah Universitas Negeri Surabaya
Salsabilla Rahma Sabrina Universitas Negeri Surabaya
Rafidah Latifah Hana Universitas Negeri Surabaya

DOI:

https://doi.org/10.59934/jaiea.v4i3.1101

Keywords:

Physical Artificial Intelligence, Robotics, Cyber-Physical Systems (CPS), AI Applications, Challenges, Technologies

Abstract

Physical AI represents a significant evolution from digital AI , interacting directly with the physical world and mimicking human functions to a greater extent. PAI is a multidisciplinary field divided into Integrated PAI (IPAI) and Distributed Physical AI (DPAI). This systematic literature review analyzes the concept of PAIs, their implementation in various domains such as IoT, automotive, agriculture, healthcare, and logistics, and highlights their transformative potential. Nonetheless, PAIs face significant challenges such as general AI concerns (privacy, bias) and specific challenges (presence in unregulated spaces, information organization, social acceptance, Cannikin law). The integration of PAIs into Cyber-Physical Systems (CPS) also presents challenges related to uncertainty, limited resources, and adversarial attacks. PAIs are supported by advanced technologies from materials science, mechanical engineering, computer science, chemistry, and biology, including deep learning, multimodal processing, domain randomization, zero-shot learning, and large language objects (LLOs). This research provides comprehensive insights to drive the development of reliable and transformative PAIs in the future.

Downloads

Download data is not yet available.

References

Y. Li, Z. Li, Y. Duan, and A. B. Spulber, “Physical artificial intelligence (PAI): the next-generation artificial intelligence,” Frontiers of Information Technology and Electronic Engineering, vol. 24, no. 8, pp. 1231–1238, Aug. 2023, doi: 10.1631/FITEE.2200675.

K. Nagatani et al., “Innovative technologies for infrastructure construction and maintenance through collaborative robots based on an open design approach,” Advanced Robotics, vol. 35, no. 11, pp. 715–722, 2021, doi: 10.1080/01691864.2021.1929471.

D. Häusermann et al., “FireDrone: Multi-Environment Thermally Agnostic Aerial Robot,” Advanced Intelligent Systems, vol. 5, no. 9, Sep. 2023, doi: 10.1002/aisy.202300101.

S. Lee et al., “Cyber-Physical AI: Systematic Research Domain for Integrating AI and Cyber-Physical Systems,” ACM Transactions on Cyber-Physical Systems, vol. 9, no. 2, Apr. 2025, doi: 10.1145/3721437.

M. Coelho, “F E AT U R E Large Language Objects: The Design of Physical AI and Generative Experiences.” [Online]. Available: https://architecture.mit.edu/news/

V. Jham, G. Malhotra, and N. Sehgal, “Consumer-brand Relationships with AI Anthropomorphic Assistant: Role of Product Usage Barrier, Psychological Distance and Trust,” International Review of Retail, Distribution and Consumer Research, vol. 33, no. 2, pp. 117–133, 2023, doi: 10.1080/09593969.2023.2178023.

L. Sørensen, D. T. Sagen Johannesen, H. Melkas, and H. M. Johnsen, “User Acceptance of a Home Robotic Assistant for Individuals With Physical Disabilities: Explorative Qualitative Study,” JMIR Rehabil Assist Technol, vol. 12, 2025, doi: 10.2196/63641.

Q. Yan et al., “A novel hybrid physical-AI approach for zero-shot diagnosis of rotor bolted joint conditions during operation.” [Online]. Available: https://ssrn.com/abstract=5110276

Y. Tao and B. Luo, “Monostable stochastic resonance activation unit-based physical reservoir computing,” Journal of the Korean Physical Society, vol. 82, no. 8, pp. 798–806, Apr. 2023, doi: 10.1007/s40042-023-00727-8.

L. Bachar, O. Matania, R. Cohen, R. Klein, M. G. Lipsett, and J. Bortman, “A novel hybrid physical AI-based strategy for fault severity estimation in spur gears with zero-shot learning,” Mech Syst Signal Process, vol. 204, Dec. 2023, doi: 10.1016/j.ymssp.2023.110748.