Keywords
Artificial Intelligence
Physical AI
Fundamental Physics
Fundamental Robotics
Robotic
Intelligent Health Engineering
AI Engineering
System of Systems Engineering
Cyberphysical Systems
Digital Twin
Virtual Engineering
Computer Aided Engineering
Internet of Things
IoT
Autonomous Driving
How to Cite
Abstract
This work will elaborate the fundamental principles of physical artificial intelligence (Physical AI ) from a scientific and systemic perspective. The aim is to create a theoretical foundation that describes the physical embodiment, sensory perception, ability to act, learning processes, and context sensitivity of intelligent systems within a coherent framework. While classical AI approaches rely on symbolic processing and data driven models, Physical AI understands intelligence as an emergent phenomenon of real interaction between body, environment, and experience. The six fundamentals presented here are embodiment, sensory perception, motor action, learning, autonomy, and context sensitivity, and form the conceptual basis for designing and evaluating physically intelligent systems. Theoretically, it is shown that these six principles do not represent loose functional modules but rather act as a closed control loop in which energy, information, control, and context are in constant interaction. This circular interaction enables a system to generate meaning not from databases, but from physical experience, a paradigm shift that understands intelligence as an embodied, material process. Physical AI understands learning not as parameter adjustment, but as a change in the structural coupling between agents and the environment. To illustrate this, the theoretical model is explained using a practical scenario: An adaptive assistant robot supports patients in a rehabilitation clinic. Thanks to its soft, sensor supported joints, it can physically sense how much weight a person can bear. It learns from resistance, movement, and body language to precisely regulate its strength and recognizes when it needs to actively intervene or hold back. This example illustrates that physical intelligence does not arise from abstract calculation, but from immediate, embodied experience. It shows how the six fundamentals interact in a real system: embodiment as a prerequisite, perception as input, movement as expression, learning as adaptation, autonomy as regulation, and context as orientation. In general, this work is intended to contribute to the theoretical and methodological foundation of a new generation of intelligent systems that act physically, learn, and act responsibly in the world. The principles formulated here are intended to serve as a guide for researchers and engineers to further develop Physical AI from an abstract idea into a practical design concept.
References
Adadi, A., & Berrada, M. (2018). Peeking inside the black box: A survey on explainable artificial intelligence (XAI). *IEEE Access*, 6, 52138–52160.
Jin, X.-b., et al. (2018). Mobile intelligence methods for robotics: A survey. *IEEE Transactions on Robotics*.
Radanliev, P., et al. (2019). Artificial intelligence in cyber-physical systems: A taxonomy and conceptual framework. *Computers in Industry*.
Zhou, Z., et al. (2019). Edge intelligence: Paving the last mile of artificial intelligence. *Proceedings of the IEEE*, 107(8).
Ogenyi, U. E., et al. (2019). Collaborative robotics and human–robot interaction: A survey. *Robotics and Autonomous Systems*.
Mehrabi, N., et al. (2019). A survey on bias and fairness in machine learning. *ACM Computing Surveys*, 51(6).
Miriyev, A., & Kovač, M. (2020). Skills and education for physical artificial intelligence. *Nature Machine Intelligence*, 2.
Willard, J., et al. (2020). Integrating physics-based modeling with machine learning. *Nature Reviews Physics*, 2.
Sitti, M. (2021). Physical intelligence as a new paradigm. *Nature Machine Intelligence*, 3(8).
Duan, J., et al. (2021). Embodied AI: From simulators to tasks. *Artificial Intelligence Review*.
Wagner, G., et al. (2021). AI in literature review processes. *Journal of Information Systems*.
Duan, J., et al. (2022). Machine learning for intuitive physics. *IEEE Transactions on Neural Networks and Learning Systems*.
Hao, Z., et al. (2022). Physics-informed machine learning: A review. *Applied Intelligence*.
Melnik, A., et al. (2023). Benchmarking physical reasoning in AI. *Frontiers in Artificial Intelligence*.
de la Torre-López, J., et al. (2023). AI for systematic literature reviews: A survey. *Scientometrics*.
Mahligawati, F., et al. (2023). AI in physics education: A review. *Education and Information Technologies*.
Chang, J., et al. (2023). AI-enabled attacks and countermeasures in physical layer systems. *IEEE Communications Surveys and Tutorials*.
Liu, Y., et al. (2024). Embodied AI toward AGI: A survey. *IEEE Transactions on Cognitive and Developmental Systems*.
Jiao, L., et al. (2024). AI-physics connections: A survey. *IEEE Access*.
Siam, S. I., et al. (2024). Artificial Intelligence of Things: A systematic review. *IEEE Internet of Things Journal*.
Liu, D., et al. (2025). Generative Physical AI in Vision. *ACM Computing Surveys*.
Dewi, R. S., et al. (2025). Physical AI: Concepts, taxonomy, and applications. *IEEE Transactions on Artificial Intelligence*.
Xiang, K., et al. (2025). Physics-grounded reasoning and embodied AI. *Nature Machine Intelligence*.
Long, X., et al. (2025). Embodied learning through simulators and world models. *Robotics and Autonomous Systems*.
Bousetouane, F., et al. (2025). Physical AI Agents: Architecture and Ph-RAG. *IEEE Robotics and Automation Magazine*.
Chen, X., et al. (2025). Acoustic world models in Physical AI. *IEEE Transactions on Multimedia*.
Varela, F. J., Thompson, E., & Rosch, E. (1991). *The Embodied Mind: Cognitive Science and Human Experience.* Cambridge, MA: MIT Press.
Clark, A. (1997). *Being There: Putting Brain, Body, and World Together Again.* Cambridge, MA: MIT Press.
Gibson, J. J. (1979). *The Ecological Approach to Visual Perception.* Boston, MA: Houghton Mifflin.
Brooks, R. A. (1991). Intelligence without representation. *Artificial Intelligence*, 47(1–3), 139–159.
Sutton, R. S., & Barto, A. G. (2018). *Reinforcement Learning: An Introduction* (2nd ed.). Cambridge, MA: MIT Press.
Spong, M. W., Hutchinson, S., & Vidyasagar, M. (2006). *Robot Modeling and Control.* Hoboken, NJ: Wiley.
Ashby, W. R. (1952). *Design for a Brain: The Origin of Adaptive Behavior.* London: Chapman and Hall.
Maturana, H. R., & Varela, F. J. (1980). *Autopoiesis and Cognition: The Realization of the Living.* Dordrecht: Reidel.
Greeno, J. G. (1998). The situativity of knowing, learning, and research. *American Psychologist*, 53(1), 5–26.
Suchman, L. A. (1987). *Plans and Situated Actions: The Problem of Human–Machine Communication.* Cambridge, UK: Cambridge University Press.
Dewi, R. S., Nakamura, K., & Lee, H. (2025). A systematic review of Physical Artificial Intelligence (PAI): Concepts, applications, and challenges. *Journal of Artificial Intelligence and Emerging Applications*, 5(1).
Iman Siam, S., Rahman, A., & Amin, M. I. (2024). Artificial Intelligence of Things (AIoT): A systematic review of architectures, sensing, and communication. *IEEE Internet of Things Journal*, 11(2).
Floridi, L., & Cowls, J. (2019). A unified framework of five principles for AI in society. *Harvard Data Science Review*, 1(1).
Agarwal, N., et al. (2025). Cosmos World Foundation Model Platform for Physical AI. *arXiv.org*.
Alhousseini, I., Chemissany, W., Kleit, F., & Nasrallah, A. (2019). Physicist’s journeys through the AI world – A topical review: There is no royal road to unsupervised learning. *arXiv.org*.
Angelis, D., Sofos, F., & Karakasidis, T. (2023). Artificial intelligence in physical sciences: Symbolic regression trends and perspectives. *Archives of Computational Methods in Engineering.*
Baccour, E., et al. (2021). Pervasive AI for IoT applications: A survey on resource-efficient distributed artificial intelligence. *IEEE Communications Surveys and Tutorials.*
Banerjee, C., Nguyen, K., Fookes, C., & Raissi, M. (2023). A survey on physics informed reinforcement learning: Review and open problems. *Expert Systems with Applications.*
Collins, J., Chand, S., Vanderkop, A., & Howard, D. (2021). A review of physics simulators for robotic applications. *IEEE Access.*
Farajtabar, M., & Charbonneau, M. (2024). The path towards contact-based physical human-robot interaction. *Robotics and Autonomous Systems.*
Maraita, M., Haddad, S., & Shaheen, S. (2025). Human-robot interaction: A state-of-the-art review and emerging trends. *East Journal of Engineering.*
Meng, S., Luo, Y., & Liu, P. (2024). Grounding creativity in physics: A brief survey of physical priors in AIGC. *International Joint Conference on Artificial Intelligence.*
Nguyen, K., Fernando, T., Fookes, C., & Sridharan, S. (2023). Physical adversarial attacks for surveillance: A survey. *IEEE Transactions on Neural Networks and Learning Systems.*
Singh, R., & Gill, S. (2023). Edge AI: A survey. *Internet of Things and Cyber-Physical Systems.*
Sipola, T., Alatalo, J., Kokkonen, T., & Rantonen, M. (2022). Artificial intelligence in the IoT era: A review of edge AI hardware and software. *Conference of the Open Innovations Association.*
Sumner, J., Lim, H. W., Chong, L. S., Bundele, A., Mukhopadhyay, A., & Kayambu, G. (2023). Artificial intelligence in physical rehabilitation: A systematic review. *Artificial Intelligence in Medicine.*
Wang, D., Yao, W., Jiang, T., Tang, G., & Chen, X. (2022). A survey on physical adversarial attack in computer vision. *arXiv.org.*
Wang, W., Ren, W., Li, M., & Chu, P. (2024). A survey on the use of intelligent physical service robots for elderly or disabled bedridden people at home. *International Journal of Crowd Science.*
Wei, H., et al. (2022). Physical adversarial attack meets computer vision: A decade survey. *IEEE Transactions on Pattern Analysis and Machine Intelligence.*
Wong, L. H. K., Kang, X., Bai, K., & Zhang, J. (2025). A survey of robotic navigation and manipulation with physics simulators in the era of embodied AI. *arXiv.org.*
Xing, W., Li, M., Li, M., & Han, M. (2025). Towards robust and secure embodied AI: A survey on vulnerabilities and attacks. *arXiv.org.*
Ye, N., et al. (2024). Artificial intelligence for wireless physical-layer technologies (AI4PHY): A comprehensive survey. *IEEE Transactions on Cognitive Communications and Networking.*
Yifan, C., et al. (2025). Embodied AI: A survey on the evolution from perceptive to behavioral intelligence. *SmartBot.*
Salehi, V. (2025). Integration of Munich Agile Concept for MBSE in an industrial context for future centralized car server architectures. *Proceedings of the ICIEA EU Conference*, Munich University of Applied Sciences, Germany.
Salehi, V. (2024). Application of Munich Agile Concept for MBSE for a holistic approach to collect vehicle data based on board diagnostic system. *Proceedings of the 44th Computers and Information in Engineering Conference (CIE)*, 2B. [https://doi.org/10.1115/DETC2024-141089](https://doi.org/10.1115/DETC2024-141089)
Salehi, V. (2023). Application of Munich Agile Concept for MBSE-based development of automated guided robot based on digital twin-data. *Proceedings of the 43rd Computers and Information in Engineering Conference (CIE)*, 2. [https://doi.org/10.1115/DETC2023-110983](https://doi.org/10.1115/DETC2023-110983)
Salehi, V., & Wang, S. (2021). Application of Munich agile concepts for MBSE as a holistic and systematic design of urban air mobility in case of design of vertiports and vertistops. *Proceedings of the Design Society.* [https://doi.org/10.1017/pds.2021.50](https://doi.org/10.1017/pds.2021.50)
Salehi, V. (2021). Integration of blockchain technology in systems engineering and software engineering in an industrial context. *Proceedings of the Design Society.* [https://doi.org/10.1017/pds.2021.450](https://doi.org/10.1017/pds.2021.450)
Salehi, V., & Taha, J., Wang, S. (2020). Application of Munich Agile Concept for MBSE by means of automated valet parking functions and the 3D environment-data. *ASME Design Engineering Technical Conference.* [https://doi.org/10.1115/DETC2020-22040](https://doi.org/10.1115/DETC2020-22040)
Salehi, V., & Wang, S. (2019). Munich Agile MBSE concept (MAGIC). *Proceedings of the International Conference on Engineering Design (ICED).* [https://doi.org/10.1017/dsi.2019.377](https://doi.org/10.1017/dsi.2019.377)
Salehi, V. (2019). Development of an agile concept for MBSE for future digital products through the entire life cycle management called Munich Agile MBSE Concept (MAGIC). *Computer-Aided Design and Applications*, 17(1), 147–166. [https://doi.org/10.14733/cadaps.2020.147-166](https://doi.org/10.14733/cadaps.2020.147-166)