EUVIMEDEUVIMED entdecken
Crossref

Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI

Kun Xiang, Terry Jingchen Zhang, Yinya Huang, Jixi He, Zirong Liu, Yueling Tang, Ruizhe Zhou, Lijing Luo, Youpeng Wen, Xiuwei Chen, Bingqian Lin, Jianhua Han und 4 weitere

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-10 · 48 (10) · 12938-12957

DOI: 10.1109/tpami.2026.3703038 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-10. Verfasst von Kun Xiang und 15 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 292 Literaturangaben. Gefördert von: Scientific Research Innovation Capability Support Project for Young Faculty, Shenzhen Science and Technology Program, General Embodied AI Center of Sun Yat-sen University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The convergence of embodied intelligence and world models has catalyzed growing interest in integrating physical laws into AI systems. While prior surveys have examined world models and embodied intelligence separately, we focus on the progression that connects these capabilities as a unified developmental pathway from passive observation to active physical comprehension. This survey provides a systematic framework revealing how physical AI advances through four interconnected stages: perception transforms sensory data into structured physical representations, reasoning derives explanations from observed phenomena, modeling enables predictive simulation grounded in physical principles, and embodied interaction closes the loop through physical manipulation and environmental feedback. Each stage enables and enhances the next: perceptual grounding supports causal reasoning, reasoning unlocks predictive capabilities, and robust models drive genuine physical interaction. Through analysis of developments spanning architectural innovations, training methodologies, causal inference, and embodied systems, we synthesize how physical understanding emerges through cumulative integration across this progression. Our framework reveals the evolution from isolated, task-specific solutions toward integrated architectures that advance from pattern recognition toward causal reasoning and counterfactual prediction. This perspective provides foundations for next-generation physical AI systems with direct implications for safe, generalizable, and interpretable deployment across robotics, scientific discovery, and autonomous systems.

Förderung

  • Scientific Research Innovation Capability Support Project for Young Faculty
  • Shenzhen Science and Technology Program
  • General Embodied AI Center of Sun Yat-sen University

Zitieren

APA

Xiang, K., Zhang, T. J., Huang, Y., He, J., Liu, Z., Tang, Y., Zhou, R., Luo, L., Wen, Y., Chen, X., Lin, B., Han, J., Xu, H., Li, H., Dong, B., & Liang, X. (2026). Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(10), 12938-12957. https://doi.org/10.1109/tpami.2026.3703038

Vancouver

Xiang K, Zhang TJ, Huang Y, He J, Liu Z, Tang Y, et al. Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(10):12938-12957. doi:10.1109/tpami.2026.3703038

BibTeX
@article{Xiang2026,
  author = {Xiang, Kun and Zhang, Terry Jingchen and Huang, Yinya and He, Jixi and Liu, Zirong and Tang, Yueling and Zhou, Ruizhe and Luo, Lijing and Wen, Youpeng and Chen, Xiuwei and Lin, Bingqian and Han, Jianhua and Xu, Hang and Li, Hanhui and Dong, Bin and Liang, Xiaodan},
  title = {Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {10},
  pages = {12938--12957},
  doi = {10.1109/tpami.2026.3703038}
}
Kostenlos starten →