EUVIMEDEUVIMED entdecken
Crossref

From Scenarios Engineering to Scenarios Intelligence: Microworld Models for Embodied AI Based on Parallel Intelligence

Yonglin Tian, Yutong Wang, Yin Zhu, Xuan Li, Xinyuan Zhang, Shixing Li, Hongmei Zhang, Yunzhe Wang, Yong Zhang, Qiang Li, Fei-Yue Wang

IEEE Transactions on Systems, Man, and Cybernetics: Systems · 2026-01 · 56 (1) · 32-45

DOI: 10.1109/tsmc.2025.3618120 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2026-01. Verfasst von Yonglin Tian und 10 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 86 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Beijing Natural Science Foundation-Fengtai Rail Transit Frontier Research Joint Fund, Young Elite Scientists Sponsorship Program of China Association of Science and Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Discrete data-based learning approaches have facilitated the wide applications of AI models, especially the notably favored foundation models. However, simply scaling the diversity and quantity of training data is still inadequate to achieve human-like thinking and action competency. A shift of learning paradigm from spatially–temporally discrete, weakly correlated, and noninteractive samples to spatially–temporally continuous, strongly correlated, and interactive scenarios is expected to go beyond the element-level understanding and promote the relation, trend, as well as situation awareness abilities of AI models. This article systematically structures the methodology of scenarios engineering (SE) and proposes a three-layer SE roadmap consisting of the scenarios development layer, scenarios organization layer, and scenarios cognition layer. This roadmap is designed to foster the flexible and efficient construction, organization, and utilization of scenarios. Building on this foundation and parallel intelligence, we introduce the framework of scenarios intelligence (SI) that leverages scenarios as next-generation data resources and microworld models to cultivate embodied AI agents, facilitating the development of descriptive, predictive, and prescriptive intelligence in tasks like perception, decision-making, and action. Experiments are conducted with unmanned aerial vehicles (UAVs) to illustrate the effectiveness of the proposed method in environmental understanding, risk assessment, and active perception.

Förderung

  • National Natural Science Foundation of China
  • Beijing Natural Science Foundation-Fengtai Rail Transit Frontier Research Joint Fund
  • Young Elite Scientists Sponsorship Program of China Association of Science and Technology
  • Science and Technology Development Fund of Macau SAR

Zitieren

APA

Tian, Y., Wang, Y., Zhu, Y., Li, X., Zhang, X., Li, S., Zhang, H., Wang, Y., Zhang, Y., Li, Q., & Wang, F. (2026). From Scenarios Engineering to Scenarios Intelligence: Microworld Models for Embodied AI Based on Parallel Intelligence. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 56(1), 32-45. https://doi.org/10.1109/tsmc.2025.3618120

Vancouver

Tian Y, Wang Y, Zhu Y, Li X, Zhang X, Li S, et al. From Scenarios Engineering to Scenarios Intelligence: Microworld Models for Embodied AI Based on Parallel Intelligence. IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2026;56(1):32-45. doi:10.1109/tsmc.2025.3618120

BibTeX
@article{Tian2026,
  author = {Tian, Yonglin and Wang, Yutong and Zhu, Yin and Li, Xuan and Zhang, Xinyuan and Li, Shixing and Zhang, Hongmei and Wang, Yunzhe and Zhang, Yong and Li, Qiang and Wang, Fei-Yue},
  title = {From Scenarios Engineering to Scenarios Intelligence: Microworld Models for Embodied AI Based on Parallel Intelligence},
  journal = {IEEE Transactions on Systems, Man, and Cybernetics: Systems},
  year = {2026},
  volume = {56},
  number = {1},
  pages = {32--45},
  doi = {10.1109/tsmc.2025.3618120}
}
Kostenlos starten →