From Scenarios Engineering to Scenarios Intelligence: Microworld Models for Embodied AI Based on Parallel Intelligence
本文提出从离散数据学习转向连续交互场景学习的范式，系统构建场景工程方法论，并基于平行智能提出场景智能框架，通过无人机实验验证其在环境理解、风险评估和主动感知中的有效性。
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.