Due to deeply intertwined physical and hardware/software components together with an increasing number of interconnected heterogeneous devices powered by artificial intelligence (AI) techniques, the design complexity of cyber–physical systems (CPSs) becomes skyrocketing. Model-driven engineering (MDE) methods have been proven to be effective in increasing the productivity of CPS design. However, there is still a lack of MDE approaches that enable design space exploration as well as the code generation for the design of Artificial Intelligence of Things (AIoT)-based CPSs. To mitigate the situation, this article presents a unified modeling language named AIoTML for AIoT-based CPSs, which enables the construction of AI-based components across different modeling levels for the purposes of intelligent sensing and control. By extending the constructs of state-of-the-art domain-specific language (DSL) ThingML, AIoTML can seamlessly unify the modeling of both autonomous executions of AIoT devices and their surrounding physical environment, which facilitates both platform-independent simulation and control optimization for platform-specific CPSs. The compiler developed for AIoTML provides a family of code generators to support the construction of digital twins on various heterogeneous target AIoT platforms. Comprehensive evaluations on two complex real-world designs demonstrate the effectiveness of our AIoTML approach in the fast development of AIoT-based CPSs with high control quality.