AI-IoT-Robotics Integration: Survey of Frameworks, Emerging Trends, and the Path Toward Connected Robotics

A comprehensive survey examines the convergence of AI, IoT, and robotics, identifying Small Language Models (SLMs) and Large Language Models (LLMs) as critical components for distributed cognition in edge and cloud environments. The research proposes unified design frameworks and modular architectures to address interoperability gaps, advancing the emerging field of Connected Robotics and Physical AI.

This survey represents a significant step toward systematizing the integration of three foundational technologies—AI, IoT, and robotics—that have largely developed in isolation. While pairwise combinations like AIoT and Internet of Robotic Things (IoRT) have matured, the absence of unified frameworks has hindered holistic system design. The research identifies SLMs and LLMs as enablers of distributed cognition, where computational tasks split between edge devices and cloud infrastructure based on latency, power, and accuracy requirements. This hybrid approach addresses a persistent bottleneck: how autonomous systems can make real-time decisions while leveraging sophisticated reasoning capabilities.

The broader context reflects growing industry recognition that next-generation robotics requires more than improved hardware or algorithms alone. Enterprises deploying autonomous systems face challenges around interoperability between disparate IoT platforms, feedback control mechanisms, and adaptive learning in dynamic environments. The survey's emphasis on modularity and interpretability directly addresses stakeholder concerns about system reliability and operational transparency in critical applications.

For developers and enterprises, the practical implications are substantial. A unified design framework reduces engineering overhead, accelerates time-to-market, and improves system reliability. Organizations investing in robotics, edge AI, or IoT infrastructure now have a conceptual roadmap for integration strategies. The focus on Connected Robotics—systems that share data and intelligence across networked agents—creates new opportunities for collaborative automation at scale.

The roadmap suggests continued investment in hybrid SLM-LLM architectures, standardized IoT protocols, and control systems that enable real-time adaptation. Watch for emerging open-source frameworks implementing these principles and enterprise deployments demonstrating measurable improvements in efficiency or cost reduction.

• →Unified AI-IoT-robotics frameworks remain absent despite decades of progress in pairwise technology combinations.
• →Hybrid SLM-LLM systems enable distributed cognition, splitting computation between edge devices and cloud infrastructure for optimal latency and reasoning.
• →Interoperability and feedback control gaps persist as major barriers to seamless integration across heterogeneous systems.
• →Modularity and interpretability are critical design principles for autonomous systems operating in dynamic, safety-critical environments.
• →Connected Robotics and Physical AI represent an emerging paradigm enabling networked, collaborative autonomous agents at scale.