Embodied.cpp: Portable Embodied AI Inference Runtime for Heterogeneous Robots

SEU-PAISys · hf · 2026-07-06

Southeast University introduced Embodied.cpp, a portable C++ inference runtime designed for the efficient deployment of embodied AI models (such as Vision-Language-Action and World-Action models) on heterogeneous edge devices. Utilizing a modular execution layer architecture, the project supports unified deployment across various robot platforms and features specialized optimizations for edge-side inference. It aims to lower the barrier to deploying embodied intelligence models like VLA on physical robot hardware, driving the transition of embodied AI from the lab to real-world applications.

Original post →

More from Embodied

Embodied channel →