[2512.10394] RoboNeuron: A Middle-Layer Infrastructure for Agent-Driven Orchestration in Embodied AI

Computer Science > Robotics arXiv:2512.10394 (cs) [Submitted on 11 Dec 2025 (v1), last revised 1 Apr 2026 (this version, v2)] Title:RoboNeuron: A Middle-Layer Infrastructure for Agent-Driven Orchestration in Embodied AI Authors:Weifan Guan, Qinghao Hu, Huasen Xi, Chenxiao Zhang, Aosheng Li, Jian Cheng View a PDF of the paper titled RoboNeuron: A Middle-Layer Infrastructure for Agent-Driven Orchestration in Embodied AI, by Weifan Guan and 5 other authors View PDF HTML (experimental) Abstract:Vision-language-action (VLA) models and LLM agents have advanced rapidly, yet reliable deployment on physical robots is often hindered by an interface mismatch between agent tool APIs and robot middleware. Current implementations typically rely on ad-hoc wrappers that are difficult to reuse, and changes to the VLA backend or serving stack often necessitate extensive re-integration. We introduce RoboNeuron, a middleware layer that connects the Model Context Protocol (MCP) for LLM agents with robot middleware such as ROS2. RoboNeuron bridges these ecosystems by deriving agent-callable tools directly from ROS schemas, providing a unified execution abstraction that supports both direct commands and modular composition, and localizing backend, runtime, and acceleration-preset changes within a stable inference boundary. We evaluate RoboNeuron in simulation and on hardware through multi-platform base control, arm motion, and VLA-based grasping tasks, demonstrating that it enables modular syste...