Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots

📄 arXiv: 2607.02501v1 📥 PDF

作者: Ling Xu, Chuyu Han, Borui Li, Hao Wu, Shiqi Jiang, Ting Cao, Chuanyou Li, Sheng Zhong, Shuai Wang

分类: cs.RO, cs.CV, cs.OS

发布日期: 2026-07-02

备注: 12 pages, 2 figures, Project website: https://github.com/SEU-PAISys/Embodied.cpp

💡 一句话要点

提出Embodied.cpp以解决异构机器人上嵌入式AI模型部署碎片化问题

🎯 匹配领域: 支柱九：具身大模型 (Embodied Foundation Models)

关键词: 嵌入式AI 推理运行时 异构机器人 多速率执行 延迟优先推理 模块化设计 视觉-语言-动作模型 世界-动作模型

📋 核心要点

  1. 现有的推理运行时无法满足嵌入式AI模型在异构设备上的高效部署需求，导致部署过程复杂且碎片化。
  2. 本文提出Embodied.cpp，一个基于C++的便携推理运行时，旨在提供模块化的多速率执行和延迟优先的推理支持。
  3. 实验结果显示，VLA模型的闭环执行成功率分别达到100%和91%，同时WAM基准测试内存占用显著降低，提升了部署效率。

📝 摘要（中文）

嵌入式AI模型涵盖视觉-语言-动作（VLA）模型和世界-动作模型（WAM），但实际部署在模型特定的Python栈、后端假设和机器人侧的粘合代码中仍然存在碎片化问题。现有的推理运行时主要设计用于请求-响应服务，无法满足嵌入式部署的运行时契约。本文提出了Embodied.cpp，一个便携的C++推理运行时，支持嵌入式模型的多速率执行、延迟优先的融合推理和可扩展的操作符及I/O支持，能够在异构设备、机器人和模拟器上实现统一的后端抽象。实验结果表明，Embodied.cpp在两个VLA模型上实现了高达100%和91%的任务成功率，并在WAM基准测试中显著减少了内存占用。

🔬 方法详解

问题定义：本文旨在解决嵌入式AI模型在异构机器人上的部署碎片化问题。现有方法主要依赖于特定的Python栈和后端假设，无法满足多速率执行和延迟优先的需求。

核心思路：提出Embodied.cpp作为一个便携的C++推理运行时，通过模块化设计实现多速率执行和可扩展的操作符支持，以适应不同的硬件和机器人平台。

技术框架：Embodied.cpp的架构分为五个层次：输入适配器、序列构建器、主干执行、头插件和部署适配器。这种分层结构使得不同功能模块可以独立开发和优化。

关键创新：Embodied.cpp的主要创新在于其模块化的多速率执行和延迟优先的推理机制，允许在异构设备上高效运行，区别于传统的请求-响应服务模型。

关键设计：在设计中，Embodied.cpp支持可扩展的操作符和I/O接口，允许用户根据具体需求进行定制，同时优化了内存使用，确保在不同模型和硬件上的高效执行。

🖼️ 关键图片

fig_0
fig_1

📊 实验亮点

在实验中，VLA模型的闭环执行成功率分别达到100%和91%，显示出Embodied.cpp在实际应用中的高效性。同时，WAM基准测试中内存占用从312.2 MiB降低至88.1 MiB，显著提升了资源利用率。

🎯 应用场景

Embodied.cpp可广泛应用于机器人、自动驾驶、智能家居等领域，能够提升嵌入式AI模型的部署效率和灵活性。其模块化设计使得开发者能够快速适应不同硬件平台，推动智能设备的普及与应用。

📄 摘要（原文）

Embodied AI models now span vision-language-action (VLA) models and world-action models (WAMs), but practical deployment remains fragmented across model-specific Python stacks, backend assumptions, and robot-side glue code, especially on heterogeneous edge devices. Existing inference runtimes are designed mainly for request-response serving and therefore do not satisfy the runtime contract of embodied deployment: multi-rate execution inside closed-loop control, latency-first batch-1 inference on heterogeneous hardware, and extensible embodied interfaces beyond fixed token I/O. We present Embodied.cpp, a portable C++ inference runtime for embodied models. Based on an architectural analysis of representative VLA models and WAMs, Embodied.cpp captures a shared execution path and organizes it into five layers: input adapters, sequence builders, backbone execution, head plugins, and deployment adapters. The runtime provides modular multi-rate execution, latency-first fused inference, and extensible operator and I/O support, enabling deployment across heterogeneous devices, robots, and simulators through one backend abstraction. We evaluate Embodied.cpp on two VLA models, HY-VLA and pi0.5, and on a preliminary WAM benchmark using a LingBot-VA Transformer block. The VLA deployments achieve successful closed-loop execution with 100.0% and 91.0% task success rates, respectively. The WAM benchmark reduces block memory from 312.2 MiB to 88.1 MiB. These results show that Embodied.cpp improves deployment efficiency while preserving high accuracy across diverse embodied model architectures.