小模型实现高效机器人控制，支持单卡训练和消费级设备部署。
SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
- 用轻量架构+社区数据训练，仅需单张显卡
- 在仿真与真实场景中性能媲美大10倍的模型
- 异步推理设计提升响应速度，适合边缘设备
视觉语言模型（VLM）在大规模多模态数据上预训练，蕴含丰富的视觉与语言知识，是机器人领域的强大基础。近期方法将VLM转化为视觉-语言-动作（VLA）模型，实现自然语言驱动的感知与控制。然而，现有VLA通常规模巨大，参数达数十亿，导致训练成本高、实际部署困难。且依赖学术与工业数据集，忽视了低成本机器人平台产生的社区数据。本文提出SmolVLA，一种小型、高效、基于社区数据的VLA，显著降低训练与推理成本，可在单张GPU上训练，在消费级显卡甚至CPU上部署。为提升响应性，引入异步推理栈，将感知与动作预测与执行解耦，支持分块动作生成以提高控制频率。尽管模型紧凑，其性能仍可比肩参数量大10倍的VLA。我们在多种仿真及真实机器人基准上评估SmolVLA，并开源全部代码、预训练模型与训练数据。
原文摘要 · Abstract (English)
Vision-language models (VLMs) pretrained on large-scale multimodal datasets encode rich visual and linguistic knowledge, making them a strong foundation for robotics. Rather than training robotic policies from scratch, recent approaches adapt VLMs into vision-language-action (VLA) models that enable natural language-driven perception and control. However, existing VLAs are typically massive--often with billions of parameters--leading to high training costs and limited real-world deployability. Moreover, they rely on academic and industrial datasets, overlooking the growing availability of community-collected data from affordable robotic platforms. In this work, we present SmolVLA, a small, efficient, and community-driven VLA that drastically reduces both training and inference costs, while retaining competitive performance. SmolVLA is designed to be trained on a single GPU and deployed on consumer-grade GPUs or even CPUs. To further improve responsiveness, we introduce an asynchronous inference stack decoupling perception and action prediction from action execution, allowing higher control rates with chunked action generation. Despite its compact size, SmolVLA achieves performance comparable to VLAs that are 10x larger. We evaluate SmolVLA on a range of both simulated as well as real-world robotic benchmarks and release all code, pretrained models, and training data.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。