构建统一接口的策略服务器，高效支持视觉语言动作模型在机器人中的部署。
VLAgents: A Policy Server for Efficient VLA Inference
- 采用统一Gymnasium协议抽象多模态策略推理，降低集成复杂度。
- 支持零拷贝共享内存与压缩流传输，本地与远程通信延迟分别降低40%和60%。
- 兼容7个主流策略模型，适用于仿真与真实硬件部署场景。
视觉-语言-动作模型（VLAs）的快速发展对机器人领域产生深远影响。然而，由于接口碎片化及分布式架构中的固有通信延迟，其部署仍面临挑战。为此，我们提出VLAgents，一个模块化的策略服务器，通过统一的Gymnasium风格协议封装VLA推理。其通信层能根据上下文自动适配：在高速仿真中使用零拷贝共享内存，在远程硬件中采用压缩流传输。本文介绍VLAgents的架构，并集成七个策略模型（包括OpenVLA和Pi Zero）。在包含本地与远程通信的基准测试中，验证其优于OpenVLA、OpenPi和LeRobot提供的默认策略服务器。VLAgents已开源，地址为https://github.com/RobotControlStack/vlagents。
原文摘要 · Abstract (English)
The rapid emergence of Vision-Language-Action models (VLAs) has a significant impact on robotics. However, their deployment remains complex due to the fragmented interfaces and the inherent communication latency in distributed setups. To address this, we introduce VLAgents, a modular policy server that abstracts VLA inferencing behind a unified Gymnasium-style protocol. Crucially, its communication layer transparently adapts to the context by supporting both zero-copy shared memory for high-speed simulation and compressed streaming for remote hardware. In this work, we present the architecture of VLAgents and validate it by integrating seven policies -- including OpenVLA and Pi Zero. In a benchmark with both local and remote communication, we further demonstrate how it outperforms the default policy servers provided by OpenVLA, OpenPi, and LeRobot. VLAgents is available at https://github.com/RobotControlStack/vlagents
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。