研究人员开发了 Jetson-PI，这是一种用于在 NVIDIA Jetson Orin 等低功耗板载设备上部署视觉-语言-动作 (VLA) 模型的新颖方法。该方法解决了 VLA 模型固有的高计算复杂度、推理延迟和控制频率的挑战。Jetson-PI 采用前瞻性对齐的异步校正技术来改善感知-执行对齐并减少反应时间，在基准测试中实现了控制频率和成功率的显著提升。 AI
影响 使边缘设备上的 AI 功能更加强大，可能带来更复杂的实时机器人应用。
排序理由 该集群包含一篇详细介绍 AI 模型部署新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2607.12659v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have achieved impressive performance on diverse embodied tasks. However, deploying VLA models on low-power onboard devices, such as the Jetson Orin, remains challenging due to their high computa…
Vision-Language-Action (VLA) models have achieved impressive performance on diverse embodied tasks. However, deploying VLA models on low-power onboard devices, such as the Jetson Orin, remains challenging due to their high computational complexity, which leads to substantial infe…