研究人员开发了 ActionMap，这是一种新颖的体素热图动作头，旨在改进视觉-语言-动作 (VLA) 模型中的机器人策略学习。这个新的动作头取代了传统的动作解码器，在动作空间上预测热图，以更好地利用动作的几何邻近性。在模拟和真实世界测试中，ActionMap 与现有方法相比表现出更优越的性能和数据效率，表明动作表示是 VLA 模型有效性的关键因素。 AI
影响 ActionMap 改进的数据效率和性能有望加速 VLA 模型开发和机器人实际部署。
排序理由 该集群包含一篇详细介绍机器人策略学习新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.06904v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have advanced rapidly across backbones, training recipes, and data scale, yet the action decoder, which converts the backbone's hidden state into a continuous control signal, has barely changed …
Vision-language-action (VLA) models have advanced rapidly across backbones, training recipes, and data scale, yet the action decoder, which converts the backbone's hidden state into a continuous control signal, has barely changed and remains a single-point predictor across the ma…