研究人员推出了一款名为DSP-SLAM++的统一框架，旨在改进面向对象的同步定位与地图构建（SLAM）系统。该新框架解决了实时性能、多类别对象支持和高保真对象模型生成之间的权衡问题。DSP-SLAM++通过异步建图管线和针对单目鱼眼-激光雷达设置的专用传感器融合，实现了高达70%的处理延迟降低，并支持实际的现实世界应用。 AI
影响 SLAM系统的这些进步可以提高自主系统和机器人的感知和导航能力。
排序理由 该集群包含两篇提交至arXiv的详细介绍新SLAM框架的独立研究论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 5 个来源。 我们如何撰写摘要 →
Existing object-aware SLAM systems force a trade-off between real-time performance, multi-class support, and the generation of high-fidelity, semantically coherent object models. To address this trade-off, we present DSP-SLAM++, which extends the DSP-SLAM framework with an asynch…
arXiv:2606.25953v1 Announce Type: cross Abstract: Existing object-aware SLAM systems force a trade-off between real-time performance, multi-class support, and the generation of high-fidelity, semantically coherent object models. To address this trade-off, we present DSP-SLAM++, w…
arXiv:2606.26046v1 Announce Type: cross Abstract: We present RoboAtlas, a contextual Active SLAM framework that adaptively balances geometric exploration and semantic reasoning using a scalable 3D semantic mapping system, OpenRoboVox. RoboAtlas integrates frontier exploration, gl…
We present RoboAtlas, a contextual Active SLAM framework that adaptively balances geometric exploration and semantic reasoning using a scalable 3D semantic mapping system, OpenRoboVox. RoboAtlas integrates frontier exploration, global semantic-map reasoning, and egocentric VLM-ba…
Existing object-aware SLAM systems force a trade-off between real-time performance, multi-class support, and the generation of high-fidelity, semantically coherent object models. To address this trade-off, we present DSP-SLAM++, which extends the DSP-SLAM framework with an asynch…