具身开发者社区

外观

论文arXiv 2609.171681 个月前

HuMemSLAM：用于鲁棒视觉SLAM的高效人类启发式语义地点识别 ​

面向视觉SLAM地点识别的鲁棒与低延迟需求，提出受人类记忆启发的HuMem-VPR并集成ORB-SLAM3，在真实图像、CARLA和在线实验中验证。

AI 整理
  • 感知与导航
  • 数据与采集
  • 端侧部署

原文链接：HuMemSLAM: Efficient Human-Inspired Semantic Place Recognition for Robust Visual SLAM（arXiv 2609.17168 · 发布日期：2026-09-15）

HuMemSLAM: Efficient Human-Inspired Semantic Place Recognition for Robust Visual SLAM

面向视觉SLAM地点识别的鲁棒与低延迟需求，提出受人类记忆启发的HuMem-VPR并集成ORB-SLAM3，在真实图像、CARLA和在线实验中验证。

核心要点 ​

  • 传统几何视觉SLAM依赖低层特征和几何一致性，易受感知混淆与感知变化影响。
  • HuMem-VPR利用自底向上感知证据与自顶向下情境推理的双向关系，实现高层地点理解。
  • HuMemSLAM将HuMem-VPR集成到ORB-SLAM3，以改进SLAM系统中的地点识别流程。
  • HuMem-VPR在真实图像基准聚合检索精度最高，在CARLA上精度具竞争力且延迟低约二至三倍；HuMemSLAM提升集成Recall @1并减少几何后端候选。

验证范围与局限：验证范围包括真实图像基准、CARLA基准、所评估数据集族及在线实验。

英文摘要 (Abstract) ​

Autonomous systems require reliable place recognition for efficient and effective simultaneous localisation and mapping (SLAM). Traditional geometric visual SLAM approaches rely on low-level features and geometric consistency, but remain vulnerable to perceptual aliasing, where different places appear similar, and perceptual variation, where the same place appears different. Although semantic SLAM and modern learned visual place recognition (VPR) methods improve robustness under challenging perceptual conditions, real-time deployment requires both high retrieval accuracy and low latency. Inspired by human memory and perception, we propose HuMem-VPR, which exploits the bidirectional relationship between bottom-up perceptual evidence and top-down contextual reasoning to achieve high-level place understanding. We further introduce HuMemSLAM, the integration of HuMem-VPR with ORB-SLAM3. HuMem VPR achieved the highest aggregate retrieval accuracy on the real-image benchmark, competitive accuracy on the CARLA benchmark, and approximately two to three times lower latency than the evaluated state-of-the-art VPR methods. Across the evaluated dataset families and online experiments, HuMemSLAM substantially improved integrated Recall @1 over ORB-SLAM3's native retrieval while reducing the proposals submitted to its geometric backend.

作者：Mayowa Adebambo, Sebastian Donnelly, Armand Amaritei, Bradley, Andrew, Alexander D. Rast

来源

本页事实对应的公开页面，以原文为准。

  1. arXiv 2609.17168：HuMemSLAM: Efficient Human-Inspired Semantic Place Recognition for Robust Visual SLAM访问 2026-10-21