English(EN) DobotTrack: Target-Grounded Vision-Language-Action Learning for Embodied Person Tracking

DobotTrack框架通过语言指导增强具身人员追踪能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-09 05:00

研究人员开发了DobotTrack，一个用于具身人员追踪的新框架，该框架利用语言指导来帮助移动代理识别和跟随目标。该系统集成了辅助地面监督和时间建模，采用人员分割和边界框地面等任务来改进目标识别。DobotTrack的Q-identity模块能有效地保留历史令牌中的关键外观和空间特征，从而构建了一个0.8B参数的模型，在EVT-Bench上取得了77.9%的成功率，比之前的方法提高了16个百分点以上。 AI

影响增强了需要精确物体识别和追踪的任务的具身AI能力。

排序理由该项目是一篇研究论文，详细介绍了一个新的具身人员追踪框架。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该项目是一篇研究论文，详细介绍了一个新的具身人员追踪框架。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Shengjun Deng, Yinghan Zhang, Chengrui Wei, Liu Liang, Songyuan Liu, Pengkun Zheng, Yajun Zheng, Ying Zhang, Yuan Tian, Xi Li, Teng Wang · 2026-11-09 05:00

DobotTrack：基于目标的视觉-语言-动作学习，用于具身人员跟踪

arXiv:2611.09041v1 Announce Type: cross Abstract: Language-guided embodied person tracking requires a mobile agent to identify a target from a referring description and consistently follow the target under egocentric observations. We present DobotTrack, a target-grounded vision-l…

本文如何被排名

报道来源 [1]

DobotTrack：基于目标的视觉-语言-动作学习，用于具身人员跟踪

相关实体

相关话题