Pengying Wu, Mingye Jiang, Yunze Hu, Zhejia Wen, Kangjie Zhou, Zongru Yang, Zhe Peng, Chang Liu · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28476 · open-access PDF
对象目标导航(ObjectNav)需要一个体化代理来在未见的环境中找到一个特定类别的实例,并在其附近停下来。该代理通常依靠一个对象探测器,但必须从有限的自私的视频流中在线判断,有时是一个单一的框架,是否是一个被检测到的候选人是目标。探测器经常自信地错误类似的对象,如床上的沙发,而停止在一个虚假的阳性失败了事件。
Machine translation (Meta M2M100); the English original follows.
Object-goal navigation (ObjectNav) requires an embodied agent to find an instance of a specified category in an unseen environment and stop near it. The agent typically relies on an object detector but must judge online from a limited egocentric video stream, sometimes a single frame, whether a detected candidate is the target. Detectors often confidently mistake similar objects, such as a sofa for a bed, and stopping at a false positive fails the episode. Prevailing systems also approach candidates greedily, leaving them occluded or partially observed. We present CLOSER, an evidence-aware act
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28476, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange