Newest papers

Industrial ReMEmbR: Scaling Spatiotemporal Memory to Robot Fleets

Jad Yammine, Malek Wahidi, Abrar Anwar, Yan Chang, Mihir Acharya, Anthony Rizk · 2026 · arXiv

DOI: 10.48550/arXiv.2610.28624 · open-access PDF

German

Warehouse-Roboterflotten beobachten kontinuierlich Betriebsbedingungen, aber diese Beobachtungen als wiederverwendbares semantisches Gedächtnis bewahren erhebliche Berechnungs-, Kommunikations- und Speicherkosten auf. Zum Beispiel kann die Erläuterung wiederkehrender Korridorblocks die Überprüfung von Videos von mehreren Robotern über mehrere Schichten erfordern. Wir präsentieren IndustrialRemembr, ein gemeinsames räumlich-zeitliches Speicher-System, das NVIDIA ReMEmbR auf Roboterflotten erweitert und Server-Seite-Computing reduziert, indem Szenenbeschreibungen nur auf Anfrage generiert werden.

Machine translation (Meta M2M100); the English original follows.

Abstract

Warehouse robot fleets continuously observe operational conditions, but preserving these observations as reusable semantic memory incurs substantial computation, communication, and storage costs. For example, explaining recurring aisle blockages can require reviewing video from multiple robots across several shifts. We present IndustrialRemembr, a shared spatiotemporal memory system that extends NVIDIA ReMEmbR to robot fleets and reduces server-side computation by generating scene descriptions only on demand. On each robot, an NVIDIA Jetson encodes video clips into retrieval embeddings with Co

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28624, 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.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange