all AI news
Out of Sight, Still in Mind: Reasoning and Planning about Unobserved Objects with Video Tracking Enabled Memory Models
March 11, 2024, 4:42 a.m. | Yixuan Huang, Jialin Yuan, Chanho Kim, Pupul Pradhan, Bryan Chen, Li Fuxin, Tucker Hermans
cs.LG updates on arXiv.org arxiv.org
Abstract: Robots need to have a memory of previously observed, but currently occluded objects to work reliably in realistic environments. We investigate the problem of encoding object-oriented memory into a multi-object manipulation reasoning and planning framework. We propose DOOM and LOOM, which leverage transformer relational dynamics to encode the history of trajectories given partial-view point clouds and an object discovery and tracking engine. Our approaches can perform multiple challenging tasks including reasoning with occluded objects, novel …
abstract arxiv cs.ai cs.cv cs.lg cs.ro encoding environments framework manipulation memory mind object object-oriented objects planning reasoning robots tracking type video work
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Director, Clinical Data Science
@ Aura | Remote USA
Research Scientist, AI (PhD)
@ Meta | Menlo Park, CA | New York City