首页|Reports from Peking University Highlight Recent Findings in Robotics and Automation (Doze: a Dataset for Open-vocabulary Zero-shot Object Navigation In Dynamic Environments)
Reports from Peking University Highlight Recent Findings in Robotics and Automation (Doze: a Dataset for Open-vocabulary Zero-shot Object Navigation In Dynamic Environments)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News – Fresh data on Robotics - Robotics and Automation are presented in a new report.According to news reporting out of Bei jing, People’s Republic of China, by NewsRx editors, researchstated, “Zero-Shot Object Navigation (ZSON) requires agents to autonomously locate and approach unseen objects in unfamiliar environments and has emerged as a particularly challe nging task within thedomain of Embodied AI. Existing datasets for developing ZS ON algorithms lack consideration of dynamicobstacles, object attribute diversit y, and scene texts, thus exhibiting noticeable discrepancies from realworldsit uations.”
BeijingPeople’s Republic of ChinaAsiaRobotics and AutomationRoboticsPeking University
NETL
NSTL
