APEX: Unsupervised, object-centric scene segmentation and tracking for robot manipulation

Recent advances in unsupervised learning for object detection, segmentation, and tracking hold significant promise for applications in robotics. A common approach is to frame these tasks as inference in probabilistic latent-variable models. In this paper, however, we show that the current state-of-t...

詳細記述

書誌詳細
主要な著者: Wu, Y, Jones, OP, Engelcke, M, Posner, I
フォーマット: Conference item
言語:English
出版事項: Institute of Electrical and Electronics Engineers 2021