English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

To be useful in everyday environments, robots must be able to observe andlearn about objects. Recent datasets enable progress for classifying data intoknown object categories; however, it is unclear how to collect reliable objectdata when operating in cluttered, partially-observable environments. In thispaper, we address the problem of building complete 3D models for real-worldobjects using a robot platform, which can remove objects from clutter forbetter classification. Furthermore, we are able to learn entirely new objectcategories as they are encountered, enabling the robot to classify previouslyunidentifiable objects during future interactions. We build models of graspedobjects using simultaneous manipulation and observation, and we guide theprocessing of visual data using a kinematic description of the robot to combineobservations from different view-points and remove background noise. To testour framework, we use a mobile manipulation robot equipped with an RGBD camerato build voxelized representations of unknown objects and then classify theminto new categories. We then have the robot remove objects from clutter tomanipulate, observe, and classify them in real-time.

Kinematically-Informed Interactive Perception: Robot-Generated 3D Models for Classification