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

Object shape provides important information for robotic manipulation; forinstance, selecting an effective grasp depends on both the global and localshape of the object of interest, while reaching into clutter requires accuratesurface geometry to avoid unintended contact with the environment. Model-based3D object manipulation is a widely studied problem; however, obtaining theaccurate 3D object models for multiple objects often requires tedious work. Inthis letter, we exploit Gaussian process implicit surfaces (GPIS) extractedfrom RGB-D sensor data to grasp an unknown object. We propose areconstruction-aware trajectory optimization that makes use of the extractedGPIS model plan a motion to improve the ability to estimate the object's 3Dgeometry, while performing a pick-and-place action. We present a probabilisticapproach for a robot to autonomously learn and track the object, while achievethe manipulation task.  We use a sampling-based trajectory generation method to explore the unseenparts of the object using the estimated conditional entropy of the GPIS model.We validate our method with physical robot experiments across eleven differentobjects of varying shape from the YCB object dataset. Our experiments show thatour reconstruction-aware trajectory optimization provides higher-quality 3Dobject reconstruction when compared with directly solving the manipulation taskor using a heuristic to view unseen portions of the object.

Building 3D Object Models during Manipulation by Reconstruction-Aware Trajectory Optimization