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

We explore a novel method to perceive and manipulate 3D articulated objectsthat generalizes to enable a robot to articulate unseen classes of objects. Wepropose a vision-based system that learns to predict the potential motions ofthe parts of a variety of articulated objects to guide downstream motionplanning of the system to articulate the objects. To predict the objectmotions, we train a neural network to output a dense vector field representingthe point-wise motion direction of the points in the point cloud underarticulation. We then deploy an analytical motion planner based on this vectorfield to achieve a policy that yields maximum articulation. We train the visionsystem entirely in simulation, and we demonstrate the capability of our systemto generalize to unseen object instances and novel categories in bothsimulation and the real world, deploying our policy on a Sawyer robot with nofinetuning. Results show that our system achieves state-of-the-art performancein both simulated and real-world experiments.

FlowBot3D: Learning 3D Articulation Flow to Manipulate Articulated Objects