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

6D robotic grasping beyond top-down bin-picking scenarios is a challengingtask. Previous solutions based on 6D grasp synthesis with robot motion planningusually operate in an open-loop setting, which are sensitive to grasp synthesiserrors. In this work, we propose a new method for learning closed-loop controlpolicies for 6D grasping. Our policy takes a segmented point cloud of an objectfrom an egocentric camera as input, and outputs continuous 6D control actionsof the robot gripper for grasping the object. We combine imitation learning andreinforcement learning and introduce a goal-auxiliary actor-critic algorithmfor policy learning. We demonstrate that our learned policy can be integratedinto a tabletop 6D grasping system and a human-robot handover system to improvethe grasping performance of unseen objects. Our videos and code can be found athttps://sites.google.com/view/gaddpg .

Goal-Auxiliary Actor-Critic for 6D Robotic Grasping with Point Clouds