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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Robot learning is often simplified to planar manipulation due to its dataconsumption. Then, a common approach is to use a fully-convolutional neuralnetwork to estimate the reward of grasp primitives. In this work, we extendthis approach by parametrizing the two remaining, lateral Degrees of Freedom(DoFs) of the primitives. We apply this principle to the task of 6 DoF binpicking: We introduce a model-based controller to calculate angles that avoidcollisions, maximize the grasp quality while keeping the uncertainty small. Asthe controller is integrated into the training, our hybrid approach is able tolearn about and exploit the model-based controller. After real-world trainingof 27000 grasp attempts, the robot is able to grasp known objects with asuccess rate of over 92% in dense clutter. Grasp inference takes less than50ms. In further real-world experiments, we evaluate grasp rates in a range ofscenarios including its ability to generalize to unknown objects. We show thatthe system is able to avoid collisions, enabling grasps that would not bepossible without primitive adaption.

Robot Learning of 6 DoF Grasping using Model-based Adaptive Primitives