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

Deep learning-based robotic grasping has made significant progress thanks toalgorithmic improvements and increased data availability. However,state-of-the-art models are often trained on as few as hundreds or thousands ofunique object instances, and as a result generalization can be a challenge.  In this work, we explore a novel data generation pipeline for training a deepneural network to perform grasp planning that applies the idea of domainrandomization to object synthesis. We generate millions of unique, unrealisticprocedurally generated objects, and train a deep neural network to performgrasp planning on these objects.  Since the distribution of successful grasps for a given object can be highlymultimodal, we propose an autoregressive grasp planning model that maps sensorinputs of a scene to a probability distribution over possible grasps. Thismodel allows us to sample grasps efficiently at test time (or avoid samplingentirely).  We evaluate our model architecture and data generation pipeline in simulationand the real world. We find we can achieve a $>$90% success rate on previouslyunseen realistic objects at test time in simulation despite having only beentrained on random objects. We also demonstrate an 80% success rate onreal-world grasp attempts despite having only been trained on random simulatedobjects.

Domain Randomization and Generative Models for Robotic Grasping