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

Robotic grasping plays an important role in the field of robotics. Thecurrent state-of-the-art robotic grasping detection systems are usually builton the conventional vision, such as RGB-D camera. Compared to traditionalframe-based computer vision, neuromorphic vision is a small and young communityof research. Currently, there are limited event-based datasets due to thetroublesome annotation of the asynchronous event stream. Annotating large scalevision dataset often takes lots of computation resources, especially thetroublesome data for video-level annotation. In this work, we consider theproblem of detecting robotic grasps in a moving camera view of a scenecontaining objects. To obtain more agile robotic perception, a neuromorphicvision sensor (DAVIS) attaching to the robot gripper is introduced to explorethe potential usage in grasping detection. We construct a robotic graspingdataset named Event-Stream Dataset with 91 objects. A spatio-temporal mixedparticle filter (SMP Filter) is proposed to track the led-based grasprectangles which enables video-level annotation of a single grasp rectangle perobject. As leds blink at high frequency, the Event-Stream dataset is annotatedin a high frequency of 1 kHz. Based on the Event-Stream dataset, we develop adeep neural network for grasping detection which consider the angle learningproblem as classification instead of regression. The method performs highdetection accuracy on our Event-Stream dataset with 93% precision atobject-wise level. This work provides a large-scale and well-annotated dataset,and promotes the neuromorphic vision applications in agile robot.

Event-based Robotic Grasping Detection with Neuromorphic Vision Sensor and Event-Stream Dataset