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 propose a new 6-DoF grasp pose synthesis approach from 2D/2.5D input basedon keypoints. Keypoint-based grasp detector from image input has demonstratedpromising results in the previous study, where the additional visualinformation provided by color images compensates for the noisy depthperception. However, it relies heavily on accurately predicting the location ofkeypoints in the image space. In this paper, we devise a new grasp generationnetwork that reduces the dependency on precise keypoint estimation. Given anRGB-D input, our network estimates both the grasp pose from keypoint detectionas well as scale towards the camera. We further re-design the keypoint outputspace in order to mitigate the negative impact of keypoint prediction noise toPerspective-n-Point (PnP) algorithm. Experiments show that the proposed methodoutperforms the baseline by a large margin, validating the efficacy of ourapproach. Finally, despite trained on simple synthetic objects, our methoddemonstrate sim-to-real capacity by showing competitive results in real-worldrobot experiments.

KGNv2: Separating Scale and Pose Prediction for Keypoint-based 6-DoF Grasp Synthesis on RGB-D input