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

In this paper, we propose a deep reinforcement learning (DRL) solution to thegrasping problem using 2.5D images as the only source of information. Inparticular, we developed a simulated environment where a robot equipped with avacuum gripper has the aim of reaching blocks with planar surfaces. Theseblocks can have different dimensions, shapes, position and orientation. Unity3D allowed us to simulate a real-world setup, where a depth camera is placed ina fixed position and the stream of images is used by our policy network tolearn how to solve the task. We explored different DRL algorithms and problemconfigurations. The experiments demonstrated the effectiveness of the proposedDRL algorithm applied to grasp tasks guided by visual depth camera inputs. Whenusing the proper policy, the proposed method estimates a robot toolconfiguration that reaches the object surface with negligible position andorientation errors. This is, to the best of our knowledge, the first successfulattempt of using 2.5D images only as of the input of a DRL algorithm, to solvethe grasping problem regressing 3D world coordinates.

Learning to Grasp from 2.5D images: a Deep Reinforcement Learning Approach