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 study the problem of learning vision-based dynamicmanipulation skills using a scalable reinforcement learning approach. We studythis problem in the context of grasping, a longstanding challenge in roboticmanipulation. In contrast to static learning behaviors that choose a grasppoint and then execute the desired grasp, our method enables closed-loopvision-based control, whereby the robot continuously updates its grasp strategybased on the most recent observations to optimize long-horizon grasp success.To that end, we introduce QT-Opt, a scalable self-supervised vision-basedreinforcement learning framework that can leverage over 580k real-world graspattempts to train a deep neural network Q-function with over 1.2M parameters toperform closed-loop, real-world grasping that generalizes to 96% grasp successon unseen objects. Aside from attaining a very high success rate, our methodexhibits behaviors that are quite distinct from more standard grasping systems:using only RGB vision-based perception from an over-the-shoulder camera, ourmethod automatically learns regrasping strategies, probes objects to find themost effective grasps, learns to reposition objects and perform othernon-prehensile pre-grasp manipulations, and responds dynamically todisturbances and perturbations.

QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation