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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Humans excel in grasping objects through diverse and robust policies, many ofwhich are so probabilistically rare that exploration-based learning methodshardly observe and learn. Inspired by the human learning process, we propose amethod to extract and exploit latent intents from demonstrations, and thenlearn diverse and robust grasping policies through self-exploration. Theresulting policy can grasp challenging objects in various environments with anoff-the-shelf parallel gripper. The key component is a learned intentionestimator, which maps gripper pose and visual sensory to a set of sub-intentscovering important phases of the grasping movement. Sub-intents can be used tobuild an intrinsic reward to guide policy learning. The learned policydemonstrates remarkable zero-shot generalization from simulation to the realworld while retaining its robustness against states that have never beenencountered during training, novel objects such as protractors and usermanuals, and environments such as the cluttered conveyor.

Learn to Grasp via Intention Discovery and its Application to Challenging Clutter