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

When robots work in a cluttered environment, the constraints for motionschange frequently and the required action can change even for the same task.However, planning complex motions from direct calculation has the risk ofresulting in poor performance local optima. In addition, machine learningapproaches often require relearning for novel situations. In this paper, wepropose a method of searching appropriate motions by using conditionalGenerative Adversarial Networks (cGANs), which can generate motions based onthe conditions by mimicking training datasets. By training cGANs with variousmotions for a task, its latent space is fulfilled with the valid motions forthe task. The appropriate motions can be found efficiently by searching thelatent space of the trained cGANs instead of the motion space, while avoidingpoor local optima. We demonstrate that the proposed method successfully worksfor an object-throwing task to given target positions in both numericalsimulation and real-robot experiments. The proposed method resulted in threetimes higher accuracy with 2.5 times faster calculation time than searching theaction space directly.

Motion Generation Considering Situation with Conditional Generative Adversarial Networks for Throwing Robots