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

A new generation of automated bin picking systems using deep learning isevolving to support increasing demand for e-commerce. To accommodate a widevariety of products, many automated systems include multiple gripper typesand/or tool changers. However, for some objects, sequential grasp failures arecommon: when a computed grasp fails to lift and remove the object, the bin isoften left unchanged; as the sensor input is consistent, the system retries thesame grasp over and over, resulting in a significant reduction in meansuccessful picks per hour (MPPH). Based on an empirical study of sequentialfailures, we characterize a class of "sequential failure objects" (SFOs) --objects prone to sequential failures based on a novel taxonomy. We then proposethree non-Markov picking policies that incorporate memory of past failures tomodify subsequent actions. Simulation experiments on SFO models and the EGADdataset suggest that the non-Markov policies significantly outperform theMarkov policy in terms of the sequential failure rate and MPPH. In physicalexperiments on 50 heaps of 12 SFOs the most effective Non-Markov policyincreased MPPH over the Dex-Net Markov policy by 107%.

Non-Markov Policies to Reduce Sequential Failures in Robot Bin Picking