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

Deploying robots in open-ended unstructured environments such as homes hasbeen a long-standing research problem. However, robots are often studied onlyin closed-off lab settings, and prior mobile manipulation work is restricted topick-move-place, which is arguably just the tip of the iceberg in this area. Inthis paper, we introduce Open-World Mobile Manipulation System, a full-stackapproach to tackle realistic articulated object operation, e.g. real-worlddoors, cabinets, drawers, and refrigerators in open-ended unstructuredenvironments. The robot utilizes an adaptive learning framework to initiallylearns from a small set of data through behavior cloning, followed by learningfrom online practice on novel objects that fall outside the trainingdistribution. We also develop a low-cost mobile manipulation hardware platformcapable of safe and autonomous online adaptation in unstructured environmentswith a cost of around 20,000 USD. In our experiments we utilize 20 articulateobjects across 4 buildings in the CMU campus. With less than an hour of onlinelearning for each object, the system is able to increase success rate from 50%of BC pre-training to 95% using online adaptation. Video results athttps://open-world-mobilemanip.github.io/

Adaptive Mobile Manipulation for Articulated Objects In the Open World