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

Imitation learning from human demonstrations has shown impressive performancein robotics. However, most results focus on table-top manipulation, lacking themobility and dexterity necessary for generally useful tasks. In this work, wedevelop a system for imitating mobile manipulation tasks that are bimanual andrequire whole-body control. We first present Mobile ALOHA, a low-cost andwhole-body teleoperation system for data collection. It augments the ALOHAsystem with a mobile base, and a whole-body teleoperation interface. Using datacollected with Mobile ALOHA, we then perform supervised behavior cloning andfind that co-training with existing static ALOHA datasets boosts performance onmobile manipulation tasks. With 50 demonstrations for each task, co-trainingcan increase success rates by up to 90%, allowing Mobile ALOHA to autonomouslycomplete complex mobile manipulation tasks such as sauteing and serving a pieceof shrimp, opening a two-door wall cabinet to store heavy cooking pots, callingand entering an elevator, and lightly rinsing a used pan using a kitchenfaucet. Project website: https://mobile-aloha.github.io

Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation