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

We introduce LOTUS, a continual imitation learning algorithm that empowers aphysical robot to continuously and efficiently learn to solve new manipulationtasks throughout its lifespan. The core idea behind LOTUS is constructing anever-growing skill library from a sequence of new tasks with a small number ofhuman demonstrations. LOTUS starts with a continual skill discovery processusing an open-vocabulary vision model, which extracts skills as recurringpatterns presented in unsegmented demonstrations. Continual skill discoveryupdates existing skills to avoid catastrophic forgetting of previous tasks andadds new skills to solve novel tasks. LOTUS trains a meta-controller thatflexibly composes various skills to tackle vision-based manipulation tasks inthe lifelong learning process. Our comprehensive experiments show that LOTUSoutperforms state-of-the-art baselines by over 11% in success rate, showing itssuperior knowledge transfer ability compared to prior methods. More results andvideos can be found on the project website:https://ut-austin-rpl.github.io/Lotus/.

LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discovery