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

The ability to leverage heterogeneous robotic experience from differentrobots and tasks to quickly master novel skills and embodiments has thepotential to transform robot learning. Inspired by recent advances infoundation models for vision and language, we propose a multi-embodiment,multi-task generalist agent for robotic manipulation. This agent, namedRoboCat, is a visual goal-conditioned decision transformer capable of consumingaction-labelled visual experience. This data spans a large repertoire of motorcontrol skills from simulated and real robotic arms with varying sets ofobservations and actions. With RoboCat, we demonstrate the ability togeneralise to new tasks and robots, both zero-shot as well as throughadaptation using only 100-1000 examples for the target task. We also show how atrained model itself can be used to generate data for subsequent trainingiterations, thus providing a basic building block for an autonomous improvementloop. We investigate the agent's capabilities, with large-scale evaluationsboth in simulation and on three different real robot embodiments. We find thatas we grow and diversify its training data, RoboCat not only shows signs ofcross-task transfer, but also becomes more efficient at adapting to new tasks.

RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation