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 describe a robotic learning system for autonomous exploration andnavigation in diverse, open-world environments. At the core of our method is alearned latent variable model of distances and actions, along with anon-parametric topological memory of images. We use an information bottleneckto regularize the learned policy, giving us (i) a compact visual representationof goals, (ii) improved generalization capabilities, and (iii) a mechanism forsampling feasible goals for exploration. Trained on a large offline dataset ofprior experience, the model acquires a representation of visual goals that isrobust to task-irrelevant distractors. We demonstrate our method on a mobileground robot in open-world exploration scenarios. Given an image of a goal thatis up to 80 meters away, our method leverages its representation to explore anddiscover the goal in under 20 minutes, even amidst previously-unseen obstaclesand weather conditions. Please check out the project website for videos of ourexperiments and information about the real-world dataset used athttps://sites.google.com/view/recon-robot.

Rapid Exploration for Open-World Navigation with Latent Goal Models