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

In recent years, learning-based approaches have demonstrated significantpromise in addressing intricate navigation tasks. Traditional methods fortraining deep neural network navigation policies rely on meticulously designedreward functions or extensive teleoperation datasets as navigationdemonstrations. However, the former is often confined to simulatedenvironments, and the latter demands substantial human labor, making it atime-consuming process. Our vision is for robots to autonomously learnnavigation skills and adapt their behaviors to environmental changes withoutany human intervention. In this work, we discuss the self-supervised navigationproblem and present Dynamic Graph Memory (DGMem), which facilitates trainingonly with on-board observations. With the help of DGMem, agents can activelyexplore their surroundings, autonomously acquiring a comprehensive navigationpolicy in a data-efficient manner without external feedback. Our method isevaluated in photorealistic 3D indoor scenes, and empirical studies demonstratethe effectiveness of DGMem.

DGMem: Learning Visual Navigation Policy without Any Labels by Dynamic Graph Memory