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 present a novel approach for image-goal navigation, where an agentnavigates with a goal image rather than accurate target information, which ismore challenging. Our goal is to decouple the learning of navigation goalplanning, collision avoidance, and navigation ending prediction, which enablesmore concentrated learning of each part. This is realized by four differentmodules. The first module maintains an obstacle map during robot navigation.The second predicts a long-term goal on the real-time map periodically, whichcan thus convert an image-goal navigation task to several point-goal navigationtasks. To achieve these point-goal navigation tasks, the third module planscollision-free command sets for navigating to these long-term goals. The finalmodule stops the robot properly near the goal image. The four modules aredesigned or maintained separately, which helps cut down the search time duringnavigation and improves the generalization to previously unseen real scenes. Weevaluate the method in both a simulator and in the real world with a mobilerobot. The results in real complex environments show that our method attains atleast a $17\%$ increase in navigation success rate and a $23\%$ decrease innavigation collision rate over some state-of-the-art models.

Image-Goal Navigation in Complex Environments via Modular Learning