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 autonomous navigation of mobile robots, sensors suffer from massiveocclusion in cluttered environments, leaving significant amount of spaceunknown during planning. In practice, treating the unknown space in optimisticor pessimistic ways both set limitations on planning performance, thusaggressiveness and safety cannot be satisfied at the same time. However, humanscan infer the exact shape of the obstacles from only partial observation andgenerate non-conservative trajectories that avoid possible collisions inoccluded space. Mimicking human behavior, in this paper, we propose a methodbased on deep neural network to predict occupancy distribution of unknown spacereliably. Specifically, the proposed method utilizes contextual information ofenvironments and learns from prior knowledge to predict obstacle distributionsin occluded space. We use unlabeled and no-ground-truth data to train ournetwork and successfully apply it to real-time navigation in unseenenvironments without any refinement. Results show that our method leverages theperformance of a kinodynamic planner by improving security with no reduction ofspeed in clustered environments.

Learning-based 3D Occupancy Prediction for Autonomous Navigation in Occluded Environments