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

A key proficiency an autonomous mobile robot must have to perform high-leveltasks is a strong understanding of its environment. This involves informationabout what types of objects are present, where they are, what their spatialextend is, and how they can be reached, i.e., information about free space isalso crucial. Semantic maps are a powerful instrument providing suchinformation. However, applying semantic segmentation and building 3D maps withhigh spatial resolution is challenging given limited resources on mobilerobots. In this paper, we incorporate semantic information into efficientoccupancy normal distribution transform (NDT) maps to enable real-time semanticmapping on mobile robots. On the publicly available dataset Hypersim, we showthat, due to their sub-voxel accuracy, semantic NDT maps are superior to otherapproaches. We compare them to the recent state-of-the-art approach based onvoxels and semantic Bayesian spatial kernel inference~(S-BKI) and to anoptimized version of it derived in this paper. The proposed semantic NDT mapscan represent semantics to the same level of detail, while mapping is 2.7 to17.5 times faster. For the same grid resolution, they perform significantlybetter, while mapping is up to more than 5 times faster. Finally, we prove thereal-world applicability of semantic NDT maps with qualitative results in adomestic application.

Efficient and Robust Semantic Mapping for Indoor Environments