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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In this paper, we develop a modular neural network for real-time semanticmapping in uncertain environments, which explicitly updates per-voxelprobabilistic distributions within a neural network layer. Our approachcombines the reliability of classical probabilistic algorithms with theperformance and efficiency of modern neural networks. Although roboticperception is often divided between modern differentiable methods and classicalexplicit methods, a union of both is necessary for real-time and trustworthyperformance. We introduce a novel Convolutional Bayesian Kernel Inference(ConvBKI) layer which incorporates semantic segmentation predictions onlineinto a 3D map through a depthwise convolution layer by leveraging conjugatepriors. We compare ConvBKI against state-of-the-art deep learning approachesand probabilistic algorithms for mapping to evaluate reliability andperformance. We also create a Robot Operating System (ROS) package of ConvBKIand test it on real-world perceptually challenging off-road driving data.

ConvBKI: Real-Time Probabilistic Semantic Mapping Network with Quantifiable Uncertainty