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 method for generating, predicting, and using SpatiotemporalOccupancy Grid Maps (SOGM), which embed future semantic information of realdynamic scenes. We present an auto-labeling process that creates SOGMs fromnoisy real navigation data. We use a 3D-2D feedforward architecture, trained topredict the future time steps of SOGMs, given 3D lidar frames as input. Ourpipeline is entirely self-supervised, thus enabling lifelong learning for realrobots. The network is composed of a 3D back-end that extracts rich featuresand enables the semantic segmentation of the lidar frames, and a 2D front-endthat predicts the future information embedded in the SOGM representation,potentially capturing the complexities and uncertainties of real-worldmulti-agent, multi-future interactions. We also design a navigation system thatuses these predicted SOGMs within planning, after they have been transformedinto Spatiotemporal Risk Maps (SRMs). We verify our navigation system'sabilities in simulation, validate it on a real robot, study SOGM predictions onreal data in various circumstances, and provide a novel indoor 3D lidardataset, collected during our experiments, which includes our automatedannotations.

The Foreseeable Future: Self-Supervised Learning to Predict Dynamic Scenes for Indoor Navigation