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

Fast, collision-free motion through unknown environments remains achallenging problem for robotic systems. In these situations, the robot'sability to reason about its future motion is often severely limited by sensorfield of view (FOV). By contrast, biological systems routinely make decisionsby taking into consideration what might exist beyond their FOV based on priorexperience. In this paper, we present an approach for predicting occupancy maprepresentations of sensor data for future robot motions using deep neuralnetworks. We evaluate several deep network architectures, including purelygenerative and adversarial models. Testing on both simulated and realenvironments we demonstrated performance both qualitatively and quantitatively,with SSIM similarity measure up to 0.899. We showed that it is possible to makepredictions about occupied space beyond the physical robot's FOV from simulatedtraining data. In the future, this method will allow robots to navigate throughunknown environments in a faster, safer manner.

Occupancy Map Prediction Using Generative and Fully Convolutional Networks for Vehicle Navigation