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 the foreseeable future, autonomous vehicles will require human assistancein situations they can not resolve on their own. In such scenarios, remoteassistance from a human can provide the required input for the vehicle tocontinue its operation. Typical sensors used in autonomous vehicles includecamera and lidar sensors. Due to the massive volume of sensor data that must besent in real-time, highly efficient data compression is elementary to preventan overload of network infrastructure. Sensor data compression using deepgenerative neural networks has been shown to outperform traditional compressionapproaches for both image and lidar data, regarding compression rate as well asreconstruction quality. However, there is a lack of research about theperformance of generative-neural-network-based compression algorithms forremote assistance. In order to gain insights into the feasibility of deepgenerative models for usage in remote assistance, we evaluate state-of-the-artalgorithms regarding their applicability and identify potential weaknesses.Further, we implement an online pipeline for processing sensor data anddemonstrate its performance for remote assistance using the CARLA simulator.

Compressing Sensor Data for Remote Assistance of Autonomous Vehicles using Deep Generative Models