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

End-to-end visual-based imitation learning has been widely applied inautonomous driving. When deploying the trained visual-based driving policy, adeterministic command is usually directly applied without considering theuncertainty of the input data. Such kind of policies may bring dramaticaldamage when applied in the real world. In this paper, we follow the recentreal-to-sim pipeline by translating the testing world image back to thetraining domain when using the trained policy. In the translating process, astochastic generator is used to generate various images stylized under thetraining domain randomly or directionally. Based on those translated images,the trained uncertainty-aware imitation learning policy would output both thepredicted action and the data uncertainty motivated by the aleatoric lossfunction. Through the uncertainty-aware imitation learning policy, we caneasily choose the safest one with the lowest uncertainty among the generatedimages. Experiments in the Carla navigation benchmark show that our strategyoutperforms previous methods, especially in dynamic environments.

Visual-based Autonomous Driving Deployment from a Stochastic and Uncertainty-aware Perspective