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

Designing or learning an autonomous driving policy is undoubtedly achallenging task as the policy has to maintain its safety in all corner cases.In order to secure safety in autonomous driving, the ability to detecthazardous situations, which can be seen as an out-of-distribution (OOD)detection problem, becomes crucial. However, most conventional datasets onlyprovide expert driving demonstrations, although some non-expert or uncommondriving behavior data are needed to implement a safety guaranteed autonomousdriving platform. To this end, we present a novel dataset called the R3 DrivingDataset, composed of driving data with different qualities. The datasetcategorizes abnormal driving behaviors into eight categories and 369 differentdetailed situations. The situations include dangerous lane changes andnear-collision situations. To further enlighten how these abnormal drivingbehaviors can be detected, we utilize different uncertainty estimation andanomaly detection methods to the proposed dataset. From the results of theproposed experiment, it can be inferred that by using both uncertaintyestimation and anomaly detection, most of the abnormal cases in the proposeddataset can be discriminated. The dataset of this paper can be downloaded fromhttps://rllab-snu.github.io/projects/R3-Driving-Dataset/doc.html.

Towards Defensive Autonomous Driving: Collecting and Probing Driving Demonstrations of Mixed Qualities