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

In this paper, we present a novel end-to-end deep neural network model forautonomous driving that takes monocular image sequence as input, and directlygenerates the steering control angle. Firstly, we model the end-to-end drivingproblem as a local path planning process. Inspired by the environmentalrepresentation in the classical planning algorithms(i.e. the beam curvaturemethod), pixel-wise orientations are fed into the network to learndirection-aware features. Next, to handle the imbalanced distribution ofsteering values in training datasets, we propose an improvement on acost-sensitive loss function named SteeringLoss2. Besides, we also present anew end-to-end driving dataset, which provides corresponding LiDAR and imagesequences, as well as standard driving behaviors. Our dataset includes multipledriving scenarios, such as urban, country, and off-road. Numerous experimentsare conducted on both public available LiVi-Set and our own dataset, and theresults show that the model using our proposed methods can predict steeringangle accurately.

Incorporating Orientations into End-to-end Driving Model for Steering Control