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 this paper, we present a transfer learning method for the end-to-endcontrol of self-driving cars, which enables a convolutional neural network(CNN) trained on a source domain to be utilized for the same task in adifferent target domain. A conventional CNN for the end-to-end control isdesigned to map a single front-facing camera image to a steering command. Toenable the transfer learning, we let the CNN produce not only a steeringcommand but also a lane departure level (LDL) by adding a new task module,which takes the output of the last convolutional layer as input. The CNNtrained on the source domain, called source network, is then utilized to trainanother task module called target network, which also takes the output of thelast convolutional layer of the source network and is trained to produce asteering command for the target domain. The steering commands from the sourceand target network are finally merged according to the LDL and the mergedcommand is utilized for controlling a car in the target domain. To demonstratethe effectiveness of the proposed method, we utilized two simulators, TORCS andGTAV, for the source and the target domains, respectively. Experimental resultsshow that the proposed method outperforms other baseline methods in terms ofstable and safe control of cars.

Driving Experience Transfer Method for End-to-End Control of Self-Driving Cars