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

Reinforcement learning (RL) is a promising solution for autonomous vehiclesto deal with complex and uncertain traffic environments. The RL trainingprocess is however expensive, unsafe, and time consuming. Algorithms are oftendeveloped first in simulation and then transferred to the real world, leadingto a common sim2real challenge that performance decreases when the domainchanges. In this paper, we propose a transfer learning process to minimize thegap by exploiting digital twin technology, relying on a systematic andsimultaneous combination of virtual and real world data coming from vehicledynamics and traffic scenarios. The model and testing environment are evolvedfrom model, hardware to vehicle in the loop and proving ground testing stages,similar to standard development cycle in automotive industry. In particular, wealso integrate other transfer learning techniques such as domain randomizationand adaptation in each stage. The simulation and real data are graduallyincorporated to accelerate and make the transfer learning process more robust.The proposed RL methodology is applied to develop a path following steeringcontroller for an autonomous electric vehicle. After learning and deploying thereal-time RL control policy on the vehicle, we obtained satisfactory and safecontrol performance already from the first deployment, demonstrating theadvantages of the proposed digital twin based learning process.

Reinforcement Learning from Simulation to Real World Autonomous Driving using Digital Twin