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 the field of motion simulation, the level of immersion strongly depends onthe motion cueing algorithm (MCA), as it transfers the reference motion of thesimulated vehicle to a motion of the motion simulation platform (MSP). Thechallenge for the MCA is to reproduce the motion perception of a real vehicledriver as accurately as possible without exceeding the limits of the workspaceof the MSP in order to provide a realistic virtual driving experience. In caseof a large discrepancy between the perceived motion signals and the opticalcues, motion sickness may occur with the typical symptoms of nausea, dizziness,headache and fatigue. Existing approaches either produce non-optimal results,e.g., due to filtering, linearization, or simplifications, or the requiredcomputational time exceeds the real-time requirements of a closed-loopapplication.  In this work a new solution is presented, where not a human designerspecifies the principles of the MCA but an artificial intelligence (AI) learnsthe optimal motion by trial and error in an interaction with the MSP. Toachieve this, deep reinforcement learning (RL) is applied, where an agentinteracts with an environment formulated as a Markov decision process~(MDP).This allows the agent to directly control a simulated MSP to obtain feedback onits performance in terms of platform workspace usage and the motion acting onthe simulator user. The RL algorithm used is proximal policy optimization(PPO), where the value function and the policy corresponding to the controlstrategy are learned and both are mapped in artificial neural networks (ANN).This approach is implemented in Python and the functionality is demonstrated bythe practical example of pre-recorded lateral maneuvers. The subsequentvalidation on a standardized double lane change shows that the RL algorithm isable to learn the control strategy and improve the quality of...

A novel approach of a deep reinforcement learning based motion cueing algorithm for vehicle driving simulation