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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

In the trajectory planning of automated driving, data-driven statisticalartificial intelligence (AI) methods are increasingly established forpredicting the emergent behavior of other road users. While these methodsachieve exceptional performance in defined datasets, they usually rely on theindependent and identically distributed (i.i.d.) assumption and thus tend to bevulnerable to distribution shifts that occur in the real world. In addition,these methods lack explainability due to their black box nature, which posesfurther challenges in terms of the approval process and social trustworthiness.Therefore, in order to use the capabilities of data-driven statistical AImethods in a reliable and trustworthy manner, the concept of TrustMHE isintroduced and investigated in this paper. TrustMHE represents a complementaryapproach, independent of the underlying AI systems, that combines AI-drivenout-of-distribution detection with control-driven moving horizon estimation(MHE) to enable not only detection and monitoring, but also intervention. Theeffectiveness of the proposed TrustMHE is evaluated and proven in threesimulation scenarios.

Enhancing System Self-Awareness and Trust of AI: A Case Study in Trajectory Prediction and Planning