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

Autonomous vehicles need to model the behavior of surrounding human drivenvehicles to be safe and efficient traffic participants. Existing approaches tomodeling human driving behavior have relied on both data-driven and rule-basedmethods. While data-driven models are more expressive, rule-based models areinterpretable, which is an important requirement for safety-critical domainslike driving. However, rule-based models are not sufficiently representative ofdata, and data-driven models are yet unable to generate realistic trafficsimulation due to unrealistic driving behavior such as collisions. In thispaper, we propose a methodology that combines rule-based modeling withdata-driven learning. While the rules are governed by interpretable parametersof the driver model, these parameters are learned online from drivingdemonstration data using particle filtering. We perform driver modelingexperiments on the task of highway driving and merging using data from threereal-world driving demonstration datasets. Our results show that driver modelsbased on our hybrid rule-based and data-driven approach can accurately capturereal-world driving behavior. Further, we assess the realism of the drivingbehavior generated by our model by having humans perform a driving Turing test,where they are asked to distinguish between videos of real driving and thosegenerated using our driver models.

A Hybrid Rule-Based and Data-Driven Approach to Driver Modeling through Particle Filtering