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

The deployment of autonomous vehicles (AVs) has faced hurdles due to thedominance of rare but critical corner cases within the long-tail distributionof driving scenarios, which negatively affects their overall performance. Toaddress this challenge, adversarial generation methods have emerged as a classof efficient approaches to synthesize safety-critical scenarios for AV testing.However, these generated scenarios are often underutilized for AV training,resulting in the potential for continual AV policy improvement remaininguntapped, along with a deficiency in the closed-loop design needed to achieveit. Therefore, we tailor the Stackelberg Driver Model (SDM) to accuratelycharacterize the hierarchical nature of vehicle interaction dynamics,facilitating iterative improvement by engaging background vehicles (BVs) and AVin a sequential game-like interaction paradigm. With AV acting as the leaderand BVs as followers, this leader-follower modeling ensures that AV wouldconsistently refine its policy, always taking into account the additionalinformation that BVs play the best response to challenge AV. Extensiveexperiments have shown that our algorithm exhibits superior performancecompared to several baselines especially in higher dimensional scenarios,leading to substantial advancements in AV capabilities while continuallygenerating progressively challenging scenarios. Code is available athttps://github.com/BlueCat-de/SDM.

Stackelberg Driver Model for Continual Policy Improvement in Scenario-Based Closed-Loop Autonomous Driving