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 driving has a natural bi-level structure. The goal of the upperbehavioural layer is to provide appropriate lane change, speeding up, andbraking decisions to optimize a given driving task. However, this layer canonly indirectly influence the driving efficiency through the lower-leveltrajectory planner, which takes in the behavioural inputs to produce motioncommands. Existing sampling-based approaches do not fully exploit the strongcoupling between the behavioural and planning layer. On the other hand,end-to-end Reinforcement Learning (RL) can learn a behavioural layer whileincorporating feedback from the lower-level planner. However, purelydata-driven approaches often fail in safety metrics in unseen environments.This paper presents a novel alternative; a parameterized bi-level optimizationthat jointly computes the optimal behavioural decisions and the resultingdownstream trajectory. Our approach runs in real-time using a customGPU-accelerated batch optimizer, and a Conditional Variational Autoencoderlearnt warm-start strategy. Extensive simulations show that our approachoutperforms state-of-the-art model predictive control and RL approaches interms of collision rate while being competitive in driving efficiency.

Bi-Level Optimization Augmented with Conditional Variational Autoencoder for Autonomous Driving in Dense Traffic