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 (AVs) have the potential to prevent accidents caused bydrivers' error and reduce road traffic risks. Due to the nature of heavyvehicles, whose collisions cause more serious crashes, the weights of vehiclesneed to be considered when making driving strategies aimed at reducing thepotential risks and their consequences in the context of autonomous driving.This study develops an autonomous driving strategy based on risk anticipation,considering the weights of surrounding vehicles and using hierarchical deepreinforcement learning. A risk indicator integrating surrounding vehicles'weights, based on the risk field theory, is proposed and incorporated intoautonomous driving decisions. A hybrid action space is designed to allow forleft lane changes, right lane changes and car-following, which enables AVs toact more freely and realistically whenever possible. To solve the above hybriddecision-making problem, a hierarchical proximal policy optimization (HPPO)algorithm is developed and an attention mechanism is incorporated, providinggreat advantages in maintaining stable performance. An indicator, potentialcollision energy in conflicts (PCEC), is newly proposed to evaluate theperformance of the developed AV driving strategy from both the perspectives ofthe likelihood and the consequences of potential accidents. An application iscarried out and the simulation results demonstrate that our model providesdriving strategies that reduce both the likelihood and consequences ofpotential accidents, at the same time maintaining driving efficiency. Thedeveloped method is especially meaningful for AVs driving on highways, whereheavy vehicles make up a high proportion of the traffic.

Risk-anticipatory autonomous driving strategies considering vehicles' weights, based on hierarchical deep reinforcement learning