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

Discretionary lane-change is one of the critical challenges for autonomousvehicle (AV) design due to its significant impact on traffic efficiency.Existing intelligent lane-change solutions have primarily focused on optimizingthe performance of the ego-vehicle, thereby suffering from limitedgeneralization performance. Recent research has seen an increased interest inmulti-agent reinforcement learning (MARL)-based approaches to address thelimitation of the ego vehicle-based solutions through close coordination ofmultiple agents. Although MARL-based approaches have shown promising results,the potential impact of lane-change decisions on the overall traffic flow of aroad segment has not been fully considered. In this paper, we present a novelhybrid MARL-based intelligent lane-change system for AVs designed to jointlyoptimize the local performance for the ego vehicle, along with the globalperformance focused on the overall traffic flow of a given road segment. With acareful review of the relevant transportation literature, a novel state spaceis designed to integrate both the critical local traffic information pertainingto the surrounding vehicles of the ego vehicle, as well as the global trafficinformation obtained from a road-side unit (RSU) responsible for managing aroad segment. We create a reward function to ensure that the agents makeeffective lane-change decisions by considering the performance of the egovehicle and the overall improvement of traffic flow. A multi-agent deepQ-network (DQN) algorithm is designed to determine the optimal policy for eachagent to effectively cooperate in performing lane-change maneuvers. LCS-TF'sperformance was evaluated through extensive simulations in comparison withstate-of-the-art MARL models. In all aspects of traffic efficiency, drivingsafety, and driver comfort, the results indicate that LCS-TF exhibits superiorperformance.

LCS-TF: Multi-Agent Deep Reinforcement Learning-Based Intelligent Lane-Change System for Improving Traffic Flow