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 recent advancements in wireless technology enable connected autonomousvehicles (CAVs) to gather information about their environment byvehicle-to-vehicle (V2V) communication. In this work, we design aninformation-sharing-based multi-agent reinforcement learning (MARL) frameworkfor CAVs, to take advantage of the extra information when making decisions toimprove traffic efficiency and safety. The safe actor-critic algorithm wepropose has two new techniques: the truncated Q-function and safe actionmapping. The truncated Q-function utilizes the shared information fromneighboring CAVs such that the joint state and action spaces of the Q-functiondo not grow in our algorithm for a large-scale CAV system. We prove the boundof the approximation error between the truncated-Q and global Q-functions. Thesafe action mapping provides a provable safety guarantee for both the trainingand execution based on control barrier functions. Using the CARLA simulator forexperiments, we show that our approach can improve the CAV system's efficiencyin terms of average velocity and comfort under different CAV ratios anddifferent traffic densities. We also show that our approach avoids theexecution of unsafe actions and always maintains a safe distance from othervehicles. We construct an obstacle-at-corner scenario to show that the sharedvision can help CAVs to observe obstacles earlier and take action to avoidtraffic jams.

A Multi-Agent Reinforcement Learning Approach For Safe and Efficient Behavior Planning Of Connected Autonomous Vehicles