Mandatory lane changes at intersections often lead to intricate conflicts and traffic oscillations.  The advent of connected and autonomous vehicles (CAVs) is expected to mitigate these disruptions by coordinating acceleration and lane-change behaviors. Addressing this, researchers developed SS-MA-PPO, a novel Multi-Agent Reinforcement Learning (MARL) framework that assists CAVs in coordinating these critical decisions. Evaluated against a real-world dataset from Langfang, this method significantly improves traffic efficiency compared with traditional models and other Multi-Agent Reinforcement Learning baselines.

High in the forests of Hawai‘i, songbirds are stealing twigs and moss from one another’s nests. UC Riverside researchers found this quiet canopy crime is surprisingly common and could threaten species already struggling to survive.