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

In transportation networks, where traffic lights have traditionally been usedfor vehicle coordination, intersections act as natural bottlenecks. Aformidable challenge for existing automated intersections lies in detecting andreasoning about uncertainty from the operating environment and human-drivenvehicles. In this paper, we propose a risk-aware intelligent intersectionsystem for autonomous vehicles (AVs) as well as human-driven vehicles (HVs). Wecast the problem as a novel class of Multi-agent Chance-Constrained StochasticShortest Path (MCC-SSP) problems and devise an exact Integer Linear Programming(ILP) formulation that is scalable in the number of agents' interaction points(e.g., potential collision points at the intersection). In particular, when thenumber of agents within an interaction point is small, which is often the casein intersections, the ILP has a polynomial number of variables and constraints.To further improve the running time performance, we show that the collisionrisk computation can be performed offline. Additionally, a trajectoryoptimization workflow is provided to generate risk-aware trajectories for anygiven intersection. The proposed framework is implemented in CARLA simulatorand evaluated under a fully autonomous intersection with AVs only as well as ina hybrid setup with a signalized intersection for HVs and an intelligent schemefor AVs. As verified via simulations, the featured approach improvesintersection's efficiency by up to $200\%$ while also conforming to thespecified tunable risk threshold.

Multi-Agent Chance-Constrained Stochastic Shortest Path with Application to Risk-Aware Intelligent Intersection