Safety-Aware AoI Scheduling for LEO Satellite-Assisted Autonomous Driving

2026-04-19

AI Summary

This work addresses safety-critical update failures in low Earth orbit satellite-aided autonomous driving, caused by compounded Doppler effects, sub-slot handover interruptions, and heterogeneous information freshness requirements. To tackle these challenges, the authors propose a two-timescale Age of Information (AoI) model integrated with virtual queues to enforce hierarchical time-averaged safety constraints. They design a predictive handover mechanism and a multi-task multi-agent reinforcement learning (MARL) scheduler to ensure timely collision alerts. Notably, they derive a closed-form AoI envelope for ping-pong handovers, revealing a quadratic relationship between oscillation duration and cumulative penalty, and uniquely prioritize suppressing frequent short-duration handovers as the highest-level safety measure. The proposed SafeScale-MATD3 algorithm combines a drift-plus-penalty framework, handover timing control, and a multi-agent twin-critic reinforcement learning architecture, achieving a 4–5.5× reduction in violation rate under a 1% alert violation budget, a 35% decrease in alert AoI, and strict Pareto optimality between energy consumption and information freshness.

Technology Category

• Planning, Routing, and Scheduling: Scheduling under Uncertainty
• Multiagent Systems: Agent Communication
• Search and Optimization: Learning to Search

Application Category

• Security and Privacy: Large-scale security measurements
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Autonomous platoons traversing infrastructure gaps increasingly depend on LEO satellite backhaul for safety-critical updates, yet no existing framework jointly addresses compound Doppler from simultaneous satellite and vehicle motion, sub-slot handover outages that exceed collision-alert deadlines, and heterogeneous freshness requirements across three vehicular priority classes. The core challenge is a \emph{timescale mismatch}: coarse control slots hide sub-slot outages, which makes both AoI spike analysis and safety verification ill-posed. Ping-pong handover oscillations further compound AoI cost in a way that purely reactive schedulers cannot mitigate. We address these challenges through a unified framework that couples a two-timescale AoI model with tiered time-average safety constraints enforced by virtual queues. A closed-form ping-pong AoI envelope reveals that cumulative penalty grows quadratically in oscillation length, analytically justifying oscillation suppression as the highest-leverage safety mechanism. The resulting drift-plus-penalty template is instantiated as SafeScale-MATD3 with proactive handover timing and multi-task dual-critic MARL. A key finding is that suppressing brief but repeated ping-pong oscillations yields larger safety returns than shortening any single outage, and that tick-level AoI accounting is a necessary condition for verifiable collision-alert guarantees under LEO handovers. Simulations show that SafeScale-MATD3 is the only method satisfying the strict 1 % collision-alert violation budget, reducing violation rate by 4 to 5.5 times versus baselines, while achieving 35 % lower collision-alert AoI and strict Pareto dominance on the energy and freshness tradeoff.

Problem

• Age of Information
• LEO satellite
• autonomous driving
• handover outage
• safety constraints

Innovation

• Age of Information (AoI)
• LEO satellite handover
• safety-aware scheduling
• multi-agent reinforcement learning
• ping-pong oscillation suppression