Optimizing Tracking Accuracy in Energy-Constrained Multimodal ISAC via Lyapunov-Driven Heterogeneous Mixture-of-Experts

TL;DR

This paper introduces a physics-aware M-ISAC framework for V2I networks that balances tracking accuracy and energy use by leveraging a Lyapunov-driven MoE reinforcement learning approach.

Contribution

It develops a novel LD-H-MoE RL architecture that decouples scheduling and spatial mapping, improving tracking accuracy and energy efficiency in multimodal ISAC systems.

Findings

LD-H-MoE achieves superior tracking accuracy and RF resilience.

The framework guarantees queue stability and long-term energy budgets.

Simulation results validate the effectiveness of the event-triggered sensing policy.

Abstract

The integration of multimodal sensing and millimeter-wave (mmWave) communications is a key enabler for highly mobile vehicle-to-infrastructure (V2I) networks. However, continuous high-resolution visual sensing incurs prohibitive computational energy, while delayed sensing information causes severe beam misalignment. This paper establishes a physics-aware multimodal integrated sensing and communication (M-ISAC) framework that mathematically bridges network-layer queuing delays with physical-layer spatial uncertainty via the semantic age of information (AoI). Guided by this relationship, we aim to strike an optimal trade-off between the tracking posterior Cramer-Rao bound (PCRB) and system energy budgets, we formulate a stochastic mixed-integer non-linear programming (MINLP) problem. Addressing the coupled challenges of temporal computing congestion and non-convex constant modulus constraints, we propose a reinforcement learning (RL) framework empowered by a Lyapunov-driven heterogeneous mixture-of-experts (LD-H-MoE) architecture. By strictly decoupling temporal scheduling and spatial phase mapping into specialized subnetworks, the LD-H-MoE circumvents gradient conflicts prevalent in monolithic multi-task learning. Simulations demonstrate that the proposed LD-H-MoE achieves a highly-effective event-triggered sensing policy, yielding superior tracking accuracy and radio-frequency (RF) resilience while guaranteeing edge computing queue stability and long-term energy budgets.