Embodied AI-Enhanced IoMT Edge Computing: UAV Trajectory Optimization and Task Offloading with Mobility Prediction

TL;DR

The paper addresses dynamic task offloading and UAV trajectory optimization in a UAV-enabled IoMT WBAN edge computing system with dual mobility and time varying task criticality. It proposes an embodied AI framework that couples a hierarchical multi scale Transformer mobility predictor with a prediction enhanced DRL algorithm to jointly optimize UAV flight and offloading under UAV energy constraints. The model accounts for time varying task criticality, LoS/NLoS channels, and energy allocation across local and UAV computation, evaluated with real GeoLife traces and simulations showing substantial improvements in weighted average task completion time over baselines. Overall, the approach enables robust, real time edge computing for healthcare scenarios, reducing latency while respecting energy and channel constraints and is validated with rigorous experiments.

Abstract

Due to their inherent flexibility and autonomous operation, unmanned aerial vehicles (UAVs) have been widely used in Internet of Medical Things (IoMT) to provide real-time biomedical edge computing service for wireless body area network (WBAN) users. In this paper, considering the time-varying task criticality characteristics of diverse WBAN users and the dual mobility between WBAN users and UAV, we investigate the dynamic task offloading and UAV flight trajectory optimization problem to minimize the weighted average task completion time of all the WBAN users, under the constraint of UAV energy consumption. To tackle the problem, an embodied AI-enhanced IoMT edge computing framework is established. Specifically, we propose a novel hierarchical multi-scale Transformer-based user trajectory prediction model based on the users' historical trajectory traces captured by the embodied AI agent (i.e., UAV). Afterwards, a prediction-enhanced deep reinforcement learning (DRL) algorithm that integrates predicted users' mobility information is designed for intelligently optimizing UAV flight trajectory and task offloading decisions. Real-word movement traces and simulation results demonstrate the superiority of the proposed methods in comparison with the existing benchmarks.

Figures (9)

• Figure 1: System model
• Figure 2: Hierarchical Transformer Trajectory Prediction Model
• Figure 3: The workflow of the interaction between the embodied UAV agent and the environment
• Figure 4: Convergence behavior of mobility prediction models
• Figure 5: RMSE comparison for user trajectory prediction models