DAG-Based QoS-Aware Dynamic Task Placement for Networked Multi-Stage Control Pipelines

2026-05-19

AI Summary

This work addresses the challenge of achieving low-latency and high-accuracy visual servo control in industrial robots, where the perception-planning-control pipeline is computationally intensive. Traditional static edge offloading struggles to balance these conflicting requirements, while existing adaptive task placement approaches often neglect inter-stage dependencies and switching overheads. To overcome these limitations, we propose a directed acyclic graph (DAG)-based dynamic task placement framework that explicitly models the multi-stage pipeline and jointly optimizes end-to-end latency, deadline violation rate, hardware utilization, and switching cost—quantified by Hamming distance. A minimum dwell-time constraint is introduced to suppress task migration jitter. By integrating a sliding-window cost function with a hysteresis-aware dynamic scheduling algorithm, our approach enables co-design across communication, computation, and control. Extensive simulation and hardware-in-the-loop experiments validate its efficacy in delivering QoS-aware, efficient deployment for networked industrial robots.

Abstract

Current Physical AI (PAI) relies heavily on closed-loop visual-servoing pipelines, whose perception and planning stages may become computationally intensive onboard due to complex models embedded on robots. In practice, offloading the perception task to on-site edges statically is inappropriate for latency-sensitive, precise industrial settings over a standardized industrial network. This emphasizes the importance of Control-Communication-Computing (3C) co-design in industrial automation: monolithic local execution saturates AI-accelerated machine and robot hardware, while static edge offloading exposes the control loop to network jitter. Existing adaptive task placement (ATP) controllers can partially address the gap by relocating a single pipeline stage on binary threshold rules, without a multi-stage model and an explicit cost on placement switching. In this Work-in-Progress (WiP) paper, we propose a directed acyclic graph (DAG) based quality-of-service (QoS)-aware dynamic task placement (DTP) framework for sensing-perception-planning-control pipelines in networked robotics. This pipeline is formalized as a DAG with task-level and node-level attributes for compute cost, communication delay, and feasible placement sets; over a small interpretable candidate set (fully local, static offload, hybrid), a window-based cost function combines tail end-to-end latency, deadline violation rate, hardware utilization, and a Hamming-distance switching penalty, and a DTP algorithm with hysteresis and a minimum dwell-time bounds placement chatter. Our WiP paper presents the theoretical framework, a structured qualitative analysis, and a two-phase simulation plus hardware-in-the-loop validation roadmap.

Problem

• Dynamic Task Placement
• QoS-aware
• Multi-Stage Control Pipeline
• Networked Robotics
• 3C Co-design

Innovation

• DAG-based task modeling
• QoS-aware dynamic task placement
• 3C co-design
• placement switching penalty
• minimum dwell-time control