RED: Adaptive Real-Time DAG Scheduling for Robotic Inference under Environmental Dynamics

2026-05-21

AI Summary

This work addresses the challenges of real-time multitask reasoning for robots in dynamic environments, where shifting computational graph structures, drifting task dependencies, and limited resources degrade both timeliness and performance. To tackle these issues, the paper introduces RED, a novel framework that incorporates environment-driven computational evolution into real-time scheduling. RED dynamically adapts directed acyclic graph (DAG)-based task schedules through deadline-aware scheduling and a MIMONet-based graph restructuring mechanism. By integrating sub-deadline allocation, workload refinement, and asynchronous inference support, RED enables efficient parameter sharing and dynamic adaptation on resource-constrained platforms. Experimental results demonstrate that RED significantly outperforms existing scheduling approaches on Jetson and Apple M-series devices, achieving higher throughput, improved deadline satisfaction rates, enhanced robustness to interference, and greater runtime efficiency.

Abstract

Robots deployed in dynamic environments must contend with environment-driven changes that reshape computation at runtime: new tasks may appear, precedence relations can shift, and overall workload structure evolves, all of which degrade performance, especially when multi-task inference is required under tight resource and real-time budgets. We present RED, a real-time scheduling framework for multi-task deep neural network workloads on resource-constrained robotic platforms that adapts to Robotic Environmental Dynamics (RED) while preserving end-to-end timing guarantees under modeling assumptions. The core of RED is a deadline-aware scheduler that assigns intermediate sub-deadlines, allowing it to accommodate evolving computation graphs and asynchronous inference induced by unpredictable conditions. The framework also supports flexible deployment of MIMONet (multi-input multi-output neural networks), commonly used in multi-tasking robots to alleviate memory pressure through weight sharing. RED explicitly leverages this shared-parameter property via a workload refinement and graph-reconstruction procedure that aligns MIMONet structure with schedulability requirements, improving compatibility and efficiency. We implement RED on NVIDIA Jetson family platforms and on an Apple M-series MacBook and evaluate it on navigation-oriented workloads representative of real robotic scenarios. Experiments show consistent gains over existing methods in throughput, deadline satisfaction, robustness to interference, adaptability, and runtime overhead.

Problem

• real-time scheduling
• environmental dynamics
• multi-task inference
• resource-constrained robotics
• computation graph evolution

Innovation

• real-time scheduling
• dynamic environments
• MIMONet
• DAG scheduling
• robotic inference