Deep Reinforcement Learning-driven Edge Offloading for Latency-constrained XR pipelines
2026-03-17 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors focus on improving how extended reality (XR) applications run on devices with limited battery and the need for quick response times. They created a system that smartly decides whether to run tasks on the device itself or send them to nearby edge servers, balancing speed and battery life. Using a lightweight deep learning method, their approach adapts to changing network conditions to keep delays low and extend battery life. Tests showed their method can more than double battery life while keeping interactions smooth, even when the network is slow.
extended reality (XR)latencyedge computingbattery managementcomputation offloadingdeep reinforcement learningmotion-to-photon latencyreal-time responsivenessnetwork bandwidthenergy efficiency
Authors
Sourya Saha, Saptarshi Debroy
Abstract
Immersive extended reality (XR) applications introduce latency-critical workloads that must satisfy stringent real-time responsiveness while operating on energy- and battery-constrained devices, making execution placement between end devices and nearby edge servers a fundamental systems challenge. Existing approaches to adaptive execution and computation offloading typically optimize average performance metrics and do not fully capture the sustained interaction between real-time latency requirements and device battery lifetime in closed-loop XR workloads. In this paper, we present a battery-aware execution management framework for edge-assisted XR systems that jointly considers execution placement, workload quality, latency requirements, and battery dynamics. We design an online decision mechanism based on a lightweight deep reinforcement learning policy that continuously adapts execution decisions under dynamic network conditions while maintaining high motion-to-photon latency compliance. Experimental results show that the proposed approach extends the projected device battery lifetime by up to 163% compared to latency-optimal local execution while maintaining over 90% motion-to-photon latency compliance under stable network conditions. Such compliance does not fall below 80% even under significantly limited network bandwidth availability, thereby demonstrating the effectiveness of explicitly managing latency-energy trade-offs in immersive XR systems.