Joint Scheduling of Multi-Band Radar Sensing and DNN Inference for Cross-Stage Parallelism

TL;DR

This paper proposes a joint scheduling framework for multi-band radar sensing and DNN inference that exploits cross-stage parallelism to minimize end-to-end latency, outperforming traditional sequential designs.

Contribution

It introduces a novel cross-stage parallelism approach with a joint scheduling formulation and heuristics for sensing and DAG execution, reducing latency in radar-DNN pipelines.

Findings

Cross-stage parallelism reduces end-to-end latency in radar-DNN pipelines.

The proposed heuristics effectively evaluate sensing decisions for latency minimization.

Simulation shows significant latency reduction in heterogeneous sensing scenarios.

Abstract

This paper studies end-to-end latency minimization for a multi-band radar sensing and deep neural network (DNN) inference pipeline. Unlike conventional stage-wise designs that treat radar sensing and DNN inference as two sequential stages, the proposed framework exploits cross-stage parallelism by allowing the inference branch associated with a sensed band to start as soon as that band completes sensing, without waiting for all bands to finish. To characterize this interaction, we formulate a joint scheduling problem that couples sensing-time allocation, branch release timing, and non-preemptive multi-core execution of a directed acyclic graph (DAG) under sensing-feasibility, precedence, and core-capacity constraints. Since the resulting problem is combinatorial and strongly time-coupled, we further develop a release-aware heuristic that evaluates each sensing decision according to its downstream impact on the DAG makespan, together with a greedy list scheduler for multi-core DAG execution under release times. Simulation results show that the proposed design can effectively exploit cross-stage parallelism and reduce end-to-end latency relative to a decoupled baseline in many heterogeneous sensing scenarios, while also clarifying the operating regimes in which the latency gain becomes limited.