Hardware Utilization and Inference Performance of Edge Object Detection Under Fault Injection

TL;DR

This study systematically characterizes hardware behavior and inference performance of YOLO object detection models on NVIDIA Jetson Nano under fault injection, revealing robustness of TensorRT pipelines despite resource degradation.

Contribution

It provides a detailed hardware-level analysis of edge object detection models under fault conditions, using a novel fault synthesis framework with LLMs and LDMs.

Findings

GPU occupancy remains stable under faults

Power consumption stays within safe limits

Memory and thermal behavior show some variability

Abstract

As deep learning models are deployed on resource constrained edge platforms in autonomous driving systems, reli able knowledge of hardware behavior under resource degradation becomes an essential requirement. Therefore, we introduce a systematic characterization of CPU load, GPU utilization, RAM consumption, power draw, throughput, and thermal behaviour of TensorRT-optimized YOLOv10s, YOLOv11s and YOLO2026n pipelines running on NVIDIA Jetson Nano under a large-scale fault injection campaign targeting both lane-following and ob ject detection tasks. Faults are synthesized using a decoupled framework that leverages large language models (LLMs) and latent diffusion models (LDMs), based on original data from our JetBot platform data collection. Results show that across both tasks and both models the inference engines keep GPU occupancy stable, temperature rise under control, and power consumption within safe limits, while memory usage settles into a consistent release pattern after the initial warm-up phase. Object detection tends to show somewhat more variability in memory and thermal behavior, yet both tasks point to the same conclusion: the TensorRT pipelines hold up well even when the input data is heavily degraded. These findings offer a hardware-level view of model reliability that sits alongside, rather than against, the broader body of work focused on inference performance at the edge.