{"paper":{"title":"Hardware Utilization and Inference Performance of Edge Object Detection Under Fault Injection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"TensorRT-optimized YOLO models on Jetson Nano keep GPU occupancy, temperature, power, and memory stable even under heavy input degradation from injected faults.","cross_cats":["cs.AI"],"primary_cat":"cs.DC","authors_text":"Achim Rettberg, Faezeh Pasandideh, Mehdi Azarafza","submitted_at":"2026-03-19T17:55:59Z","abstract_excerpt":"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 fram"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"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.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The faults synthesized using LLMs and LDMs based on JetBot platform data accurately represent the kinds of real-world input degradation that would occur in deployed autonomous driving systems.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"TensorRT YOLO pipelines on Jetson Nano keep GPU occupancy, power draw, and temperature stable even under heavy fault-injected inputs for object detection and lane following.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"TensorRT-optimized YOLO models on Jetson Nano keep GPU occupancy, temperature, power, and memory stable even under heavy input degradation from injected faults.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e2b816fe7ad4feb1394299210520358d8b07aa2c5669737284b396d051919d95"},"source":{"id":"2604.09631","kind":"arxiv","version":2},"verdict":{"id":"433892a8-5a78-4828-b5b1-cb285c5da7be","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T07:58:44.899781Z","strongest_claim":"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.","one_line_summary":"TensorRT YOLO pipelines on Jetson Nano keep GPU occupancy, power draw, and temperature stable even under heavy fault-injected inputs for object detection and lane following.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The faults synthesized using LLMs and LDMs based on JetBot platform data accurately represent the kinds of real-world input degradation that would occur in deployed autonomous driving systems.","pith_extraction_headline":"TensorRT-optimized YOLO models on Jetson Nano keep GPU occupancy, temperature, power, and memory stable even under heavy input degradation from injected faults."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.09631/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}