Global Journal of Engineering and Technology Research (GJETR) · Research article · Open access

Edge-Optimized YOLO Architectures for Real-Time Autonomous Vehicle Perception: A Hardware-Aware Co-Design Framework

Harouna Wendpanga Yann Christian Sankara, Serif Oyindamola Oyesiji, Emmanuel Eniola Aalaj, Stanley Nwakamma

9 September 2026 · Vol. 2, Issue 9, pp. 495-506

DOI: 10.65150/EP-gjetr/V2E9/2026-09

Download full text (PDF)Cite this article

Abstract

Object detection is the perceptual backbone of autonomous driving, and single-stage detectors of the YOLO family have become the practical default wherever frames must be processed within real-time budgets. Yet the published detection literature optimizes predominantly for benchmark accuracy on server-class accelerators, while vehicles impose a different objective: bounded end-to-end latency at high frame rates, on power- and thermally-constrained embedded accelerators, across multiple simultaneous camera streams, under safety expectations that penalize missed detections far more than the mean average precision metric reflects. This paper develops a research concept for an edge-optimized YOLO-based perception component designed and evaluated against vehicle-grade constraints. The concept specifies a co-design space spanning architecture, compact backbones, decoupled heads, resolution and anchor policy tuned to driving object statistics, and compression, structured pruning, quantization-aware training to integer arithmetic, and knowledge distillation from a high-capacity teacher, searched jointly under hardware-in-the-loop latency measurement rather than proxy operation counts. A deployment architecture allocates per-camera detection instances across embedded accelerator resources with a frame-freshness scheduling policy that privileges recency over throughput, and an optional offload path is analyzed and deliberately excluded from the safety path. The evaluation plan is phased: accuracy and robustness on driving benchmarks with corruption suites; latency, jitter, energy, and thermal behavior measured on target hardware across compression configurations; and system-level metrics that couple detection quality to reaction distance at speed. The concept's central claim is methodological: for vehicle perception, the deployable operating point is a property of the model-compression-hardware triple, and it must be measured as such.

Keywords: Edge-optimized YOLO, real-time object detection, autonomous vehicle perception, hardware-aware co-design, model compression (pruning, quantization, distillation), embedded accelerators, multi-camera latency, safety-critical edge AI

Harouna Wendpanga Yann Christian Sankara, Serif Oyindamola Oyesiji, Emmanuel Eniola Aalaj, & Stanley Nwakamma (2026). Edge-Optimized YOLO Architectures for Real-Time Autonomous Vehicle Perception: A Hardware-Aware Co-Design Framework. Global Journal of Engineering and Technology Research, 2(9), 495-506. https://doi.org/10.65150/EP-gjetr/V2E9/2026-09

@article{Harouna2026,
  title   = {Edge-Optimized YOLO Architectures for Real-Time Autonomous Vehicle Perception: A Hardware-Aware Co-Design Framework},
  author  = {Harouna Wendpanga Yann Christian Sankara and Serif Oyindamola Oyesiji and Emmanuel Eniola Aalaj and Stanley Nwakamma},
  journal = {Global Journal of Engineering and Technology Research},
  year    = {2026},
  volume  = {2},
  number  = {9},
  pages   = {495-506},
  doi     = {10.65150/EP-gjetr/V2E9/2026-09},
  url     = {https://doi.org/10.65150/EP-gjetr/V2E9/2026-09}
}

← All articlesAbout GJETR and how to submit