September 10, 2025ElectronicsOpen Access

Lightweight Semantic Segmentation for AGV Navigation: An Enhanced ESPNet-C with Dual Attention Mechanisms

View Full Paper

Ask AI

Bookmark

The model achieves 90.5% Miou at 0.425 M parameters, enhancing efficiency for automated guided vehicles.
It reduces computational costs by 70–92% compared to DeepLabV3+, indicating significant resource savings.
Boundary coherence improved by 22% under uneven lighting, enhancing navigation accuracy in dynamic environments.
The model demonstrates generalization with 90.2% Miou on public datasets, ensuring versatility in real-world applications.

Discussion

No takes yet. Share an insight, caveat, or question.

New approach improves semantic segmentation performance for automated guided vehicles, highlighting efficiency and adaptability.

Shu et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark