To address issues in traditional forest fire detection models, such as large parameter sizes, slow detection speed, and unsuitability for resource-constrained devices, this paper proposes a forest fire detection method, FEDS-YOLOv11n, based on an improved YOLOv11n model. First, the C3k2 module was redesigned using the FasterBlock module, replacing C3k2 with C3k2-Faster in both the Backbone network and Neck section to achieve a lightweight model design. Second, an EMA attention mechanism was introduced into the C3k2-Faster module in the Backbone, replacing C3k2-Faster with C3k2-Faster-EMA to compensate for the accuracy loss in small-object detection caused by the lightweight design. Third, the original upsampling module in the Neck was replaced with the lightweight dynamic upsampling operator DySample. Finally, the detection head was improved using the SEAM attention module, replacing the original Detect head with SEAMHead, which enables better handling of occluded objects. The experimental results show that compared to YOLOv11n, the proposed FEDS-YOLOv11n achieves improvements of 0.9% in precision (P), 1.9% in recall (R), 2.1% in mean precision at IoU 0.5 (mAP@0.5), and 2.3% in mean precision at IoU 0.5–0.95 (mAP@0.5–0.95). Additionally, the number of parameters is reduced by 21.32%, GFLOPs are reduced by 26.98%, and FPS increases from 48.2 to 71.8. The FEDS-YOLOv11n model ensures high accuracy while maintaining lower computational complexity and faster inference speed, making it suitable for real-time forest fire detection applications.

The A* algorithm is widely used in mobile robot path planning; however, it faces challenges such as unsmooth planned paths, redundant nodes, and extensive search areas. This paper proposes a hybrid algorithm combining an improved A* algorithm with the Dynamic Window Approach. By quantifying grid obstacle data to extract environmental information and employing a grid-based environmental modeling method, the proposed approach enhances path smoothness at turns using second-order Bezier curve smoothing. It improves the heuristic function and child node selection process, applying these advancements in experimental path planning scenarios. A simulated 2D map was constructed using point cloud scanning in RViz to validate the hybrid algorithm through simulations and real-world outdoor tests. Experimental results demonstrate that, compared to the A* and DWA algorithms, the improved hybrid algorithm enhances search efficiency by 10.93%, reduces search node count by 32.26%, decreases the number of turning points by 36.36% and the value of turning angle by 34.83%, shortens the total path length by 22.05%, and improves overall path smoothness. Simulations and field tests confirm that the proposed hybrid algorithm is more stable, significantly reduces collision probability, and demonstrates its applicability for mobile robot localization and navigation in real-world environments.