In response to the challenge posed by low recognition accuracy in rugged terrains with diverse topography as well as feature recognition agricultural settings, this paper presents an optimized version of the YOLOv5 algorithm alongside the development of a specialized laser weeding experimental platform designed for precise identification of corn seedlings and weeds. The enhanced YOLOv5 algorithm integrates the effective channel attention (CBAM) mechanism while incorporating the DeepSort tracking algorithm to reduce parameter count for seamless mobile deployment. Ablation tests validated this model’s achievement of 96.2% accuracy along with superior mAP values compared to standard YOLOv5 by margins of 3.1% and 0.7%, respectively. Additionally, three distinct datasets captured different scenarios, and their amalgamation resulted in an impressive recognition rate reaching up to 96.13%. Through comparative assessments against YOLOv8, the model demonstrated lightweight performance improvements, including a notable enhancement of 2.1% in recognition rate coupled with a marginal increase of 0.2% in mAP value, thus ensuring heightened precision and robustness during dynamic object detection within intricate backgrounds.

To realize the visual navigation of agricultural robots in the complex environment of orchards, this study proposed a method for fruit tree recognition and navigation based on YOLOv5. The YOLOv5s model was selected and trained to identify the trunks of the left and right rows of fruit trees; the quadratic curve was fitted to the bottom center of the fruit tree recognition box, and the identified fruit trees were divided into left and right columns by using the extreme value point of the quadratic curve to obtain the left and right rows of fruit trees; the straight-line equation of the left and right fruit tree rows was further solved, the median line of the two straight lines was taken as the expected navigation path of the robot, and the path tracing navigation experiment was carried out by using the improved LQR control algorithm. The experimental results show that under the guidance of the machine vision system and guided by the improved LQR control algorithm, the lateral error and heading error can converge quickly to the desired navigation path in the four initial states of [0 m, −0.34 rad], [0.10 m, 0.34 rad], [0.15 m, 0 rad] and [0.20 m, −0.34 rad]. When the initial speed was 0.5 m/s, the average lateral error was 0.059 m and the average heading error was 0.2787 rad for the navigation trials in the four different initial states. Its average driving was 5.3 m into the steady state, the average value of steady state lateral error was 0.0102 m, the average value of steady state heading error was 0.0253 rad, and the average relative error of the robot driving along the desired navigation path was 4.6%. The results indicate that the navigation algorithm proposed in this study has good robustness, meets the operational requirements of robot autonomous navigation in orchard environment, and improves the reliability of robot driving in orchard.