# Star Lightweight Convolution and NDT-RRT: An Integrated Path Planning Method for Walnut Harvesting Robots

## TL;DR

This paper introduces a new method combining lightweight detection and path planning for walnut harvesting robots to improve speed and accuracy in orchards.

## Contribution

The integration of star-shaped convolution and NDT-RRT for real-time, lightweight detection and path planning in agricultural robots.

## Key findings

- YOLO-FW achieves 90.6% precision, 90.4% recall, and 95.7% mAP@0.5 with a 3.62 MB model size.
- NDT-RRT reduces search time by 87.71% while maintaining path quality.
- The system shows robustness and real-time performance in real orchard environments.

## Abstract

To address issues such as slow response speed and low detection accuracy in fallen walnut picking robots in complex orchard environments, this paper proposes a detection and path planning method that integrates star-shaped lightweight convolution with NDT-RRT. The method includes the improved lightweight detection model YOLO-FW and an efficient path planning algorithm NDT-RRT. YOLO-FW enhances feature extraction by integrating star-shaped convolution (Star Blocks) and the C3K2 module in the backbone network, while the introduction of a multi-level scale pyramid structure (CA_HSFPN) in the neck network improves multi-scale feature fusion. Additionally, the loss function is replaced with the PIoU loss, which incorporates the concept of Inner-IoU, thus improving regression accuracy while maintaining the model’s lightweight nature. The NDT-RRT path planning algorithm builds upon the RRT algorithm by employing node rejection strategies, dynamic step-size adjustment, and target-bias sampling, which reduces planning time while maintaining path quality. Experiments show that, compared to the baseline model, the YOLO-FW model achieves precision, recall, and mAP@0.5 of 90.6%, 90.4%, and 95.7%, respectively, with a volume of only 3.62 MB and a 30.65% reduction in the number of parameters. The NDT-RRT algorithm reduces search time by 87.71% under conditions of relatively optimal paths. Furthermore, a detection and planning system was developed based on the PySide6 framework on an NVIDIA Jetson Xavier NX embedded device. On-site testing demonstrated that the system exhibits good robustness, high precision, and real-time performance in real orchard environments, providing an effective technological reference for the intelligent operation of fallen walnut picking robots.