Xirui Zhang

To address the limited endurance caused by the single power-supply mode of existing fixed rubber-tapping machines, this work proposes a vibration energy harvester (VEH) that couples two groove-modulated acoustic black hole (ABH) half-beams with a 1-3-2 piezoelectric composite material (PCM) by exploiting the ABH effect and piezoelectric effect. Preliminary self-excited vibration tests are conducted on fixed rubber-tapping machines installed on 22 rubber trees, followed by time-domain and power spectral density analyses. A groove-modulated ABH beam is designed and evaluated through finite-element time-domain simulations of stress, strain energy density (SED), and energy-flow concentration. Finite-element simulations of the VEH are then performed to investigate the effects of piezoelectric geometric parameters on energy harvesting. Finally, the 1-3-2 PCM and VEH prototype are fabricated and evaluated through fixed-frequency and field tests. The results show that the peak open-circuit voltage reaches 321.5 mV with the ABH structure, representing an approximately 6.0-fold increase in output relative to the structure without an ABH. Under loaded field conditions, the voltage peak and mean value reach 437.7 mV and 53.98 mV, respectively. The proposed device effectively harvests self-excited vibration energy and provides a reference for self-powered fixed rubber-tapping machines and endurance-oriented design.

Natural rubber harvesting remains highly dependent on manual labor, particularly during latex cup collection, which limits efficiency and increases operational costs. Intelligent robotic harvesting systems require accurate visual perception and reliable grasp point positioning under rubber plantation environments. However, latex cups are typically small, visually diverse, and often affected by adjacent latex drains, making detection and manipulation challenging for existing vision models. To address these challenges, this study proposed a lightweight vision-based framework for latex cup detection and grasp-point positioning in automated rubber harvesting. The proposed NRLC-YOLO is developed based on YOLO11n-seg by integrating a lightweight backbone, a local–global attention enhancement module, and a dynamic convolution strategy. In addition, a fast grasp-point positioning method is designed to determine the gripping center of latex cups, enabling stable robotic manipulation. As validated by experimental results, our model yields a mAP _@50–95 of 78.5%, which surpasses the baseline approach with fewer parameters and lower computational costs. The average error of the proposed grasp-point positioning scheme is measured at 8.08 pixels. Field experiments further demonstrate a grasping success rate of up to 93.3% under real plantation conditions. The proposed framework provides an efficient AI-enabled perception solution for automated latex cup harvesting and offers practical support for the development of intelligent rubber plantation management systems.

天然橡胶林行间通道狭窄、障碍物分布密集且路径安全裕度不足，对割胶机器人的林间导航能力提出了较高要求。针对该问题，提出一种改进的A*算法路径规划方法。首先采用Chebyshev距离作为启发函数优化节点搜索过程，并在路径生成后引入障碍物斥力后处理机制，对初始路径进行安全距离修正与平滑优化，然后构建全局路径规划与局部动态避障相结合的协同导航框架，最后实现机器人在胶林环境中的稳定行驶与定点停靠。仿真实验结果表明：改进算法生成的路径步数更少，且与障碍物保持更大的安全间距；定位精度实验对LIO-SAM算法进行了定量评估，采用绝对位姿误差与相对位姿误差进行统计分析，在天然橡胶林环境下其均方根误差分别为24.80和22.73 cm，定位过程稳定且无明显漂移。实地导航实验结果显示，定点纵向误差与定点横向误差的均方根误差均小于11.00 cm，平均停止误差约为5.00～6.00 cm。