Improved Robotics Algorithm for Fruit-Picking Tasks

Strategic Insights -

Research at Chongqing Three Gorges University in China has led to the development of an advanced algorithm for robotics, specifically for fruit-picking tasks in unstructured orchard environments. The new algorithm, called CAM-SCSO, improves upon earlier methods by incorporating a chaos-opposition strategy, adaptive differential perturbation, and a multi-angle hybrid localization strategy. This enhanced algorithm has been shown to achieve superior accuracy, speed, and stability, demonstrating a 23.59% reduction in motion time using the Xarm6 six-axis robotic arm.

Key Takeaways:

  • The CAM-SCSO algorithm is designed for time-optimal trajectory planning of a fruit-picking robotic arm operating in unstructured orchard environments.
  • The algorithm addresses the limitations of the original SCSO by incorporating a chaos-opposition strategy, adaptive differential perturbation, and a multi-angle hybrid localization strategy.
  • CAM-SCSO has been shown to achieve the best performance on 90% of the benchmark functions on the CEC2022 test suite, demonstrating superior accuracy, speed, and stability.
  • The algorithm was validated through simulations in MATLAB/ROS and physical tests in a fruit tree environment, showing a 23.59% reduction in motion time using the Xarm6 six-axis robotic arm.
  • The research was funded by the National Key R&D Program of China, Natural Science Foundation of Chongqing, and the Scientific and Technological Research Program of Chongqing Municipal Education Commission.
  • The improved algorithm is expected to enhance the efficiency and effectiveness of fruit-picking robotic arms in unstructured orchard environments.

Statistics:

  • 90% of benchmark functions achieved best performance on the CEC2022 test suite.
  • 23.59% reduction in motion time achieved using the Xarm6 six-axis robotic arm.
  • 5 research institutions contributed to this study: Chongqing Three Gorges University, Chongqing Key Laboratory of Geoenvironment Monitoring and Disaster Early Warning of Three Gorges Reservoir Area, National Key R&D Program of China, Natural Science Foundation of Chongqing, and Scientific and Technological Research Program of Chongqing Municipal Education Commission.
  • The research involved 7 authors: Qiang Chen, Peng Yang, Binbin Zhou, Lv Yunpeng, Hongbing Li, Siqi Zhu, Siyun Tan, and Chunzhe Zhao.

Sources:

  • Cam-scso: Robotic Arm Trajectory Planning Based On Multi-strategy Improved Sand Cat Swarm Algorithm. The Journal of Supercomputing, 2025;81(15).
  • Journal of Engineering.
  • Chongqing Three Gorges University.
  • Qiang Chen, Chongqing Three Gorges University, Chongqing Key Lab Geol Environm Monitoring & Disas, Chongqing 404120, People's Republic of China.