Agricultural Robots: A Breakthrough in Fruit Harvesting and Recognition

Strategic Insights -

Research at Southwest University has made significant advancements in the field of agricultural robots, with a focus on automatic fruit identification and harvesting. A team of researchers has designed a human-robot collaborative picking robot that utilizes somatosensory interactive servo control. The robot system consists of four main parts: picking execution mechanism, hand information acquisition system, human-machine interaction interface, and human-robot collaborative picking strategy.

The researchers used a six-degree-of-freedom robotic arm as the picking execution mechanism, employing the D-H method for forward and inverse kinematic modeling. An inverse kinematic optimal solution selection method was proposed, taking into account mechanical interference, correctness, rationality, and smoothness of motion. The Leap Motion controller was used for hand information acquisition, collecting and analyzing data from three types of hand movements. A spatial mapping method was also developed to achieve a direct correspondence between the Leap Motion interaction space and the operating range of the robotic arm.

The test results showed that the average response time of the double-click picking command was 332 ms, while the average time consumption for somatosensory control targeting was 6.5 s. The accuracy rate of the picking gesture judgment was 96.7%. This breakthrough has significant implications for the agricultural industry, enabling more efficient and accurate fruit harvesting.

Key Takeaways:

  • The research team designed a human-robot collaborative picking robot using somatosensory interactive servo control, which demonstrates a significant breakthrough in agricultural robotics.
  • The robot system consists of four main parts: picking execution mechanism, hand information acquisition system, human-machine interaction interface, and human-robot collaborative picking strategy.
  • The picking execution mechanism used a six-degree-of-freedom robotic arm, employing the D-H method for forward and inverse kinematic modeling.
  • An inverse kinematic optimal solution selection method was proposed to ensure accurate and smooth motion of the robotic arm.
  • The Leap Motion controller was used for hand information acquisition, collecting data from three types of hand movements.
  • A spatial mapping method was developed to achieve a direct correspondence between the Leap Motion interaction space and the operating range of the robotic arm.
  • The test results demonstrated that the average response time of the double-click picking command was 332 ms, while the average time consumption for somatosensory control targeting was 6.5 s.
  • The accuracy rate of the picking gesture judgment was 96.7%.

Statistics:

  • 332 ms - Average response time of the double-click picking command
  • 6.5 s - Average time consumption for somatosensory control targeting
  • 96.7% - Accuracy rate of the picking gesture judgment
  • 2025 - Year in which the research was conducted
  • 12(2):190-207 - Page numbers of the journal article in Frontiers of Agricultural Science and Engineering

Sources:

  • Design and control algorithm of a motion sensing-based fruit harvesting robot. Frontiers of Agricultural Science and Engineering, 2025, 12(2):190-207.
  • Higher Education Press. (Publisher for Frontiers of Agricultural Science and Engineering)
  • https://doi-org.sdpl.idm.oclc.org/10.15302/J-FASE-2024588 (Free version of the journal article)
  • Southwest University
  • National Citrus Engineering Research Center
  • Chongqing Key Laboratory of Agricultural Equipment for Hilly and Mountainous Regions, College of Engineering and Technology, Southwest University
  • Yuhang Chen, Hui Li, Pei Wang (Co-authors of the research)
  • NewsRx LLC (Publisher of the news article)
  • NewsRx. Study Findings from Southwest University Broaden Understanding of Agricultural Robots (Design and control algorithm of a motion sensing-based fruit harvesting robot). Information Technology Newsweekly. June 10, 2025; p 1009.