First Intelligent Daylily Picking Robot Debuts in Datong, Shanxi

Deep News08-02 20:30

On July 28, a tracked daylily picking robot moved steadily through the daylily planting base in Tuofang Village, Yunzhou District, Datong, Shanxi. Farmers issued picking commands remotely via their mobile phones, and the robot's dual arms operated precisely, using specialized grippers to harvest daylilies and store them in a collection basket. The entire picking process for a single flower took less than five seconds.

Due to operational precision limitations, the robot uses a zonal harvesting mode, with a single fixed-point picking area of four square meters. "This marks the first daylily picking robot jointly developed by a university and enterprise to be put into field operation in Shanxi, meaning this provincial key R&D project has moved from the laboratory to real-world field testing," said Professor Zhang Yanjun, Deputy Dean of the School of Mechanical Engineering at Taiyuan University of Science and Technology. On the same day, a field application demonstration for the intelligent daylily picking robot was held in Tuofang Village, where technicians explained the robot's working principles and demonstrated the operational process. The research team also exchanged ideas with farmers and cooperative operators on key technologies like intelligent identification, precise positioning, and non-destructive picking.

Addressing the Industry's Core Challenge

Yunzhou District is known as the "Hometown of Daylilies" in China, with the crop being a pillar industry for local prosperity. However, daylily harvesting is extremely time-sensitive, involving high labor intensity and rising labor costs, leaving the sector facing a dilemma of "no machines available" for harvesting. "The picking period for daylilies is only about 40 days, mostly between 2:00 am and 8:00 am. You can only pick the buds that are about to open. Once sunlight hits them, they open, making them unsuitable for picking or significantly reducing their price," explained a farmer surnamed Wang. To ensure adequate moisture for growth, the fields are irrigated during the peak blooming period, making the harvesting work intensive and the environment challenging. This leads to difficulties in recruitment, high costs, and the abandonment of many daylilies due to a shortage of labor.

To tackle this industry pain point, the "Key Technology Research and Application Demonstration of Intelligent Daylily Picking Robots" project was approved as a key R&D project of Shanxi Province in 2023. Led by Taiyuan University of Science and Technology, and in collaboration with Shanxi Nonggu Modern Agricultural Equipment Technology Co., Ltd. and Shanxi Agricultural University, the team worked for nearly three years, achieving continuous breakthroughs in key technologies such as intelligent identification, precise positioning, and non-destructive picking, ultimately launching the first-generation daylily picking robot.

Core Technology and Advantages

The robot features four-dimensional precise visual positioning, path recognition and autonomous navigation capabilities on its chassis, and 5G communication, allowing farmers to monitor its status or issue picking commands via their phones. It is equipped with two parallel mechanism manipulators for collaborative operation, improving efficiency. The specialized gripper mimics the human side-picking method to ensure non-destructive harvesting. Professor Li Haihong from Taiyuan University of Science and Technology noted that the combination of four-dimensional vision, dual-arm coordination, and the specialized gripper enables the robot to "operate precisely" even in low-light conditions. During field demonstrations, the robot showcased several core technologies, with the four-dimensional precise visual positioning being a key highlight. Targeting the dark, humid, and complex field environment of early morning, the robot's two vision modules can output a four-dimensional picking point, including X, Y, and Z spatial coordinates and the blade entry angle, guiding the manipulators for precise, non-destructive harvesting.

Performance and Future Potential

The robot's dual-arm system operates collaboratively. An industrial computer uses algorithms to assign picking tasks to the two arms, performing path planning and posture calculation based on the four-dimensional positioning data to achieve efficient collaborative work. Currently, the picking speed is about 5 seconds per flower, with a target of no more than 2 seconds per flower in the future. In terms of power and endurance, the robot uses a tracked gantry-type electric chassis, suitable for navigating daylily fields. Solar panels on the roof charge the lithium battery during non-picking hours, eliminating the need to return to base. LED lights provide illumination for nighttime operation. Compared to manual picking, this robot offers clear advantages: a unified picking standard independent of human experience; fully unmanned operation with remote control; and the ability to work continuously during the day, preventing missed harvesting opportunities.

From 'No Machine' to 'Real Machine' in the Field

The intelligent daylily picking robot has taken its first step from "no machine available" to "real machine in the field." However, as a first-generation model, it has room for improvement. "It cannot operate in windy or rainy conditions, and the visual recognition algorithms, trajectory planning, and collaborative control algorithms still need further upgrades," Li Haihong admitted. He described the first-generation model as being "like a train just leaving the depot; subsequent acceleration and lane changes will depend on data running-in." Through field operation demonstrations and technical exchanges, the team has collected first-hand feedback data, which will drive continuous iterative upgrades in the future.

Disclaimer: Investing carries risk. This is not financial advice. The above content should not be regarded as an offer, recommendation, or solicitation on acquiring or disposing of any financial products, any associated discussions, comments, or posts by author or other users should not be considered as such either. It is solely for general information purpose only, which does not consider your own investment objectives, financial situations or needs. TTM assumes no responsibility or warranty for the accuracy and completeness of the information, investors should do their own research and may seek professional advice before investing.

Comments

We need your insight to fill this gap
Leave a comment