By LIU MINGTAI in Changchun and ZHOU HUIYING |
China Daily |
Updated: 2026-07-08 08:49
In the race to modernize world agriculture, a crew of Chinese scientists and engineers has lately developed a self-propelled, synthetic intelligence-driven robotic that blasts weeds with high-energy lasers in milliseconds, eliminating the need for chemical herbicides.
Developed by means of a 20-million-yuan ($2.94 million) collaboration between Changchun University of Science and Technology and Ningbo Yibin Electronic Technology, the fourth-generation clever laser weeding robotic has accomplished its last discipline trials. It is scheduled to enter mass manufacturing by the tip of this 12 months.
“The robot utilizes laser technology, along with the capabilities of multipurpose unmanned ground vehicles, to accurately identify and locate weeds,” mentioned Wang Xiantao, a professor from the college and head of the analysis crew. “High-energy laser units are used for precise weeding and navigation technology enables the machine to follow a reasonable path.”
In 2023, the college fashioned a 10-member specialised R&D crew, composed of consultants in optics, mechanics, electronics and management. Chassis engineers had been recruited from the corporate.
The crew grew to become the primary in China to systematically develop laser weeding tools.
“At that time, the Ministry of Agriculture and Rural Affairs listed laser weeding technology as a shortfall project in China’s agricultural machinery, which relied on physical weeding,” Wang mentioned.
In November 2023, the crew accomplished the first-generation prototype, establishing the fundamental ideas of laser weeding.
In April 2024, they launched the second-generation towed discipline prototype outfitted with eight laser models, finishing information assortment underneath varied situations in cornfields and verifying the feasibility of discipline operations.
By September of the identical 12 months, the third-generation unbiased unmanned prototype was developed, reaching real-time measurement of weed peak in three dimensions, with dynamic positioning accuracy managed inside three millimeters.
In May 2025, the finalized fourth-generation pure electrical self-propelled weeding robotic accomplished a full chain of technological developments, with complete optimization of the optical path construction and the popularity management system.
The delay from AI recognition to laser placing has been decreased to lower than 10 milliseconds, with weed positioning accuracy enabling exact concentrating on of weed meristems for bodily ablation whereas the car continues to transfer, Wang mentioned.
“Based on AI visual recognition technology, it can instantly distinguish between crops and weeds,” mentioned Wang. “We have established data models for over 10 crops, including corn, soybeans and potatoes, with a crop recognition rate exceeding 99.5 percent.”
The laser weed cutter can attain speeds of up to 3.6 kilometers per hour, adjusting adaptively based mostly on weed density, he mentioned. It can clear 50,000 to 100,000 weeds per hour, greater than 50 occasions the effectivity of guide labor.
These technological achievements have led to the functions for seven nationwide invention patents, 4 of which have already licensed, establishing a very unbiased mental property portfolio.
Phasing out chemical substances
The black soil in Northeast China — one of many world’s 4 main black soil areas — is named the “panda of arable land” due to its excessive nutrient content material. However, long-term and intensive use of chemical herbicides has led to soil compaction and pesticide residue exceeding requirements, whereas guide weeding is inefficient and conventional mechanical weeding can harm crops.
In the provinces of Heilongjiang, Jilin and Liaoning, and the japanese a part of the Inner Mongolia autonomous area, the entire corn planting space exceeds 15.33 million hectares, with an estimated tools demand of 700,000 to 1.4 million models, Wang mentioned. “Once the laser cutter is implemented, it will form a 100-billion-yuan smart agricultural machinery industry,” he mentioned.
The crew plans to proceed advancing laser weeding know-how towards multi-sensor fusion, cloud platform clever administration and cluster collaborative operations.
Han Junhong in Changchun contributed to this story.
Contact the writers at [email protected]