Chinese scientists created MASM-YOLO, a lightweight AI model that helps grazing robots detect cattle behaviors accurately in challenging grassland conditions.

Chinese researchers have developed MASM-YOLO, a lightweight AI model that enables grazing robots to accurately detect six key behaviors in beef cattle—such as feeding, resting, and locomotion—under tough grassland conditions including poor lighting and motion blur. The model, created by the Agricultural Information Institute of the Chinese Academy of Agricultural Sciences, uses advanced techniques to balance high accuracy with low computational needs, making it ideal for real-time use on mobile robots. It supports improved herd management by aiding in disease detection, breeding tracking, and calving prediction. The findings were published in Computers and Electronics in Agriculture.