Zhejiang University

Jinfan Xu

Tao Lin

Yibin Ying

Zhixian Lin

Hao Jiang

K C Ting

Huanyu Jiang

Renhai Zhong

Kuan-Chong Ting

Guoqiang Ren

A robot with the perception capability of livestock and poultry information and a mapping approach based on autonomous navigation are disclosed. The robot includes a four-wheeled vehicle (), an autonomous navigation system, a motion module and an information acquisition module. The autonomous navigation system includes a LiDAR (), a RGB-D camera (), an inertial measurement unit (), an odometer and a main control module (). The information acquisition module includes two thermal imagers (), an environmental detection sensor module () and a wireless transmission module (). The robot is controlled in indoor working environment, and simultaneously information about surrounding environment during movement is obtained with the autonomous navigation system; positioning locations are obtained through data processing and a global map is constructed, which can improve positioning accuracy, reduce dependence on breeders, realize automatic environment detection. The present invention has the advantages of high efficiency, high economic benefits, and wide applicability.

Robot with perception capability of livestock and poultry information and mapping approach based on autonomous navigation

A crop yield estimation method based on spatio-temporal deep learning including: obtaining regional historical crop yield data and meteorological data, preprocessing the meteorological data and the yield data to respectively obtain meteorological parameters and a detrended yield as input and output of the crop yield spatio-temporal deep learning model; constructing the spatio-temporal deep learning model for crop yield estimation, and optimizing hyperparameters; and building a training set by taking the meteorological parameters as an input and the detrended yield as output to train the model and obtain parameters of the model; for the crop yield to be estimated, feeding meteorological parameters into the trained model, and obtaining the crop yield estimation result. The model combined temporal and spatial learning to achieve better crop yield estimation accuracy and stability at large spatial scales.

Crop yield estimation method based on deep temporal and spatial feature combined learning

Growing community of inventors

Zhejiang, China

Jinfan Xu