In cut tobacco production line, the loosening and conditioning process is one of the most significant links affecting tobacco leaves quality. In order to solve the modeling difficulties of tobacco loosening and conditioning system due to time delay, strong coupling, nonlinearity and missing parameters, a data-driven model based on Long-Short-Term Memory networks is designed. Using the strong time series information learning ability and nonlinear fitting ability of the LSTM networks, it is trained only with the historical time series data of the outlet moisture and temperature of the loosening and conditioning cylinder, and the system model that can accurately predict the outlet moisture and temperature in output tobacco is obtained. The model predicts the output moisture and temperature values at the next time by inputting 60 consecutive historical output values. It is verified that the model has excellent fitting effect on both training set and verification set.

Reconfigurable robots have excellent reconfigurability and environmental adaptability, but the configuration design method to select appropriate configuration with different environments has not been fully studied. Most of the existing work is based on the known global environment information, or only focus on the structure design. How to effectively obtain rich terrain information for subsequent configuration design is the subject of this paper. In our work, a comprehensive method of obtaining robotic configuration is proposed which considering geometric information and semantic information of unstructured terrain. And it provides new possibilities for reconfigurable robots to perform autonomous tasks in complex scenarios. Results of simulation experiments prove the availability of the mentioned method.