Predictive and Control of Unmanned Vehicle Based on LSTM and PID Control
HAO Qihong
HAN Bin
Abstract：In order to predict and control the position of unmanned vehicle in transit,the information of the continuous time speed,direction and position of the unmanned vehicle are extracted. LSTM and PID are used to build the model. Data including speed,direction and position are entered as test training models. The predicted track and the actual track of the vehicle can be drawn using only the speed and direction test model. Whether there is a big error between the data with different noise and the model trained with normal data is analyzed and compared. The target position is entered and the model is used to train the theoretical con?trol of vehicle speed and direction. Then each control change to the vehicle position is simulated. The trajectory of the vehicle is drawn to simulate the control effect. Finally,whether it can be applied to the actual control of the unmanned vehicle is judged ac?cording to the running trajectory of the unmanned vehicle.
Keywords：LSTMPIDunmanned vehicleprediction and control
Publication Date：2019-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 2473-2477 )