Road parameter identification is of great significance for the active safety control of tracked vehicles and the improvement of vehicle driving safety. In this study, a method for establishing a prediction model of the engine output torques in tracked vehicles based on vehicle driving data was proposed, and the road rolling resistance coefficient was further estimated using the model. First, the driving data from the tracked vehicle were collected and then screened by setting the driving conditions of the tracked vehicle. Then, the mapping relationship between the engine torque , the engine speed , and the accelerator pedal position was obtained by a genetic algorithm–backpropagation (GA–BP) neural network algorithm, and an engine output torque prediction model was established. Finally, based on the vehicle longitudinal dynamics model, the recursive least squares (RLS) algorithm was used to estimate the . The experimental results showed that when the driving state of the tracked vehicle satisfied the set driving conditions, the engine output torque prediction model could predict the engine output torque in real time based on the changes in the and , and then the RLS algorithm was used to estimate the road rolling resistance coefficient . The average coefficient of determination of the was 0.91, and the estimation accuracy of the was 98.421%. This method could adequately meet the requirements for engine output torque prediction and real-time estimation of the road rolling resistance coefficient during tracked vehicle driving.
A position estimation method for unmanned tracked vehicles based on a steering dynamics model was developed during this study. This method can be used to estimate the position of a tracked vehicle in real time without relying on a high-precision positioning system. First, the relationship between the shear displacement of the track relative to the ground and the speed and yaw rate of the tracked vehicle during the steering process was analyzed. Next, the steering force of the tracked vehicle was calculated by using the shear force–displacement theory, and a steering dynamics model considering the acceleration of the vehicle was established. The experimental results show that this steering dynamics model produced more accurate position estimations for an unmanned tracked vehicle than did the kinematics model. This method can serve as a reference for the positioning of unmanned tracked vehicles working in special environments that cannot use precise positioning systems.