A Prediction Algorithm for Lower Limb Movement Intention Based on Plantar Pressure

This paper proposes a lower limb motion intention prediction algorithm based on plantar pressure. First install the pressure sensors on the soles of the foot, install the IMUs to the lower limbs of the human body. At the same time, it collects plantar pressures information and motion information such as the angle and angular velocity of the lower limbs during walking; Then, the sliding window method is used to divide each prediction sample, and a prediction model based on CNN-LSTM is trained. The plantar pressure is used to predict the motion intention of the lower limbs at the current moment (the motion information collected by IMUs);Finally, this paper verifies the performance of the model. The test results show that through the lower limb motion intention to predict the algorithm designed in this paper, the plantar pressure sensors can replace the IMUs installed in the lower limbs, predict the current motion intention of the lower limbs of the human body, thereby reducing the number of sensors installation, reducing the complexity of the exoskeleton robot’s electrical system and mechanical structure.