Pulse graph neural network tactile object identification method based on graph learning

The invention provides a pulse graph neural network tactile object recognition method based on graph learning, and the algorithm comprises the steps: obtaining a tactile graph, and constructing an M-tree tactile graph or a Z-tree tactile graph based on the tactile graph; an object recognition model is established, the M-tree touch image or the Z-tree touch image is used for training the object recognition model, and the object recognition model comprises LIF spiking neurons, a topological adaptive image convolution layer, a full connection layer and a final voting layer; performing weighting by using Gaussian prior distribution loss and back propagation training loss of an object recognition model of LIF spiking neurons, and then optimizing the object recognition model; and judging the category of the touch object by using the optimized object recognition model. According to the method, the Gaussian prior distribution loss and the back propagation training loss of the LIF spiking neuron object recognition mod