The Driver Time Memory Car-Following Model Simulating in Apollo Platform with GRU and Real Road Traffic Data

Algorithm 1

Pseudocode for the construction of the GRU-based CF model.

	GRU-based car-following model
	Input:
	Output:
(1)	Data normalization using MinMaxScaler.
(2)	The input is constructed as , The output is constructed as
(3)	The constructed data is divided into training set and testing set.
(4)	Modelling Sequential(), add GRU Layer and Dense Layer
(5)	Compiler model, loss function = “MSE,” optimizer = “Adam”
(6)	while model convergence do
(7)	Training model
(8)	end while
(9)	Test model