An Optimally Configured HP-GRU Model Using Hyperband for the Control of Wall Following Robot

Abstract

In this paper, we presented an autonomous control framework for the wall following robot using an optimally configured Gated Recurrent Unit (GRU) model with the hyperband algorithm. GRU is popularly known for the time-series or sequence data, and it overcomes the vanishing gradient problem of RNN. GRU also consumes less memory and is computationally more efficient than LSTMs. The selection of hyper-parameters of the GRU model is a complex optimization problem with local minima. Usually, hyper-parameters are selected through hit and trial, which does not guarantee an optimal solution. To come around this problem, we used a hyperband algorithm for the selection of optimal parameters. It is an iterative method, which searches for the optimal configuration by discarding the least performing configurations on each iteration. The proposed HP-GRU model is used on a dataset of SCITOS G5 robots with 24 sensors mounted. The results show that HP-GRU has a mean accuracy of 0.9857 and a mean loss of 0.0810, and it is comparable with other deep learning algorithms.

Adaptive Controller with PID, FOPID, and NPID Compensators for Tracking Control of Electric – Wind Vehicle

“…Therefore, the propulsion system has played a crucial role in determining how well an EV performs overall. The researchers concentrated on creating controls for the electric vehicle's propulsion system [22]- [26]. Two crucial parameters efficient performance and optimal energy management require thorough and targeted research.…”

Optimally configured Gated Recurrent Unit using Hyperband for the long-term forecasting of photovoltaic plant

“…Likewise, Gao et al, [21] used LSTM-RNN with fewer weather parameters to train the model and predicted PV power for spring, summer, autumn, and winter separately. Khan et al, [22] used GRU model for the control of wall-following robot.…”