An Optimally Configured HP-GRU Model Using Hyperband for the Control of Wall Following Robot
Open Access
- 22 February 2021
- journal article
- Published by ASCEE Publications in International Journal of Robotics and Control Systems
- Vol. 1 (1), 66-74
- https://doi.org/10.31763/ijrcs.v1i1.281
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.Keywords
This publication has 23 references indexed in Scilit:
- Obstacle Avoidance and Tracking Control of Redundant Robotic Manipulator: An RNN-Based Metaheuristic ApproachIEEE Transactions on Industrial Informatics, 2019
- New Design of Line Maze Solving Robot with Speed Controller and Short Path Finder AlgorithmInternational Review of Automatic Control (IREACO), 2019
- Power-Type Varying-Parameter RNN for Solving TVQP Problems: Design, Analysis, and ApplicationsIEEE Transactions on Neural Networks and Learning Systems, 2018
- Intelligent wall following control of differential drive mobile robot along with target tracking and obstacle avoidancePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Automatic navigation of wall following mobile robot using Adaptive Resonance Theory of Type-1Biologically Inspired Cognitive Architectures, 2015
- Controlling Wall Following Robot Navigation Based on Gravitational Search and Feed Forward Neural NetworkPublished by Association for Computing Machinery (ACM) ,2015
- Neural network approach to control wall-following robot navigationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Wall-Following Control of a Hexapod Robot Using a Data-Driven Fuzzy Controller Learned Through Differential EvolutionIEEE Transactions on Industrial Electronics, 2014
- Classification-based learning by particle swarm optimization for wall-following robot navigationNeurocomputing, 2013
- Investigating the Use of Bayesian Network and k-NN Models to Develop Behaviours for Autonomous RobotsPublished by Taylor & Francis Ltd ,2012