Abstract
In this paper, we propose a multi-stage genetic algorithm that allows to automatically initialize deep multilayer perceptron neural network models to train it for prediction of robot execution failures. The proposed genetic algorithm system is divided on three stages, the first stage consists of initializing number of hidden layers. The second stage aims to fix number of neurons in each hidden layer. The final stage generates the activation function and the optimizer used to train neural network models. The next step is the application of the generated neural network models to predict robot execution failures. The aim of this approach is giving a robot many models so it can better take a more precise decision, since there is no scientific method to choose neural network model, genetic algorithm allows to generate many models automatically. Results obtained in this study show the efficiency of deep neural networks on robotic failures detection, as well as the efficiency of genetic algorithms to generate different models automatically which prevent the manual setup.
Similar content being viewed by others
References
Michalewicz Z, Fogel DB (2013) How to solve it: modern heuristics. Springer, Berlin
Binitha S, Sathya SS (2012) A survey of bio inspired optimization algorithms. Int J Soft Comput Eng 2(2):137–151
Abraham A, Grosan C, Ramos V (eds) (2007) Swarm intelligence in data mining, vol 34. Springer, Berlin
Holland JH (1992) Genetic algorithms. Sci Am 267(1):66–73
Kapela R, Świetlicka A, Kolanowski K, Pochmara J, Rybarczyk A (2017) A set of dynamic artificial neural networks for robot sensor failure detection. IEEE, pp 199–204
Alishev N, Lavrenov R, Hsia KH, Su KL, Magid E (2018) Network failure detection and autonomous return algorithms for a crawler mobile robot navigation. IEEE, pp 169–174
Park D, Hoshi Y, Kemp CC (2018) A multimodal anomaly detector for robot-assisted feeding using an lstm-based variational autoencoder. IEEE Robot Autom Lett 3(3):1544–1551
Dewantara BSB, Ardilla F (2018) Self monitoring, failure-detection and decision-making system to support E-trashbot (EEPIS trash bin robot) operations: preliminary report. IEEE, pp 1–6
Inceoglu A, Ince G, Yaslan Y, Sariel S (2018) Comparative assessment of sensing modalities on manipulation failure detection. In: IEEE ICRA workshop on perception, inference and learning for joint semantic, geometric and physical understanding
Kaveti P, Singh H (2019) ROS rescue: fault tolerance system for robot operating system. arXiv:1910.01078
Furukawa JI, Noda T, Teramae T, Morimoto J (2017) Human movement modeling to detect biosignal sensor failures for myoelectric assistive robot control. IEEE Trans Robot 33(4):846–857
Miriyala SS, Mittal P, Majumdar S, Mitra K (2016) Comparative study of surrogate approaches while optimizing computationally expensive reaction networks. Chem Eng Sci 140:44–61
Miriyala SS, Mitra K (2020) Deep learning based system identification of industrial integrated grinding circuits. Powder Technol 360:921–936
Miriyala SS, Subramanian VR, Mitra K (2018) TRANSFORM-ANN for online optimization of complex industrial processes: casting process as case study. Eur J Oper Res 264(1):294–309
Inapakurthi RK, Miriyala SS, Mitra K (2020) Recurrent neural networks based modelling of industrial grinding operation. Chem Eng Sci 219:115585
Pantula PD, Miriyala SS, Mitra K (2017) KERNEL: enabler to build smart surrogates for online optimization and knowledge discovery. Mater Manuf Process 32(10):1162–1171
Hinton G, Srivastava N, Swersky K (2012) Neural networks for machine learning lecture 6a overview of mini-batch gradient descent. Cited on 14(8)
Duchi J, Hazan E, Singer Y (2011) Adaptive subgradient methods for online learning and stochastic optimization. J Mach Learn Res 12:2121–2159
Sammut C, Webb GI (2011) Encyclopedia of machine learning. Springer, Berlin
McMahan HB, Holt G, Sculley D, Young M, Ebner D, Grady J, Chikkerur S (2013) Ad click prediction: a view from the trenches, pp 1222–1230
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
All authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Rahmani, M.E., Amine, A. & Fernandes, J.E. Multi-stage Genetic Algorithm and Deep Neural Network for Robot Execution Failure Detection. Neural Process Lett 53, 4527–4547 (2021). https://doi.org/10.1007/s11063-021-10610-x
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-021-10610-x