Welcome to the InfoSci Platform
Reference Hub1
Enhanced Footsteps Generation Method for Walking Robots Based on Convolutional Neural Networks

Enhanced Footsteps Generation Method for Walking Robots Based on Convolutional Neural Networks

Sergei Savin, Aleksei Ivakhnenko
Copyright: © 2019 |Pages: 24
ISBN13: 9781522578628|ISBN10: 1522578625|EISBN13: 9781522578635
DOI: 10.4018/978-1-5225-7862-8.ch002
Cite Chapter Cite Chapter

MLA

Savin, Sergei, and Aleksei Ivakhnenko. "Enhanced Footsteps Generation Method for Walking Robots Based on Convolutional Neural Networks." Handbook of Research on Deep Learning Innovations and Trends, edited by Aboul Ella Hassanien, et al., IGI Global, 2019, pp. 16-39. https://doi.org/10.4018/978-1-5225-7862-8.ch002

APA

Savin, S. & Ivakhnenko, A. (2019). Enhanced Footsteps Generation Method for Walking Robots Based on Convolutional Neural Networks. In A. Hassanien, A. Darwish, & C. Chowdhary (Eds.), Handbook of Research on Deep Learning Innovations and Trends (pp. 16-39). IGI Global. https://doi.org/10.4018/978-1-5225-7862-8.ch002

Chicago

Savin, Sergei, and Aleksei Ivakhnenko. "Enhanced Footsteps Generation Method for Walking Robots Based on Convolutional Neural Networks." In Handbook of Research on Deep Learning Innovations and Trends, edited by Aboul Ella Hassanien, Ashraf Darwish, and Chiranji Lal Chowdhary, 16-39. Hershey, PA: IGI Global, 2019. https://doi.org/10.4018/978-1-5225-7862-8.ch002

Export Reference

Mendeley
Favorite

Abstract

In this chapter, the problem of finding a suitable foothold for a bipedal walking robot is studied. There are a number of gait generation algorithms that rely on having a set of obstacle-free regions where the robot can step to and there are a number of algorithms for generating these regions. This study breaches the gap between these algorithms, providing a way to quickly check if a given obstacle free region is accessible for foot placement. The proposed approach is based on the use of a classifier, constructed as a convolutional neural network. The study discusses the training dataset generation, including datasets with uncertainty related to the shapes of the obstacle-free regions. Training results for a number of different datasets and different hyperparameter choices are presented and showed robustness of the proposed network design both to different hyperparameter choices as well as to the changes in the training dataset.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.