Comparing CNN inputs for terrain classification using simulation
Mobile robots frequently operate in rough, uneven terrain. One way for them to identify easier to traverse paths is to use deep learning methods, such as a convolutional neural network (CNN). It is not clear, however, what input should be provided to the CNN to best enable it to classify different terrain. In this study, we investigate and compare several input formats for improving terrain classification using a CNN. All experiments take place in simulation, where we have complete control over terrain (e.g., shapes and textures) and information about our robot. Our experiments lead us to the following conclusions: (1) input formats should prefer grayscale over color images as color has a tendency to overfit the training data and (2) disparity maps also improve classification compared with raw image data. These results can be used to improve the performance of terrain classification; particularly as they apply to transformable-wheel robots.
Deep learning, Mobile robotics, Transformable robotics
Clark, Anthony, Jesse Simpson, and Jared Hall. "Comparing CNN Inputs for Terrain Classification using Simulation." In 2019 First International Conference on Transdisciplinary AI (TransAI), pp. 43-47. IEEE, 2019.