Using Convolutional Neural Networks in Robots with Limited Computational Resources: Detecting NAO Robots while Playing Soccer

The main goal of this paper is to analyze the general problem of using Convolutional Neural Networks (CNNs) in robots with limited computational capabilities, and to propose general design guidelines for their use. In addition, two different CNN based NAO robot detectors that are able to run in real-time while playing soccer are proposed. One of the detectors is based on the XNOR-Net and the other on the SqueezeNet. Each detector is able to process a robot object-proposal in ~1ms, with an average number of 1.5 proposals per frame obtained by the upper camera of the NAO. The obtained detection rate is ~97%.

[1]  Bora Uçar,et al.  On Two-Dimensional Sparse Matrix Partitioning: Models, Methods, and a Recipe , 2010, SIAM J. Sci. Comput..

[2]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Ali Farhadi,et al.  XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks , 2016, ECCV.

[4]  Daniele Nardi,et al.  A Deep Learning Approach for Object Recognition with NAO Soccer Robots , 2016, RoboCup.

[5]  Christopher R'e,et al.  Caffe con Troll: Shallow Ideas to Speed Up Deep Learning , 2015, DanaC@SIGMOD.

[6]  Hassan Foroosh,et al.  Sparse Convolutional Neural Networks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Andrew Zisserman,et al.  Speeding up Convolutional Neural Networks with Low Rank Expansions , 2014, BMVC.

[8]  Eugenio Culurciello,et al.  ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation , 2016, ArXiv.

[9]  Qiang Chen,et al.  Network In Network , 2013, ICLR.

[10]  Sven Behnke,et al.  Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition , 2010, ICANN.

[11]  Song Han,et al.  Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding , 2015, ICLR.

[12]  Forrest N. Iandola,et al.  SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size , 2016, ArXiv.

[13]  Yann LeCun,et al.  Fast Training of Convolutional Networks through FFTs , 2013, ICLR.

[14]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[15]  Stefan Wermter,et al.  Ball Localization for Robocup Soccer Using Convolutional Neural Networks , 2016, RoboCup.