Using Convolutional Neural Networks in Robots with Limited Computational Resources: Detecting NAO Robots while Playing Soccer
This work addresses the problem of real-time object detection for robots in resource-constrained environments, such as soccer-playing NAO robots, though it is incremental as it applies existing methods like XNOR-Net and SqueezeNet to a specific domain.
The paper tackled the challenge of deploying Convolutional Neural Networks on robots with limited computational resources, specifically for detecting NAO robots in soccer, achieving a detection rate of ~97% with real-time processing of ~1ms per proposal.
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%.