Driving Mobile Robots using a Deep LSTM Architecture: An Experimental Approach
Keywords:LSTM, Mobile Robots, Deep Learning
Driving mobile robots is defined as to move a robot to his goal without colliding with obstacles, quickly and with no deviations along the planned way. This process requires a trained, skilled and with expertise pilot to performing it. Among the various techniques available which help to drive mobile robots, many of them are based on the use of deep learning approaching. This work presents a new proposal model using a deep Long-Short Term Memory (LSTM) architecture to assist the driving activities in mobile robots, using as a main source, learning extracted from an expert pilot. The main contributions are i) a new model architecture for the deep LSTM; ii) a new information data fusion strategy in the guidance command stage; and iii) exhaustive tests in scenarios using a real mobile robot.