Move like humans: End-to-end Gaussian process regression based target tracking control for mobile robots

In this paper, we address the problem of target tracking control for mobile robots with limited sensing range. An end-to-end Gaussian process regression learning control method is proposed to transfer the human control experiences to the controller. The end-to-end learning architecture directly learns the control mapping from the original sensing input space to the final control output space in an human-like manner. The non-parametric Gaussian process regression accurately transfers the complex human control experiences to the control model. In addition, realistic training data set are collected from human operators for the end-to-end control learning. The performance of the proposed target tracking control method is extensively evaluated on various real-world scenarios, experimental results have demonstrated the robustness, accuracy, and effectiveness of the proposed method.