Yazar "Canbek, Kansu Oguz" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    A multiple sensor fusion based drift compensation algorithm for mecanum wheeled mobile robots
    (Tubitak Scientific & Technological Research Council Turkey, 2021) Alhalabi, Abdulrahman; Ezim, Mert; Canbek, Kansu Oguz; Baran, Eray A.
    This paper investigates a multiple sensor fusion based drift compensation technique for a mecanum wheeled mobile robot platform. The mobile robot is equipped with high-precision encoders integrated to the wheels and four accelerometers placed on its chassis. The proposed algorithm combines the information from the encoders and the acceleration sensors to estimate the total drift in the acceleration dimension. The inner loop controller is designed utilizing a disturbance-observer-based acceleration control structure which is blind against the slipping motion of the wheels. The estimated drift acceleration from the sensor fusion is then mapped back to the joint space of the robot and used as additional compensation over the existing controllers. The proposed algorithm is tested on a series of experiments. The results of the experiments are also compared with those of a recent study in order to provide a benchmark evaluation. The enhanced tracking performance yielding towards smaller error magnitudes in the experiments illustrate the efficacy and success of the proposed control architecture in attenuating the positioning drift of mecanum wheeled robots.
  • Küçük Resim Yok
    Öğe
    Drift compensation of a holonomic mobile robot using recurrent neural networks
    (Springer Heidelberg, 2022) Canbek, Kansu Oguz; Yalcin, Hulya; Baran, Eray A.
    Mecanum wheeled robots can exhibit serious slippage problems because of the discontinuous contact between the wheels and the ground which negatively influences the overall navigation quality. Addressing this problem, the aim of this paper is to demonstrate how a learning-based method can be used for the estimation of the drifting error from multiple sensors with distinct measurement types. Here, a recurrent neural network (RNN)-based drift compensation algorithm is proposed for the estimation of the positioning drift. In order to improve the positioning performance in dead reckoning the estimated drift is used within the real-time control loop for proper modification of the motion trajectory. During the training phase, the data acquired from the acceleration sensors attached to the robot chassis and the encoders of the wheels of the robot are used as the main features to train a gated recurrent unit-based RNN. The drift estimator is trained using the computer-generated reference position data, and the response position data which is measured using an optoelectronic motion tracking device. The performance of the proposed learning-based drift estimation and control algorithm is validated through a series of experiments. The responses obtained from the experiments are graphically illustrated and the improvements in the positioning performances are numerically evaluated. The results obtained from the experiments illustrate the effective performance of the proposed algorithm by considerably decreasing the positioning errors.