This paper presents a new method of learning visual docking skills for non-holonomic vehicles by direct interaction with the environment. The method is based on a reinforcement algorithm, which speeds up Q-learning by applying memory-based sweeping and enforcing the “adjoining property”, a filtering mechanism to only allow transitions between states that satisfy a fixed distance. The method overcomes some limitations of reinforcement learning techniques when they are employed in applications with continuous nonlinear systems, such as car-like vehicles. In particular, a good approximation to the optimal behaviour is obtained by a small look-up table. The algorithm is tested within an image-based visual servoing framework on a docking task. The training time was less than 1 hour on the real vehicle. In experiments, we show the satisfactory performance of the algorithm.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Learning visual docking for non-holonomic autonomous vehicles


    Contributors:


    Publication date :

    2008-06-01


    Size :

    1398353 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Learning Visual Docking for Non-Holonomic Autonomous Vehicles

    Martinez-Marin, T. / Duckett, T. | British Library Conference Proceedings | 2008


    Hybrid path planning for non-holonomic autonomous vehicles: An experimental evaluation

    Esposto, Francesco / Goos, Jorrit / Teerhuis, Arjan et al. | IEEE | 2017


    Elliptical trajectories for non-holonomic vehicles

    Bampi, F. / Scalzo, A. / Zaccaria, R. et al. | British Library Conference Proceedings | 2007


    Elliptical trajectories for non-holonomic vehicles

    Bampi, F. / Scalzo, A. / Zaccaria, R. et al. | IEEE | 2007


    Neural-network-based docking of autonomous vehicles

    Wong, J. / Nejat, G. / Fenton, R.G. et al. | IEEE | 2006