A technique is developed for vehicle navigation and control in the presence of obstacles. A potential function was devised that peaks at the surface of obstacles and has its minimum at the proper vehicle destination. This function is computed using a systolic array and is guaranteed not to have local minima. A feedfoward neural network is then used to control the steering of the vehicle using local potential field information. In this case, the vehicle is a trailer truck backing up. Previous work has demonstrated the capability of a neural network to control steering of such a trailer truck backing to a loading platform, but without obstacles. Now, the neural network was able to learn to navigate a trailer truck around obstacles while backing toward its destination. The network is trained in an obstacle free space to follow the negative gradient of the field, after which the network is able to control and navigate the truck to its target destination in a space of obstacles which may be stationary or movable.


    Access

    Access via TIB

    Check availability in my library


    Export, share and cite



    Title :

    Cascading a Systolic Array and a Feedforward Neural Network for Navigation and Obstacle Avoidance Using Potential Fields


    Contributors:

    Publication date :

    1991


    Size :

    23 pages


    Type of media :

    Report


    Type of material :

    No indication


    Language :

    English





    Unmodelled Obstacle Avoidance in Structured Environments Using Feedforward Neural Nets

    Delgado Romero, E. / Raimundez Alvarez, J. C. / International Federation of Automatic Control | British Library Conference Proceedings | 1998


    Robot navigation using velocity potential fields and particle filters for obstacle avoidance

    Necsulescu, Dan-Sorin / Bai, Jin / Sasiadek, Jurek | IEEE | 2015


    Autonomous Navigation and Obstacle Avoidance

    Berger, Jesse / Carson, Cory / Towhidnejad, Massood et al. | AIAA | 2009