In recent years there has been remarkable advances in artificial intelligence domain, suchas computer vision, machine learning, autonomous driving and end-to-end learning. Theincrease of human need, the abundance of research, and the increased availability of com-puting power have also led to a better development in the robotics sector. As with any rapidlygrowing field, it is becoming increasingly difficult to stay up-to-date. The work in this pa-per is divided into theoretical and practical parts. Firstly, historically relevant literature ispresented, as well as current progress in several autonomous driving and computer visionsdomains, including object recognition, tracking and scene understanding. The performanceof several models in different challenges with the comparison data setKITTIis analyzed.In addition, future issues and related research challenges are discussed. The practical partis implemented by constructing an autonomous robot with end-to-end methodology thatcan drive without the help of an operator with the feed form the camera. An analysis ofthe robot design, operating principles and practical implementation will be provided. ThentheEffiecientNetnetwork model is implemented to deal with object detection task and theresults are analyzed and compared.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Dirbtinio intelekto kameros regėjimo sistema robotui automobiliui ; Artificial intelligence vision system for a robot vehicle



    Erscheinungsdatum :

    2021-06-01


    Medientyp :

    Hochschulschrift


    Format :

    Elektronische Ressource


    Sprache :

    Lithuanian , Englisch


    Klassifikation :

    DDC:    629