Topic outline

  • General

  • Chapter 1 - Overview of RFID Sensor Technology


    Author: Boris Antić, Faculty of Technical Sciences, University of Novi Sad, Serbia

    This chapter introduces the RFID technology with emphasis on sensor applications and in particular on their applications in agriculture. The chapter provides an overview of the RFID systems based on their operating frequency, readout range, reader and tag power supply, data rates and prices. It further introduces the concept of the inverse RFID design and how various analogue and digital sensors can be developed using the RFID. Some state-of-the-art innovation is presented to demonstrate the current limits of the technology. In line with the SMART4ALL verticals, a special emphasis is given to agricultural applications and RFID incorporation into various EDGE systems that are not continuously online but that can be ad-hoc read out and powered up to fit the restrictions of the Customised Low-Energy Computing (CLEC) for CyberPhysical Systems (CPS) and the Internet of Things (IoT). Part of the presented material deals with some original research results obtained in various projects conducted by the chapter author at the University of Novi Sad, Serbia.

  • Chapter 2 - UAV platforms for semantic scene analysis in agricultural applications


    Author: Branko Brkljač, Faculty of Technical Sciences, University of Novi Sad, Serbia

    Motivated by recent trends in the field of embedded vision platforms, this chapter discusses potential of such solutions in providing foundations for the next generation of Cyber-Physical Systems (CPS). Improved capabilities and reduced price of these platforms will have profound effect on their everyday usage and applications. In comparison to speech and natural language processing, which have established speech recognition and machine translation applications as indispensable in many contemporary CPSs, the vision community is still searching for an application that would be so necessary and desirable to make most of the consumers buy specific vision hardware just to run it. That would be the ultimate proof of the core value of the technology in the market. Thus, also vision problems come with a longstanding tradition and history of numerous solutions, it is still hard to point out a single application that would incorporate many specific vision tasks into one device, and which would be ubiquitously useful and affordable to all (e.g. like smartphone has done in the fields of communication and personal computing). However, with development of new miniaturization technologies and spatial AI it is reasonable to expect that there will be more possibilities for designing CPS with capabilities of visual understanding of outdoor, dynamic and uncontrolled environments. One step in such direction are embedded vision platforms that besides powerful computing capabilities also provide multimodal perception, and thus improve the algorithm performance. As an example, a stereo depth perception in the context of new spatial AI platforms like OAK-D lite, and point out some possibilities for its improvement and integration into future CPS is discussed.

    The course participants are encouraged to first read the scientific paper before moving to the power point presentation and the videos clips.

  • Exercises


    Author: Tjark Schütte, Leibniz Institute for Agricultural Engineering and Bioeconomy e.V. (ATB), Engineering for Crop Production - Agromechatronics, Potsdam-Bornim, Germany

    These exercises contain a presentation on localising robots and transforming data in Robot Operating System (ROS), with the emphasis on how the RFID data could be read out and geo-tagged by robots in form of unmanned ground vehicles and/or drones. Possible both or either one of two scenarios are considered:

    scenario #1: we know where the robot is, but not the sensors,

    scenario #2: position of the sensors is known (e.g. from UAV imagery) but not the robot position with an option to use the RFID-sensors to update the position.

    The course participants are invited to solve practical tasks of collecting and geo-tagging the data in either scenario 1 or 2 on a simulated mobile robot on a virtual machine. The robot has movement primitives ready and the sensors provide the ROS messages. Scenario 1 is definitely the easier one, especially having in mind the restrictions intended for this course and the complexity of the localization theory.

    • Introduction to exercises

    • Overview of exercises - practical implementation in ROS File PDF document

      Tjark Schütte, Leibniz Institute for Agricultural Engineering and Bioeconomy e.V. Potsdam, Germany

    • The code for exercises

    • .devcontainer Folder
    • data Folder
    • launch Folder
    • results Folder
    • scripts Folder
    • .gitignore File
    • CMakeLists.txt File
    • package.xml File

    • About the code... Database
      Open in Dev Containers
      These study materials were originally created for the Infield Robotics Workshop of the VDI-Land.Technik / EurAgEng pre-conference. You can run the exercises directly on your own machine using a local ROS install, inside a VS-devcontainer, or using the VirtualBox VM template provided to course attendants.


      Table of Contents
      • Requirements
      • Installation
        • installation in a new catkin workspace
        • installation in an existing catkin workspace
        • installation using VS Code Devcontainer
      • Running the Excercises
      Requirements

      A system with setup ROS 1 Melodic or higher (tested for Melodic and Noetic)

      Installation

      Installation in a new catkin workspace


      exemplary installation using using catkin_make

      source your ROS installation (replace ROS_DISTRO with the ROS_DISTRO you are using (e.g. 'noetic')

      source /opt/ros/ROS_DISTRO/setup.bash

      create new catkin workspace

      mkdir -p ~/infield_robotics_ws/src

      switch into that workspace

      cd ~/infield_robotics_ws/src

      clone the repository with the tasks from above or git clone our alternative hub repository:

      (optional) clone the repository with the solutions (see below), or git clone our alternative hub repository:

      switch to workspace root folder

      cd ~/infield_robotics_ws

      build the workspace

      catkin_make

      Installation in an existing catkin workspace
      1. source your catkin workspace
      2. change directory into your workspaces src folder
      3. clone the reposistories
      4. build using catkin_make / catkin build
      Installation using Devcontainers (VS Code)


      NOTE: This option installs the workspace in a Docker container, unlike the above two options which install on your local system.

      A Devcontainer configuration is provided in this repo under .devcontainer for use within VS Code. Note: You will need to have Docker installed on your system in order to build and run the container.

          Install the Dev Containers extension for VS Code.
          From the remote connection window (found by clicking on the green icon at the bottom left of the VS Code window) choose "Reopen in Container"
          From the ~/infield_robotics_ws directory in a bash shell, build using catkin_make / catkin build

      The container will open in a pre-made ROS workspace directory with this respository cloned inside a src/ subdirectory, having already run the setup script for ROS.

      See here for more information about using Devcontainers in VS Code.

      Running the Exercises


      Open a terminal and source your catkin_ws and ROS installation

      ~/infield_robotics_ws/devel/setup.bash

      launch the data playback

      roslaunch infield_robotics_workshop workshop.launch

      open a second terminal and source your catkin_ws and ROS installation

      ~/infield_robotics_ws/devel/setup.bash

      run the tasks contained in the 'scripts' foulder (here the task1.py)

      rosrun infield_robotics_workshop task1.py

    • Solutions to exercises

    • scripts Folder
    • results Folder
    • CMakeLists.txt File
    • package.xml File

    • About solutions... Database

      These study materials were originally created for the Infield Robotics Workshop of the VDI-Land.Technik / EurAgEng pre-conference.

      For detailled documentation see https://github.com/ATB-potsdam-automation/infield_robotics_workshop.git