Git Product home page Git Product logo

kinect_based_arm_tracking's Introduction

Demo Description
    This is a demo that makes baxter to mimic the arm motion of a human.It use a package, openni_tracker, to get the data of a human body, which is in fact some tf frames related to the camera.Then, it translates these frames to arm angles, which are used to control the baxter.

What we need
    baxter robot(real or in gazebo)
    microsoft kinect

How to use this demo
    We had some problems in working with the openni in the first place, which showed some errors when we tried to use openni to connect the kinect.Then, following the solution of BastiAB in this website:
            ros-drivers/openni_tracker#9 (comment)
    We make it work 
    
    Here are the steps we take to run the demo:
        1.follow the instructions of BastiAB in 
            ros-drivers/openni_tracker#9 (comment)
        2.connect the kinect to your PC    
        3.open a terminal, run:
                roslaunch openni_launch openni.launch 
          this command will use openni to connect to the kinect
          
          then, open a terminal, run:
                rosrun openni_tracker openni_tracker 
          this command will run the tracker code and thus generate skeletons of human bodies.
          
        4.open a terminal, run:
                rosrun rviz rviz
          when rviz is launched, choose "openni_depth_frame" in Fixed Frame, add TF to display.
          You should see a least one skeleton of a human body now. 
          If nothing shows, make sure some one stands in front of the kinect.
        5.choose the index of the body you want to track in rviz.
          open our puber code, change the value of "user_index"
          
          for example:
            we want to tract the person with 'head_1', 
            then we change the value of "user_index" to be '1' in tf_listen_v8_puber.py
          
          now, open a terminal, run:
                rosrun [package_name] tf_listen_v8_puber
          this command will make our puber run.
          the puber is used to receive and smooth the data of the tracked body, then publish them.
        6.open a terminal, run:
                rosrun [package_name] tf_listen_v8_controller
          this command will make our controller run.
          it subscribes to the topics of smoothed data published by our puber, and controls the baxter accordingly.
        7.now move your arms in front of the kinect, and the baxter will mimic you!

Demo Video Link
    https://www.youtube.com/watch?v=U5lJFFy4i3A


Feel free to ask or comment!(this may be a bad "read me", grammatically)

kinect_based_arm_tracking's People

Contributors

seanshi007 avatar

Stargazers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.