Giter VIP home page Giter VIP logo

baxter_two's Introduction

About

A ROS project developed as part of ME495 - Embedded Systems in Robotics course at Northwestern University (NU).

To launch (in a ROS workspace), type in terminal:

cd ~/baxter_ws/
. baxter.sh
rosrun baxter_tools enable_robot.py -e
roslaunch baxter_two baxter_two.launch

Goal of Project

Use baxter to pick and place objects from one location to another

Tutorial

The following sections describe contents of this package and how to use them:

1. Prerequisites

The following packages need to be installed for baxter_two package to work:

  1. Baxter SDK - to be installed in baxter_ws/src directory
  2. MoveIt!
  3. moveit_python by Michael Ferguson - to be installed in baxter_ws/src directory
  4. Baxter Simulator - v1.1 (ONLY needed if NOT working with actual baxter robot)

2. Package Contents

The baxter_two package consists of following main files:

  • baxter_two.launch: A launch file that starts the following nodes:

    • joint_action_trajectory_server.py (required for MoveIt!)
    • MoveIt! with rviz
    • baxter_img.cpp
    • baxter_pnp.py
  • baxter_img.cpp: subscribes to the /cameras/right_hand_camera/image topic, calculates object locations using OpenCV tools, and publishes this information to baxter_pnp node via a PoseArray() message

  • baxter_pnp.py: subscribes to the topic (called Dpos) published by baxter_img, and calls PlanningSceneInterface and MoveGroupInterface classes from moveit_python bindings to add collision objects and move baxter's arms respectively

    • Allows both arms to be moved at the same time
    • Allows velocity scaling using max_velocity_scaling_factor
    • Uses baxter_interface for gripper control

3. Step-by-step guide

This section gives a step-by-step approach to run a successful baxter pick and place with this package.

  1. Items needed - a table of height ~ 0.6 m; square blocks (with green top surface); a baxter robot with electric parallel grippers; an ethernet cable (to connect baxter to computer)
  2. Set up networking with baxter
  3. Install the required packages as outlined in Prerequisites section
  4. Clone this package to your baxter_ws/src directory
  5. Source baxter.sh file, enable the robot, and launch baxter_two.launch as follows
cd ~/baxter_ws/
. baxter.sh
rosrun baxter_tools enable_robot.py -e
roslaunch baxter_two baxter_two.launch

4. rqt_graph

The following rqt_graph shows a ROS computation graph for baxter pick and place highlighting all important nodes and topics during operation:

Future Work

  • Camera Calibration: We are looking into improving the camera calibration. Currently, variations in surrounding lighting affect the object detection. Using more finely-tuned methods of calibrating the camera will minimize the lighting issue.

  • GUI Development: We are also looking to create a Graphical User Interface (GUI) that allows the user to click an object in the virtual world (e.g in Gazebo), and pick and place that particular object. This GUI is currently under development.

Team

baxter_two's People

Contributors

patilnabhi avatar vincemartinez avatar

Watchers

James Cloos avatar Chang-Yi Kuo 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.