top of page

Acerca de

Balance Board

Demo

Please view github for more video demos.

Overview

This is a ROS project developed as part of ME495 - Embedded Systems in Robotics course at Northwestern University.

​

The goal of this project is to control a ping-pong ball by using Franka Panda robot to manipulate a white board.Generally, there are two types of tasks that our controlling of ping-pong ball can be achieved:

  1. Follow a line trajectory drawn on a white board.

  2. Follow the path solved by our maze solver algorithm, with a maze drawn on a white board.

 

The project integrates two main portions. First part is the perception: we use real sense camera as our sensor to capture the transient positions of ball and board, and using OpenCV library processes the sensing images. Second part is the control: there are two PD controllers we are implementing to control the ping-pong ball following the target trajectory on the white board. The higher level control loop takes ball positions as input and outputs desired angles of corresponding two arm joints. Then the updated joint angles received by the low level control loop. By tuning PD gains, this loop is able to send desired efforts to robot arm through ros_control topic.

​

Team members:

Devesh Bhura, Davin Landry, Kevin Nella, Daelan Roosa, Haozhi Zhang

Architecture

Control Loop

For more details, please view my Github pages.
bottom of page