Author: Yu Hang He Email: hey6@unlv.nevada.edu
Date: Last modified on <09/12/17>

The HuroCup Sprint challenge is a sprint competition for humanoid robots. The rule of competition is for robot to sprint as fast as possible from a start line to a goal line, then backpedal to the start line. The track dimension is 300cm by 80cm and a visual marker can be placed inside goal zone. More detailed rule can be found here. The goal of this project is to use DARWIN-OP 2 to complete HuroCup Sprint challenge. The schedule below is a tentative outline of project timeline.

This tutorial will demonstrate how to add a new mode to Darwin OP 2's demo program. The new mode will be added alongside Autonomous Soccer, Interactive Motion, and Vision Processing mode. Use mode button on the back of Darwin OP 2 to cycle through modes and press start button to start the new mode. Tutorial for adding new mode .

This tutorial will demonstrate how to use vision processing capability on Darwin OP 2 to detect and track color. Darwin OP 2 have computer vision that can detect multiple colors and return x and y center position of those colors. A second class will move camera to keep track of color based on x and y position. For more detail, follow this tutorial for color detection and camera tracking .

This tutorial will demonstrate how to program Darwin to walk towards a target. The tutorial will incorporate materials from previous two sections: How to Add a New Mode to Darwin OP 2 and How to Use Darwin OP 2's Computer Vision. The target is consisted of two 20cm by 20cm panels, colored green and blue, perpendicular to each other. Tutorial for walking toward target.

This tutorial will demonstrate how to program Darwin OP 2 to walk backward. The walking algorithm for backward motion is included in Darwin OP 2's source code by Robotis. However, there is no on-line, or barely any, documentation of this process. This tutorial will provide some insight into the process. How to Program Darwin OP 2 to Walk Backward

This tutorial will demonstrate how to program Darwin OP 2 to walk backward while guided by computer vision. In previous tutorial, tutorial for walking toward target, we used BallFollower class to target the marker. However, the BallFollower class will only work with forward motion. This tutorial will provide some insight into the process of program Darwin OP 2 to walk backward with computer vision. How to Program Darwin OP 2 to Walk Backward with CV

01. 09/11/17

A. Post one-page summary of papers on walking algorithm for humanoid robot
B. Post a ½ page summary of papers published by previous winning teams for this challenge

02. 09/18/17

A. Build a mock-up track
B. Program DARWIN-OP 2 to walk for set distance in straight line
C. Post ½ page summary on difference between walking and sprinting for humanoid robot

03. 09/25/17

A. Program the robot to sprint for set distance in straight line
B. Write a tutorial on walking algorithm currently on the robot and how to manipulate its parameters for sprinting

04. 10/02/17

A. Post one-page summary of papers on backpedaling for humanoid robot
B. Program the robot to backpedal

05. 10/09/17

A. Test and improve on the program for backpedaling
B. Write a tutorial on how to program the robot to backpedal

06. 10/16/17

A. Post one-page summary on computer vision (CV) available on the robot
B. Program the robot to use CV to recognize marked target

07. 10/23/17

A. Program the robot to walk toward marked target
B. Write a tutorial on how to use CV on the robot

08. 10/30/17

A. Use CV to steer while the robot is sprinting towards goal line
B. Use CV to steer while the robot is backpedaling towards start line

09. 11/06/17

A. Implement sprint, backpedal, and CV to complete HuroCup Sprint challenge
B. Test and improve the final program

10. 11/13/17

A. Test and improve the final program.
B. Get ready for demonstration.

By the end of 10 weeks period, I will finish a program that will accomplish HuroCup Sprint challenge. Maybe not breaking the competition records but at least completing the challenge.