Hostname: page-component-7b7567c8c-7pwfn Total loading time: 0 Render date: 2026-11-16T22:48:18.176Z Has data issue: false hasContentIssue false

Localization and obstacle avoidance in soccer competition of humanoid robot by gait and vision system

Published online by Cambridge University Press:  20 November 2019

Shu-Yin Chiang*
Affiliation:
Department of Information and Telecommunications Engineering, Ming Chuan University, 5 De Ming Road, Gui Shan District, Taoyuan City 333, Taiwan; e-mail: sychiang@mail.mcu.edu.tw
Jia-Huei Lu
Affiliation:
Department of Information and Telecommunications Engineering, Ming Chuan University, 5 De Ming Road, Gui Shan District, Taoyuan City 333, Taiwan; e-mail: sychiang@mail.mcu.edu.tw
Rights & Permissions [Opens in a new window]

Abstract

In this study, we designed a localization and obstacle avoidance system for humanoid robots in the Federation of International Robot-soccer Association (FIRA) HuroCup united soccer competition event. The localization is implemented by using grid points, gait, and steps to determine the positions of each robot. To increase the localization accuracy and eliminate the accumulated distance errors resulting from step counting, the localization is augmented with image pattern matching using a system model. The system also enables the robot to determine the ball’s position on the field using a color model of the ball. Moreover, to avoid obstacles, the robots calculate the obstacle distance using data extracted from real-time images and determine a suitable direction for movement. With the integration of this accurate self-localization algorithm, ball identification scheme, and obstacle avoidance system, the robot team is capable of accomplishing the necessary tasks for a FIRA soccer game.

Information

Type
Research Article
Copyright
© Cambridge University Press, 2019 
Figure 0

Figure 1Field of the FIRA HuroCup united soccer competition

Figure 1

Figure 2Regions in which white-line information is available

Figure 2

Figure 3DARwIn-OP servomotor numbering and positions

Figure 3

Figure 4Total foot trajectory of a robot for one step

Figure 4

Figure 5Relationship between steps and distances for X- and Y-axis

Figure 5

Figure 6Grid with a 50 × 60 mesh in the X-and Y-axes for self-localization of the robot

Figure 6

Figure 7A total of 320 scan lines are applied to calculate the distance from the first white-line pixel to the bottom

Figure 7

Figure 8Comparison of the range of the system model line and the estimated robot position

Figure 8

Figure 9Ball color model

Figure 9

Figure 10Relationship of the ball image pixel size versus distance to the robot

Figure 10

Figure 11Coordinate and angle

Figure 11

Figure 12Ball position at different coordinates

Figure 12

Figure 13Focus area and the distances of the obstacle, dy and dx

Figure 13

Table 1Positioning by counting steps

Figure 14

Figure 14Five test points to verify the localization method based on step counting

Figure 15

Table 2Positioning by step counting

Figure 16

Figure 15Exp. 1 for localization by image pattern matching with system model

Figure 17

Figure 16Exp. 2 for localization by image pattern matching with system model

Figure 18

Figure 17Exp. 3 for localization by image pattern matching with system model

Figure 19

Table 3Positioning by image pattern matching

Figure 20

Figure 18The robot avoids the obstacles and kicks the ball to the goal