RoboCup 2016 Humanoid TeenSize Winner NimbRo: Robust Visual Perception and Soccer Behaviors

TL;DR

This paper presents the NimbRo team's advancements in visual perception and soccer behaviors for humanoid robots, addressing challenges posed by realistic environments like irregular surfaces and similar-colored goals, to improve RoboCup performance.

Contribution

The paper introduces new adaptations and developments in visual perception and soccer behaviors for humanoid robots in challenging, realistic RoboCup environments.

Findings

Successful implementation of robust visual perception on humanoid robots

Enhanced soccer behaviors for irregular surfaces and goal detection

Winning strategies demonstrated in RoboCup 2016 competition

Abstract

The trend in the RoboCup Humanoid League rules over the past few years has been towards a more realistic and challenging game environment. Elementary skills such as visual perception and walking, which had become mature enough for exciting gameplay, are now once again core challenges. The field goals are both white, and the walking surface is artificial grass, which constitutes a much more irregular surface than the carpet used before. In this paper, team NimbRo TeenSize, the winner of the TeenSize class of the RoboCup 2016 Humanoid League, presents its robotic platforms, the adaptations that had to be made to them, and the newest developments in visual perception and soccer behaviour.