RoboCup 2016 Humanoid TeenSize Winner NimbRo: Robust Visual Perception and Soccer Behaviors
This work solves incremental improvements in robot soccer for competition teams, focusing on adapting to rule changes and environmental conditions.
The paper addresses the challenges of visual perception and walking on irregular surfaces in the RoboCup Humanoid League, presenting adaptations and developments that led team NimbRo to win the 2016 TeenSize class.
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.