Starkit: RoboCup Humanoid KidSize 2021 Worldwide Champion Team Paper

TL;DR

This paper discusses the development and evaluation of vision, mechanical, and algorithmic features for RoboCup Humanoid KidSize teams, including simulation aspects, between 2019 and 2021, highlighting innovations and performance analysis.

Contribution

It presents new approaches and insights into robot perception, mechanics, and algorithms, with a focus on virtual competition adaptations and performance evaluation.

Findings

Improved detection and localization methods

Mechanical and algorithmic innovations implemented

Performance analysis of various approaches

Abstract

This article is devoted to the features that were under development between RoboCup 2019 Sydney and RoboCup 2021 Worldwide. These features include vision-related matters, such as detection and localization, mechanical and algorithmic novelties. Since the competition was held virtually, the simulation-specific features are also considered in the article. We give an overview of the approaches that were tried out along with the analysis of their preconditions, perspectives and the evaluation of their performance.