日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

群制御arXiv:2402.00031

FIRSTロボティクス競技におけるチーム編成と勝敗予測の統合フレームワーク:モデル・アルゴリズム・分析

An Integrated Framework for Team Formation and Winner Prediction in the FIRST Robotics Competition: Model, Algorithm, and Analysis

シェア:XThreadsFacebookLINEはてブBluesky

FIRSTロボティクス競技を対象に、チーム全体の成績から個人スキルを推定し、アライアンス編成の最適化と深層学習による勝敗予測を行う統合手法を提案した。

著者: Federico Galbiati, Ranier X. Gran, Brendan D. Jacques, Sullivan J. Mulhern, Chun-Kit Ngan

分類: cs.LG, cs.AI, cs.RO

原文アブストラクト

This research work aims to develop an analytical approach for optimizing team formation and predicting team performance in a competitive environment based on data on the competitors' skills prior to the team formation. There are several approaches in scientific literature to optimize and predict a team's performance. However, most studies employ fine-grained skill statistics of the individual members or constraints such as teams with a set group of members. Currently, no research tackles the highly constrained domain of the FIRST Robotics Competition. This research effort aims to fill this gap by providing an analytical method for optimizing and predicting team performance in a competitive environment while allowing these constraints and only using metrics on previous team performance, not on each individual member's performance. We apply our method to the drafting process of the FIRST Robotics competition, a domain in which the skills change year-over-year, team members change throughout the season, each match only has a superficial set of statistics, and alliance formation is key to competitive success. First, we develop a method that could extrapolate individual members' performance based on overall team performance. An alliance optimization algorithm is developed to optimize team formation and a deep neural network model is trained to predict the winning team, both using highly post-processed real-world data. Our method is able to successfully extract individual members' metrics from overall team statistics, form competitive teams, and predict the winning team with 84.08% accuracy.

関連論文

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2Google DeepMind、ロボット向けAIを発表新製品・発表
  3. 3newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開

PR・アフィリエイト広告

FRONTIER(GPU搭載BTOパソコン)

FRONTIER(GPU搭載BTOパソコン)の公式広告バナーFRONTIERでGPU搭載PCを見る ↗
PR本紙発行元 EmplifAI