日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

AR/ロボットプログラミングarXiv:2106.07944

拡張現実とエンドユーザー開発によるロボットプログラミングの簡素化

Simplifying Robot Programming using Augmented Reality and End-User Development

シェア:XThreadsFacebookLINEはてブBluesky

ARとエンドユーザー開発の原則を組み合わせ、専門家から非専門家まで複雑なロボットプログラミングを容易に行えるプロトタイプ環境SPEAREDを開発し、産業用自動化の専門家インタビューで有効性を評価した。

著者: Enes Yigitbas, Ivan Jovanovikj, Gregor Engels

分類: cs.RO

原文アブストラクト

Robots are widespread across diverse application contexts. Teaching robots to perform tasks, in their respective contexts, demands a high domain and programming expertise. However, robot programming faces high entry barriers due to the complexity of robot programming itself. Even for experts robot programming is a cumbersome and error-prone task where faulty robot programs can be created, causing damage when being executed on a real robot. To simplify the process of robot programming, we combine Augmented Reality (AR) with principles of end-user development. By combining them, the real environment is extended with useful virtual artifacts that can enable experts as well as non-professionals to perform complex robot programming tasks. Therefore, Simple Programming Environment in Augmented Reality with Enhanced Debugging (SPEARED) was developed as a prototype for an AR-assisted robot programming environment. SPEARED makes use of AR to project a robot as well as a programming environment onto the target working space. To evaluate our approach, expert interviews with domain experts from the area of industrial automation, robotics, and AR were performed. The experts agreed that SPEARED has the potential to enrich and ease current robot programming processes.

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. 2Hugging Face、ロボット学習基盤「LeRobot v0.7.0」を公開 対話操作と大規模データ学習に対応新製品・発表
  3. 3AGIBOTのG2 6台、上海のコンビニで24時間試験 1,730タスクを実施量産・展開
  4. 4Agility Robotics、ナスダックで取引開始 米国初の人型ロボット専業上場企業と報道業界動向
  5. 5UC BerkeleyとNVIDIAの研究者、AIエージェントでロボット制御コードを仮想環境で改善研究・技術
PR本紙発行元 EmplifAI