日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

動作生成arXiv:2410.16623

MotionGlot: 複数身体に対応する動作生成モデル

MotionGlot: A Multi-Embodied Motion Generation Model

シェア:XThreadsFacebookLINEはてブBluesky

LLMの訓練手法を応用し、四足歩行ロボットや人体など異なる行動次元を持つ複数の身体に対応した動作生成モデルを提案。6タスクで平均35.3%の改善を達成し、新規データセットも公開。

著者: Sudarshan Harithas, Srinath Sridhar

分類: cs.RO

原文アブストラクト

This paper introduces MotionGlot, a model that can generate motion across multiple embodiments with different action dimensions, such as quadruped robots and human bodies. By leveraging the well-established training procedures commonly used in large language models (LLMs), we introduce an instruction-tuning template specifically designed for motionrelated tasks. Our approach demonstrates that the principles underlying LLM training can be successfully adapted to learn a wide range of motion generation tasks across multiple embodiments with different action dimensions. We demonstrate the various abilities of MotionGlot on a set of 6 tasks and report an average improvement of 35.3% across tasks. Additionally, we contribute two new datasets: (1) a dataset of expert-controlled quadruped locomotion with approximately 48,000 trajectories paired with direction-based text annotations, and (2) a dataset of over 23,000 situational text prompts for human motion generation tasks. Finally, we conduct hardware experiments to validate the capabilities of our system in real-world applications.

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. 2newmo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
  3. 3GXO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
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  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・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