日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

sim2realarXiv:2502.10894

アスレチックな移動操作のためのSim-to-Realギャップの橋渡し

Bridging the Sim-to-Real Gap for Athletic Loco-Manipulation

シェア:XThreadsFacebookLINEはてブBluesky

実世界データを活用したUnsupervised Actuator Netと参照軌道を用いた事前学習・微調整により、ロボットが物を持ち上げたり投げたりする動的な移動操作をシミュレーションから実機へ高精度に転移させる手法を提案。

著者: Nolan Fey, Gabriel B. Margolis, Martin Peticco, Pulkit Agrawal

分類: cs.RO, cs.AI, cs.LG

原文アブストラクト

Achieving athletic loco-manipulation on robots requires moving beyond traditional tracking rewards - which simply guide the robot along a reference trajectory - to task rewards that drive truly dynamic, goal-oriented behaviors. Commands such as "throw the ball as far as you can" or "lift the weight as quickly as possible" compel the robot to exhibit the agility and power inherent in athletic performance. However, training solely with task rewards introduces two major challenges: these rewards are prone to exploitation (reward hacking), and the exploration process can lack sufficient direction. To address these issues, we propose a two-stage training pipeline. First, we introduce the Unsupervised Actuator Net (UAN), which leverages real-world data to bridge the sim-to-real gap for complex actuation mechanisms without requiring access to torque sensing. UAN mitigates reward hacking by ensuring that the learned behaviors remain robust and transferable. Second, we use a pre-training and fine-tuning strategy that leverages reference trajectories as initial hints to guide exploration. With these innovations, our robot athlete learns to lift, throw, and drag with remarkable fidelity from simulation to reality.

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. 2GXO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
  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. 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

MINISFORUM(ミニPC)

MINISFORUM(ミニPC)の公式広告バナーMINISFORUM公式ストアを見る ↗
PR本紙発行元 EmplifAI