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:2109.15233

深層強化学習による実機ロボットチャレンジの攻略

Solving the Real Robot Challenge using Deep Reinforcement Learning

シェア:XThreadsFacebookLINEはてブBluesky

3本指ロボットで立方体を目標軌道に沿って運ぶ課題を、シミュレーションでのドメインランダム化とHindsight Experience Replayを用いた純粋な強化学習で解き、実機転移に成功した。

著者: Robert McCarthy, Francisco Roldan Sanchez, Qiang Wang, David Cordova Bulens, Kevin McGuinness, Noel O'Connor, Stephen J. Redmond

分類: cs.RO, cs.LG

原文アブストラクト

This paper details our winning submission to Phase 1 of the 2021 Real Robot Challenge; a challenge in which a three-fingered robot must carry a cube along specified goal trajectories. To solve Phase 1, we use a pure reinforcement learning approach which requires minimal expert knowledge of the robotic system, or of robotic grasping in general. A sparse, goal-based reward is employed in conjunction with Hindsight Experience Replay to teach the control policy to move the cube to the desired x and y coordinates of the goal. Simultaneously, a dense distance-based reward is employed to teach the policy to lift the cube to the z coordinate (the height component) of the goal. The policy is trained in simulation with domain randomisation before being transferred to the real robot for evaluation. Although performance tends to worsen after this transfer, our best policy can successfully lift the real cube along goal trajectories via an effective pinching grasp. Our approach outperforms all other submissions, including those leveraging more traditional robotic control techniques, and is the first pure learning-based method to solve this challenge.

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

OZ GAMING(GPU搭載BTOゲーミングPC)

OZ GAMING(GPU搭載BTOゲーミングPC)の公式広告バナーOZ GAMINGで完成品PCを見る ↗
PR本紙発行元 EmplifAI