日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

マニピュレーションarXiv:2109.14275

多指ロボット把持のためのシミュレーションベースベイズ推論

Simulation-based Bayesian inference for multi-fingered robotic grasping

シェア:XThreadsFacebookLINEはてブBluesky

ロボットの確率的順シミュレーションを用いたベイズ事後推論により、多指ハンドの把持姿勢を計画する手法を提案。深層ニューラルネットによる尤度比近似とリーマン多様体最適化で高成功率を実現した。

著者: Norman Marlier, Olivier Brüls, Gilles Louppe

分類: cs.RO, cs.LG

原文アブストラクト

Multi-fingered robotic grasping is an undeniable stepping stone to universal picking and dexterous manipulation. Yet, multi-fingered grippers remain challenging to control because of their rich nonsmooth contact dynamics or because of sensor noise. In this work, we aim to plan hand configurations by performing Bayesian posterior inference through the full stochastic forward simulation of the robot in its environment, hence robustly accounting for many of the uncertainties in the system. While previous methods either relied on simplified surrogates of the likelihood function or attempted to learn to directly predict maximum likelihood estimates, we bring a novel simulation-based approach for full Bayesian inference based on a deep neural network surrogate of the likelihood-to-evidence ratio. Hand configurations are found by directly optimizing through the resulting amortized and differentiable expression for the posterior. The geometry of the configuration space is accounted for by proposing a Riemannian manifold optimization procedure through the neural posterior. Simulation and physical benchmarks demonstrate the high success rate of the procedure.

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. 3Google DeepMind、ロボット向けAIを発表新製品・発表
  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

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