Phillip Isola

Massachusetts Institute of Technology

収録論文 19本 ・ フィジカルAI/ロボット学習

※arXiv著者名で収集。同姓同名の別人の論文が含まれる場合があります。

論文

• シミュレーションでの視覚的器用さの事前学習
  器用操作/事前学習2026/8/16

  VRヘッドセットを使い、人間がシミュレーション内で物体を操作して収集したデータで、多指ロボットハンドの操作ポリシーを事前学習する手法を提案。実機での微調整により、ゼロから学習するよりも高い性能を達成した。

• Scalable Behavior Cloning with Open Data, Training, and Evaluation
  2026/6/1
• Lucid-XR: An Extended-Reality Data Engine for Robotic Manipulation
  2026/5/1
• Scalable Real2Sim: Physics-Aware Asset Generation Via Robotic Pick-and-Place Setups
  2025/3/1
• Adaptive Length Image Tokenization via Recurrent Allocation
  2024/11/1
• Learning Visual Parkour from Generated Images
  2024/11/1
• LangNav: Language as a Perceptual Representation for Navigation
  2023/10/1
• Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation
  2023/8/1
• MIRA: Mental Imagery for Robotic Affordances
  2022/12/1
• NeRF-Supervision: Learning Dense Object Descriptors from Neural Radiance Fields
  2022/3/1
• OPEn: An Open-ended Physics Environment for Learning Without a Task
  2021/10/1
• Learning to See before Learning to Act: Visual Pre-training for Manipulation
  2021/7/1
• Curious Representation Learning for Embodied Intelligence
  2021/5/1
• INeRF: Inverting Neural Radiance Fields for Pose Estimation
  2020/12/1
• Noisy Agents: Self-supervised Exploration by Predicting Auditory Events
  2020/7/1
• Experience-Embedded Visual Foresight
  2019/11/1
• Omnipush: accurate, diverse, real-world dataset of pushing dynamics with RGB-D video
  2019/10/1
• Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity
  2019/2/1
• Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulation
  2017/3/1