Daesol Cho

Seoul National University

収録論文 16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

• BooST: 意味と動作を橋渡しする効率的なスキル転送
  スキル転送2026/8/11

  ロボット学習におけるスキル抽象化の課題を解決するため、意味的意図と動作ダイナミクスを統合した二段階フレームワークBooSTを提案し、シミュレーションと実機で効率的なスキル転送を実証した。

• BooST: Bridging Semantics and Motions for Efficient Skill Transfer
  2026/8/1
• FLAG: Flow Policy MaxEnt-RL by Latent Augmented Guidance
  2026/5/1
• DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation
  2026/5/1
• AdaptManip: Learning Adaptive Whole-Body Object Lifting and Delivery with Online Recurrent State Estimation
  2026/2/16
• Temporal Action Representation Learning for Tactical Resource Control and Subsequent Maneuver Generation
  2026/2/1
• AdaptManip: Learning Adaptive Whole-Body Object Lifting and Delivery with Online Recurrent State Estimation
  2026/2/1
• EgoAVFlow: Robot Policy Learning with Active Vision from Human Egocentric Videos via 3D Flow
  2026/2/1
• Periodic Skill Discovery
  2025/11/5
• Periodic Skill Discovery
  2025/11/1
• Leveraging Temporally Extended Behavior Sharing for Multi-task Reinforcement Learning
  2025/9/1
• Demonstration-free Autonomous Reinforcement Learning via Implicit and Bidirectional Curriculum
  2023/5/1
• Outcome-directed Reinforcement Learning by Uncertainty & Temporal Distance-Aware Curriculum Goal Generation
  2023/1/1
• S2P: State-conditioned Image Synthesis for Data Augmentation in Offline Reinforcement Learning
  2022/9/1
• Automating Reinforcement Learning with Example-based Resets
  2022/4/1
• Unsupervised Reinforcement Learning for Transferable Manipulation Skill Discovery
  2022/4/1