Lei Han

Noitom Robotics

収録論文 26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

• HiPHI: 高精度な人体動作と物体インタラクションのための大規模ベンチマーク
  データセット/ベンチマーク2026/8/17

  本論文は、600時間以上の高精度な全身動作と物体インタラクションを収録した大規模データセットHiPHIを構築し、動作多様性やインタラクションの接地性を評価するベンチマークを提案した。

• PFM-HR: 人型ロボットのためのポーズフローマッチング
  歩行2026/8/4

  大規模な非順序ポーズデータから学習した再利用可能なフローマッチング事前分布を導入し、ポーズ幾何スコアを用いて追跡報酬を調整することで、人型ロボットの動的動作追跡性能を向上させた。

• PFM-HR: Pose Flow Matching for Humanoid Robots
  2026/8/1
• Try Once, Then Optimal: De-Redundified Procedure Memory for Cross-Episode Exploration Amortization
  2026/7/1
• OmniContact: Chaining Meta-Skills via Contact Flow for Generalizable Humanoid Loco-Manipulation
  2026/6/1
• When Video Misreads: Closed-Loop Distillation of Reading Heuristics for Exploratory Manipulation Trace QA
  2026/6/1
• UniLab: A Heterogeneous Architecture for Robot RL Beyond GPU-Dominant Paradigms
  2026/5/1
• GS-Playground: A High-Throughput Photorealistic Simulator for Vision-Informed Robot Learning
  2026/4/1
• Cooperative-Competitive Team Play of Real-World Craft Robots
  2026/2/1
• FILIC: Dual-Loop Force-Guided Imitation Learning with Impedance Torque Control for Contact-Rich Manipulation Tasks
  2025/9/1
• AgentWorld: An Interactive Simulation Platform for Scene Construction and Mobile Robotic Manipulation
  2025/8/1
• VLM-TDP: VLM-guided Trajectory-conditioned Diffusion Policy for Robust Long-Horizon Manipulation
  2025/7/1
• 3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model
  2025/6/1
• MinD: Learning A Dual-System World Model for Real-Time Planning and Implicit Risk Analysis
  2025/6/1
• Learning 3D Persistent Embodied World Models
  2025/5/1
• VLN-Game: Vision-Language Equilibrium Search for Zero-Shot Semantic Navigation
  2024/11/1
• HumanVLA: Towards Vision-Language Directed Object Rearrangement by Physical Humanoid
  2024/6/1
• An Efficient Model-Based Approach on Learning Agile Motor Skills without Reinforcement
  2024/3/1
• Learning Highly Dynamic Behaviors for Quadrupedal Robots
  2024/2/1
• Terrain-Aware Quadrupedal Locomotion via Reinforcement Learning
  2023/10/1
• Learning Terrain-Adaptive Locomotion with Agile Behaviors by Imitating Animals
  2023/8/1
• Lifelike Agility and Play in Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained Models
  2023/8/1
• Robust Quadrupedal Locomotion via Risk-Averse Policy Learning
  2023/8/1
• Crossing the Reality Gap in Tactile-Based Learning
  2023/5/1
• MHER: Model-based Hindsight Experience Replay
  2021/7/1
• Variational Dynamic for Self-Supervised Exploration in Deep Reinforcement Learning
  2020/10/1