Lei Sun

Nankai University

収録論文 25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

• GAINS: 強化学習における不整合な人間介入信号の活用
  介入学習/強化学習2026/8/16

  人間の介入信号の遅延や不整合性を扱うため、分布強化学習と悲観的探索を用いた介入ベースのロボット操作学習フレームワークを提案し、シミュレーションと実機で高い成功率を達成した。

• DeformMaster: An Interactive Physics-Neural World Model for Deformable Objects from Videos
  2026/5/1
• HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulation
  2026/4/1
• Towards Universal Computational Aberration Correction in Photographic Cameras: A Comprehensive Benchmark Analysis
  2026/3/1
• Interp3R: Continuous-time 3D Geometry Estimation with Frames and Events
  2026/3/1
• Gaussian Sequences with Multi-Scale Dynamics for 4D Reconstruction from Monocular Casual Videos
  2026/2/1
• Real-world Reinforcement Learning from Suboptimal Interventions
  2025/12/1
• Federated Split Learning for Resource-Constrained Robots in Industrial IoT: Framework Comparison, Optimization Strategies, and Future Directions
  2025/10/1
• AutoDrive-R$^2$: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Driving
  2025/9/1
• An Atomic Skill Library Construction Method for Data-Efficient Embodied Manipulation
  2025/1/1
• Towards Single-Lens Controllable Depth-of-Field Imaging via Depth-Aware Point Spread Functions
  2024/9/1
• NGM-SLAM: Gaussian Splatting SLAM with Radiance Field Submap
  2024/5/1
• Empowering Embodied Manipulation: A Bimanual-Mobile Robot Manipulation Dataset for Household Tasks
  2024/5/1
• Exploring Quasi-Global Solutions to Compound Lens Based Computational Imaging Systems
  2024/4/1
• Representing Domain-Mixing Optical Degradation for Real-World Computational Aberration Correction via Vector Quantization
  2024/3/1
• Towards Anytime Optical Flow Estimation with Event Cameras
  2023/7/1
• Efficient Human Pose Estimation via 3D Event Point Cloud
  2022/6/1
• Outlier-Robust Geometric Perception: A Novel Thresholding-Based Estimator with Intra-Class Variance Maximization
  2022/4/1
• TriVoC: Efficient Voting-based Consensus Maximization for Robust Point Cloud Registration with Extreme Outlier Ratios
  2021/11/1
• DANIEL: A Fast and Robust Consensus Maximization Method for Point Cloud Registration with High Outlier Ratios
  2021/10/1
• Aerial-PASS: Panoramic Annular Scene Segmentation in Drone Videos
  2021/5/1
• RANSIC: Fast and Highly Robust Estimation for Rotation Search and Point Cloud Registration using Invariant Compatibility
  2021/4/1
• ICOS: Efficient and Highly Robust Rotation Search and Point Cloud Registration with Correspondences
  2021/4/1
• IRON: Invariant-based Highly Robust Point Cloud Registration
  2021/3/1
• Real-time Fusion Network for RGB-D Semantic Segmentation Incorporating Unexpected Obstacle Detection for Road-driving Images
  2020/2/1