Nick Heppert
University of Freiburg
収録論文 16本 ・ フィジカルAI/ロボット学習
視覚的注意/ポリシー学習
※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
- 行動から注意を学ぶ：ポリシー学習のための創発的視覚ボトルネック視覚的注意/ポリシー学習2026/8/13
行動教師信号のみから注目領域（ROI）を学習するSeekerを提案し、RGBクロップや点群フィルタリングの空間インターフェースとして利用。実機で成功率を大幅に向上させた。
- Attention from Action, for Action: Emergent Visual Bottlenecks for Policy Learning2026/8/1
- AnchorD: Metric Grounding of Monocular Depth Using Factor Graphs2026/5/1
- SparTa: Sparse Graphical Task Models from a Handful of Demonstrations2026/2/1
- Scaling Single Human Demonstrations for Imitation Learning using Generative Foundational Models2026/2/1
- cVLA: Towards Efficient Camera-Space VLAs2025/7/1
- Neural Fields in Robotics: A Survey2024/10/1
- Learning Robotic Manipulation Policies from Point Clouds with Conditional Flow Matching2024/9/1
- Imagine2touch: Predictive Tactile Sensing for Robotic Manipulation using Efficient Low-Dimensional Signals2024/5/1
- CenterArt: Joint Shape Reconstruction and 6-DoF Grasp Estimation of Articulated Objects2024/4/1
- PseudoTouch: Efficiently Imaging the Surface Feel of Objects for Robotic Manipulation2024/3/1
- DITTO: Demonstration Imitation by Trajectory Transformation2024/3/1
- CenterGrasp: Object-Aware Implicit Representation Learning for Simultaneous Shape Reconstruction and 6-DoF Grasp Estimation2023/12/1
- AO-Grasp: Articulated Object Grasp Generation2023/10/1
- CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects2023/3/1
- Category-Independent Articulated Object Tracking with Factor Graphs2022/5/1