UniFField: 任意のシーンにおける視覚・意味・空間の不確かさを統合する汎用ニューラル特徴場
UniFField: A Generalizable Unified Neural Feature Field for Visual, Semantic, and Spatial Uncertainties in Any Scene
RGB-D画像から視覚・意味・幾何特徴を統合し、各モダリティの不確かさも予測する汎用ニューラル特徴場を提案。未知環境にゼロショット適用でき、移動マニピュレータの能動物体探索で頑健な意思決定を実現。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Christian Maurer, Snehal Jauhri, Sophie Lueth, Georgia Chalvatzaki
分類: cs.RO, cs.CV, cs.LG
原文アブストラクト
Comprehensive visual, geometric, and semantic understanding of a 3D scene is crucial for successful execution of robotic tasks, especially in unstructured and complex environments. Additionally, to make robust decisions, it is necessary for the robot to evaluate the reliability of perceived information. While recent advances in 3D neural feature fields have enabled robots to leverage features from pretrained foundation models for tasks such as language-guided manipulation and navigation, existing methods suffer from two critical limitations: (i) they are typically scene-specific, and (ii) they lack the ability to model uncertainty in their predictions. We present UniFField, a unified uncertainty-aware neural feature field that combines visual, semantic, and geometric features in a single generalizable representation while also predicting uncertainty in each modality. Our approach, which can be applied zero shot to any new environment, incrementally integrates RGB-D images into our voxel-based feature representation as the robot explores the scene, simultaneously updating uncertainty estimation. We evaluate our uncertainty estimations to accurately describe the model prediction errors in scene reconstruction and semantic feature prediction. Furthermore, we successfully leverage our feature predictions and their respective uncertainty for an active object search task using a mobile manipulator robot, demonstrating the capability for robust decision-making.
