ロボット基盤モデルにおける近道学習を軽減する人工中心窩知覚
Artificial Foveated Perception for Mitigating Shortcut Learning in Robotic Foundation Models
ロボット基盤モデルがシーン内の無関係な相関に依存する「近道学習」を起こす問題を指摘し、タスク関連領域に注意を向けるマスクを生成する軽量モジュール（AFP）を提案。微調整時の補助信号として用いることで、モデルの性能とロバスト性を向上させる。
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: Xiatao Sun, Yuan Zhuang, Mateo Sanchez Lopez Negrete, Matei-Victor Coldea, Chen Liang, Haoyang Zhang, Che Liu, Ziyao Zeng, Shawn Li, Qian Wang, Fei Miao, Daniel Rakita
分類: cs.RO
原文アブストラクト
Robotic foundation models have recently made substantial progress in multi-task capability, cross-embodiment transfer, and language-conditioned control. Yet robust deployment across diverse real-world settings remains difficult, in part because policies often fail to distinguish causally relevant visual structure from spurious scene-level correlations. We identify this failure mode as shortcut learning: the tendency to exploit predictive but non-causal correlations in the training distribution rather than the task-relevant visual evidence that determines successful action. Although shortcut learning has been extensively studied in computer vision and broader machine learning, its role in robotic foundation models remains comparatively underexplored. We propose Artificial Foveated Perception (AFP), a lightweight, policy-agnostic module that takes the same vision and language inputs as Vision-Language-Action and World Action Model pipelines and predicts task-conditioned masks over relevant objects, the robot, and other action-critical regions. We use these masks primarily as an auxiliary grounding signal during fine-tuning, aligning policy attention with task-relevant regions while leaving the core architecture unchanged. After fine-tuning, the policy executes on the original observation stream without requiring AFP in the control loop. We evaluate AFP across state-of-the-art robotic foundation models and show that foveated perception reduces fine-tuning time, suppresses overfitting, and improves generalization under environmental perturbations. Ablations over mask quality and grounding-loss design further show that these gains arise from directing policy learning toward task-relevant visual evidence. These results suggest that task-conditioned foveated perception is a practical mechanism for making robotic foundation models more robust, data-efficient, and scalable.
関連論文
- SPARK: 事前学習済み知識をロボット制御に適応させる簡易ポストトレーニングロボット基盤モデル
- WSA$_1$: 3D中心の世界・空間・行動モデルによる汎用ロボット制御ロボット基盤モデル
- ロボット基盤モデルのための仕様を考慮した分布整形ロボット基盤モデル
