CLARE: 自律的アダプタルーティングと拡張による視覚-言語-行動モデルの継続学習
CLARE: Continual Learning for Vision-Language-Action Models via Autonomous Adapter Routing and Expansion
VLAモデルに軽量アダプタを追加し、層ごとの特徴類似度に基づいて必要な箇所だけを自律的に拡張することで、過去データやタスクIDなしに破滅的忘却を防ぎながら新タスクを継続学習するフレームワークを提案。
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: Ralf Römer, Yi Zhang, Yuming Li, Angela P. Schoellig
分類: cs.RO, cs.LG
原文アブストラクト
To teach robots complex manipulation tasks, a common approach is to fine-tune a pre-trained vision-language-action model (VLA) on task-specific data. However, since this recipe updates existing representations, it is unsuitable for long-term operation in the real world, where robots must continually adapt to new tasks and environments while retaining the knowledge they have already acquired. Existing continual learning methods for robotics commonly require storing previous data (exemplars), struggle with long task sequences, or rely on task identifiers for deployment. To address these limitations, we propose CLARE, a general, parameter-efficient framework for exemplar-free continual learning with VLAs. CLARE introduces lightweight modular adapters into selected VLA modules and autonomously expands the model only where necessary when learning a new task, guided by layer-wise feature similarity. During deployment, an autoencoder-based routing mechanism dynamically activates the most relevant adapters without requiring task labels. Through extensive experiments on the LIBERO benchmark and five real-world tasks, we show that CLARE achieves high performance on new tasks without catastrophic forgetting of earlier tasks, significantly outperforming even exemplar-based methods. Code, data, and videos are available at our website: https://tum-lsy.github.io/clare.
