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
SPARK: Simple Post-training for Adapting pRetrained Knowledge to Robot Control
大規模基盤モデルの視覚特徴を、時間変化や行動に関わる情報を保ちながらロボット制御向けに適応させるポストトレーニング手法を提案し、複数ベンチマークと実機マニピュレーションで成功率と汎化性能の向上を示した。
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: Taekyung Kim, Jeongeun Park, Byeongho Heo, Sungjoon Choi, Sangdoo Yun, Dongyoon Han
分類: cs.RO, cs.CV
原文アブストラクト
Large-scale representation learning has produced public foundation models that provide strong general-purpose visual features. However, their pretraining objectives are not designed for robot representation learning, so the resulting embeddings tend to emphasize global semantics rather than the temporally sensitive representations required for robot control. Training robot models from scratch is also undesirable due to the limited scale and high collection cost of robotics data, as well as the substantial computational burden of pre-training. In this paper, we propose SPARK (Simple Post-training for Adapting pRetrained Knowledge), a post-training method that adapts foundation models to robot control. SPARK is built on two principles: temporal abstraction, which encourages the encoder to derive compact features that preserve information essential for understanding temporal changes and action-relevant scene structure, and knowledge preservation, which aligns patch-level representations with those of the original foundation model to retain useful pretrained semantics. These objectives yield compact visual state representations that remain semantically meaningful while preserving useful prior knowledge. Experiments across multiple robotics benchmarks show that SPARK consistently improves success rates and generalization over vanilla foundation models, and further demonstrate that these gains transfer to real-world robot manipulation.
関連論文
- 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