ECHO: 視覚言語行動モデルのための連続階層メモリ
ECHO: Continuous Hierarchical Memory for Vision-Language-Action Models
長期的な操作タスクにおけるVLAモデルの性能を向上させるため、経験を階層的に整理する連続メモリフレームワークECHOを提案。双曲オートエンコーダでメモリを木構造に組織化し、効率的な検索と合成を実現。
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: Yanbin Hu, Jin Cui, Jiayi Lu, Ruixuan Yang, Jun Ye, Boran Zhao, Xingyu Chen, Xuguang Lan, Pengju Ren
分類: cs.RO
原文アブストラクト
Memory capacity is a critical factor determining the performance of Vision-Language-Action (VLA) models in long-horizon manipulation tasks. Existing memory-augmented architectures primarily rely on linear or flat storage, lacking structural priors for manipulation categories and hierarchical organization. This deficiency hinders efficient experience retrieval and limits generalization to unseen long-horizon task compositions. Inspired by the hierarchical organization of human experience, we propose ECHO (Experience Consolidation and Hierarchical Organization), a novel memory framework operating within a Continuous Hierarchical Space. By employing a hyperbolic autoencoder, ECHO maps VLA hidden states into this space. Leveraging hyperbolic metrics and entailment constraint mechanisms, experience vectors are organized into a semantic memory tree that supports efficient top-down retrieval. In parallel, a background consolidation mechanism continuously refines the memory tree through geometric interpolation and structural splitting, supporting virtual memory synthesis in the continuous space. We integrate ECHO into the $\pi_0$ foundation model. Evaluations on LIBERO and preliminary real-world experiments demonstrate the effectiveness of our approach, notably achieving a 12.8% absolute improvement in execution success rate over the $\pi_0$ baseline on LIBERO-Long, while improving compositional generalization on cross-suite unseen long-horizon tasks.
