身体性マニピュレーションのための効率的な視覚-言語-行動モデル:系統的サーベイ
Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey
視覚-言語-行動(VLA)モデルの計算・メモリ効率を改善する手法を、モデルアーキテクチャ、知覚特徴、行動生成、訓練・推論戦略の4次元で分類し、系統的にレビューしたサーベイ論文。
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: Weifan Guan, Qinghao Hu, Aosheng Li, Jian Cheng
分類: cs.RO, cs.LG
原文アブストラクト
Vision-Language-Action (VLA) models extend vision-language models to embodied control by mapping natural-language instructions and visual observations to robot actions. Despite their capabilities, VLA systems face significant challenges due to their massive computational and memory demands, which conflict with the constraints of edge platforms such as on-board mobile manipulators that require real-time performance. Addressing this tension has become a central focus of recent research. In light of the growing efforts toward more efficient and scalable VLA systems, this survey provides a systematic review of approaches for improving VLA efficiency, with an emphasis on reducing latency, memory footprint, and training and inference costs. We categorize existing solutions into four dimensions: model architecture, perception feature, action generation, and training/inference strategies, summarizing representative techniques within each category. Finally, we discuss future trends and open challenges, highlighting directions for advancing efficient embodied intelligence.
