コマンド持続予測でナビゲーションVLAの意味推論を効率化するASPEN
ASPEN: Adaptive Semantic Reasoning via Command Persistence Prediction for Efficient Navigation VLAs
ナビゲーションVLAが同じコマンドを再推論する無駄を、軽量なマルチモーダル予測器でコマンド持続を予測して再利用し、VLA呼び出しを約9.5%削減した研究。
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: Vieri N. Akustia, Bin Hu
分類: cs.RO
原文アブストラクト
Navigation vision-language-action (VLA) policies repeatedly invoke costly semantic reasoning even when the next command remains unchanged. Command reuse can reduce computation but risks missing instruction-dependent turns or stops. We introduce ASPEN, an event-triggered scheduler based on command persistence prediction: estimating whether the frozen base policy would reissue its previous command. A lightweight multimodal predictor combines temporal observations, language instructions, execution history, and cached VLA confidence. At eligible command boundaries, sufficient predicted persistence permits command reuse. Otherwise, ASPEN triggers fresh semantic reasoning from the VLA. Evaluated with frozen NaVILA on cross-dataset RxR-CE val-unseen, ASPEN reduces VLA calls by 9.5% and estimated inference time by 8.1%, including scheduling overhead. It maintains comparable navigation performance and preserves identical baseline action sequences on 92.1% of episodes.