依意而行：萃取視覺-語言-動作模型的行為意圖

摘要

視覺-語言-動作（VLA）模型能將多模態情境轉化為機器人動作，但其動作解碼器在很大程度上仍透過行為克隆來訓練。這種方式監督了被示範的馬達指令，卻隱含地忽略了該行為在指令下所服務的局部目標。基於未來的監督學習透過幀、潛在觀測、軌跡或運動表示來豐富動作學習，但這些訊號捕捉的是可能發生的特定實現方式，而非即將到來行為的共享語義目標。我們提出意圖蒸餾（INDI），將行為層級的意圖蒸餾進動作解碼器。在訓練期間，一個凍結的教師視覺語言模型從當前觀測、指令、粗略動作摘要及對應的執行影片中解讀示範片段。部署中的VLA則從其標準輸入中，在解碼器的中層恢復出相應的多模態意圖表示，並利用它結合行為如何展開及其達成結果的表示來組織動作預測。在SimplerEnv-Bridge上，INDI將GR00T-N1.7從64.3%提升至84.7%；在RoboCasa Kitchen上，其將受控的GR00T-N1.7基線從64.1%提升至70.3%，且在兩個基準上對π_{0.5}均取得一致的增益。在真實世界任務中，INDI將平均成功率從62.0%提升至68.7%，在長期任務上提升達12.0個百分點。進一步分析顯示，恢復出的潛在表示確實被解碼器所使用，能捕捉行為目標與執行進度，並以依賴目標的方式組織後續預測。這些結果表明，對所生成行為的語義目標進行顯式建模，能有效提升動作解碼器的效能。

English

Vision-Language-Action (VLA) models can turn multimodal context into robot actions, but their action decoders are still trained largely by behavior cloning. This supervises which motor command was demonstrated while leaving implicit the local objective served by the behavior under the instruction. Future-based supervision enriches action learning with frames, latent observations, trajectories, or motion representations, but these signals capture particular realizations of what may happen rather than the shared semantic objective of the forthcoming behavior. We propose Intention Distillation (INDI), which distills behavior-level intent into the action decoder. During training, a frozen teacher VLM interprets a demonstrated segment from the current observation, instruction, coarse action summary, and corresponding execution video. From its standard inputs, the deployed VLA recovers the resulting multimodal intent representation at an intermediate decoder layer and uses it to organize action prediction together with representations of how the behavior unfolds and what it achieves. On SimplerEnv-Bridge, INDI improves GR00T-N1.7 from 64.3% to 84.7%, and on RoboCasa Kitchen it improves the controlled GR00T-N1.7 baseline from 64.1% to 70.3%, with consistent gains on π_{0.5} across both benchmarks. In real-world tasks, INDI improves average success from 62.0% to 68.7%, with gains of up to 12.0 pp on longer-horizon tasks. Further analyses show that the recovered latent is used by the decoder, captures behavior objective and execution progress, and organizes downstream predictions in an objective-dependent manner. These results show that action decoders benefit from explicitly modeling the semantic objective of the behavior they generate.