带着意图行动：为视觉-语言-动作模型蒸馏行为意图

摘要

视觉-语言-动作（VLA）模型能够将多模态上下文转化为机器人动作，但其动作解码器在很大程度上仍通过行为克隆进行训练。这种方式监督了所演示的电机指令，同时使指令下行为所服务的局部目标保持隐式。基于未来的监督通过帧、潜在观测、轨迹或运动表示来丰富动作学习，但这些信号捕捉的是可能发生的特定实现方式，而非未来行为所共享的语义目标。我们提出意图蒸馏（INDI），将行为层面的意图蒸馏到动作解码器中。在训练期间，冻结的教师VLM从当前观测、指令、粗粒度动作摘要及相应的执行视频中解读演示片段。部署的VLA从其标准输入中，在中间解码器层恢复由此产生的多模态意图表示，并利用该表示连同行为如何展开及其所实现目标的表示来组织动作预测。在SimplerEnv-Bridge上，INDI将GR00T-N1.7从64.3%提升至84.7%；在RoboCasa Kitchen上，将受控的GR00T-N1.7基线从64.1%提升至70.3%，并且在两个基准测试中对π_{0.5}均取得一致的提升。在真实世界任务中，INDI将平均成功率从62.0%提升至68.7%，在更长时程任务上提升高达12.0个百分点。进一步分析表明，恢复的潜在表示被解码器所使用，能够捕捉行为目标与执行进度，并以目标依赖的方式组织下游预测。这些结果表明，动作解码器受益于对其所生成行为的语义目标进行显式建模。

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.