StreamVLA: 通过完成状态门控打破原因-行动循环
StreamVLA: Breaking the Reason-Act Cycle via Completion-State Gating
AI总结：
StreamVLA通过完成状态门控机制，实现高效机器人操作，减少推理延迟并提升任务成功率。
摘要：
长周期机器人操作需要弥合高层规划（系统2）与低层控制（系统1）之间的差距。当前的视觉-语言-动作（VLA）模型往往将这些过程融合在一起，在每个时间步进行冗余的多模态推理，导致高延迟和目标不稳定。为了解决这个问题，我们提出了StreamVLA，一种双系统架构，它在一个参数高效的核心结构中统一了文本任务分解、视觉目标想象和连续动作生成。我们引入了“锁定-门控”机制，以智能调节计算：只有在子任务转换被检测到时，模型才会触发慢速思考来生成文本指令并想象特定的视觉完成状态，而不是通用的未来帧。关键的是，这个完成状态作为时间不变的目标锚点，使策略在执行速度变化时保持稳健。在稳定执行期间，这些高层意图被锁定以条件化一个流匹配动作头，使模型能够绕过昂贵的自回归解码，从而在72%的时间步中避免这种解码。这种分层抽象确保了子目标的关注，同时显著减少了推理延迟。广泛的评估表明，StreamVLA实现了最先进的性能，在LIBERO基准上达到了98.5%的成功率，并在现实世界干扰场景中表现出鲁棒性，相比全推理基线减少了48%的延迟。
英文摘要：
Long-horizon robotic manipulation requires bridging the gap between high-level planning (System 2) and low-level control (System 1). Current Vision-Language-Action (VLA) models often entangle these processes, performing redundant multimodal reasoning at every timestep, which leads to high latency and goal instability. To address this, we present StreamVLA, a dual-system architecture that unifies textual task decomposition, visual goal imagination, and continuous action generation within a single parameter-efficient backbone. We introduce a "Lock-and-Gated" mechanism to intelligently modulate computation: only when a sub-task transition is detected, the model triggers slow thinking to generate a textual instruction and imagines the specific visual completion state, rather than generic future frames. Crucially, this completion state serves as a time-invariant goal anchor, making the policy robust to execution speed variations. During steady execution, these high-level intents are locked to condition a Flow Matching action head, allowing the model to bypass expensive autoregressive decoding for 72% of timesteps. This hierarchical abstraction ensures sub-goal focus while significantly reducing inference latency. Extensive evaluations demonstrate that StreamVLA achieves state-of-the-art performance, with a 98.5% success rate on the LIBERO benchmark and robust recovery in real-world interference scenarios, achieving a 48% reduction in latency compared to full-reasoning baselines.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
