TurboVLA：在RTX 4090上以32 Hz運行、VRAM低於1 GB的即時視覺-語言-行動模型

摘要

視覺-語言-動作（VLA）模型普遍採用以大語言模型為核心的「V→L→A」路徑，先將視覺觀測投影到大語言模型的表徵空間，再解碼為機器人動作。儘管此設計行之有效，但每次調用策略時會產生大量的計算與記憶體開銷。本研究提出TurboVLA，這是一種全新的VLA範式，將傳統的「V→L→A」路徑重塑為直接的「V+L→A」映射。不同於以大語言模型作為感知與動作的中樞介面，TurboVLA分別編碼視覺觀測與語言指令，透過輕量化的雙向視覺-語言交互直接在兩者之間交換信息，並以緊湊的解碼器預測連續動作片段。這種簡潔的設計直接從視覺與語言特徵中構建任務條件表徵，顯著降低了VLA推理的計算與記憶體成本。在LIBERO基準上，TurboVLA僅用0.2B參數、31.2毫秒推理延遲與0.9 GB推理顯存（在消費級RTX 4090上），即達到97.7%的平均成功率，與顯著更大的VLA策略相當甚至更優。這些結果確立了TurboVLA作為主流以大語言模型為核心的VLA範式之簡潔有效替代方案，為如何連結視覺、語言與動作以實現高效機器人操作提供了全新視角。程式碼開源於 https://github.com/H-EmbodVis/TurboVLA。

English

Vision-language-action (VLA) models commonly adopt an LLM-centric V to L to A pathway, where visual observations are projected into the representation space of a large language model before being decoded into robot actions. Although effective, this design incurs substantial computation and memory overhead at every policy invocation. In this work, we introduce TurboVLA, a new VLA paradigm that reformulates the conventional V to L to A pathway as a direct V + L to A mapping. Instead of using a large language model as the central interface between perception and action, TurboVLA independently encodes visual observations and language instructions, directly exchanges information between them through lightweight bidirectional vision-language interaction, and predicts continuous action chunks with a compact decoder. This simple design constructs task-conditioned representations directly from visual and linguistic features, significantly reducing the computational and memory costs of VLA inference. On LIBERO, TurboVLA achieves 97.7% average success with only 0.2B parameters, 31.2 ms inference latency, and 0.9 GB inference VRAM on a consumer-grade RTX 4090, matching or outperforming substantially larger VLA policies. These results establish TurboVLA as a simple and effective alternative to the prevailing LLM-centric VLA paradigm, offering a new perspective on how vision, language, and action can be connected for efficient robotic manipulation. Code is available at https://github.com/H-EmbodVis/TurboVLA.