EVA-Client：一個統一的數據收集、推理和部署框架，用於真實機器人的具身策略

摘要

我們提出EVA-Client，這是一個開源框架，用於在真實機器人上部署、收集資料與評估訓練好的操作策略。EVA-Client 位於策略伺服器與實體硬體之間，將策略迭代循環中的真實機器人階段統一在單一程式碼庫中。它做出了三項貢獻：第一，一種組件解耦的架構，其中機器人後端、推理策略與傳輸中介層形成一個正交網格：新增機器人或策略只會影響其自身的層級。第二，透過「除錯（Debug）」、「收集（Collect）」與「評估（Eval）」工作流程實現可檢視的執行，模式從開環模擬到連續即時控制。第三，每次評估運行同時也是資料收集，會以訓練就緒的格式記錄完整的執行軌跡，並附帶詳盡的日誌與並排比較檢視器，因此每次評估都能為下一輪訓練提供資料，而非以未記錄的觀察結果告終。EVA-Client 進一步整合了主要的即時推理策略，包括同步與非同步執行、ACT 風格的時間集成（Temporal Ensembling）、即時分塊（Real-Time Chunking），以及一個簡單的非同步消融基線，全部透過單一配置介面管理。

English

We present EVA-Client, an open-source framework for deployment, data collection, and evaluation of trained manipulation policies on real robots. Sitting between a policy server and the physical hardware, EVA-Client unifies the real-robot stages of the policy iteration loop within a single codebase. It makes three contributions. First, a component-decoupled architecture in which robot backends, inference strategies, and transport middlewares form an orthogonal grid: adding a robot or a strategy touches only its own layer. Second, inspectable execution through Debug, Collect, and Eval workflows, with modes ranging from open-loop simulation to continuous real-time control. Third, every evaluation run doubles as a data collection, recording full rollouts in training-ready format alongside exhaustive logs and a side-by-side comparison viewer, so each evaluation feeds the next round of training rather than ending as an unrecorded impression. EVA-Client further consolidates major real-time inference strategies, synchronous and asynchronous execution, ACT-style temporal ensembling, Real-Time Chunking, and a naive-async ablation baseline, behind a single configuration surface.