行为克隆在专家演示数据上离线训练策略，但部署处于闭环状态：每个动作都会影响策略随后接收到的观测值。我们研究了紧凑的多模态策略在 CARLA 模拟器中能从离线演示数据中获得多少闭环驾驶能力。该策略利用 RGB 图像、LiDAR、车辆遥测数据和车道航点组成的五帧历史序列，以 20 Hz 的频率预测油门、制动和转向指令。演示数据分三个阶段收集，最后采用一种系统化的路线生成程序，枚举生成点和可行机动动作，并验证已完成的自动驾驶路线。发布的包含 136 万参数的策略在 236,882 个窗口上进行训练，这些窗口代表了来自 448 次采集的大约 3.3 小时驾驶数据。所得策略能够在训练路线和保留路线上自主行驶数小时。在我们的运行中，它未发生碰撞，并且定性迁移到了具有不同道路几何结构的未见过的 CARLA 城镇。我们还观察到从大幅轨迹偏差中的恢复情况，尽管在没有受控评估的情况下，我们不声称具备系统性恢复能力。我们报告了离线指标，并区分了测量结果与定性的闭环观察结果。我们发布了代码、训练检查点、ONNX 模型、数据样本以及针对所报告主张的证据审计。

Behavioral cloning trains a policy offline on expert demonstrations, but deployment is closed loop: each action affects the observations the policy receives next. We study how much closed-loop driving competence a compact multimodal policy can acquire from offline demonstrations in the CARLA simulator. The policy uses five-frame histories of RGB images, LiDAR, vehicle telemetry, and lane waypoints to predict throttle, brake, and steering at 20 Hz. Demonstrations were collected in three stages, ending with a systematic route-generation procedure that enumerates spawn points and feasible maneuvers and verifies completed autopilot routes. The released 1.36 million parameter policy was trained on 236,882 windows, representing about 3.3 hours of driving from 448 captures. The resulting policy drives autonomously for hours on training and held-out routes. In our runs, it did so without collisions and also transferred qualitatively to an unseen CARLA town with different road geometry. We also observed recovery from large trajectory deviations, although we do not claim systematic recovery without controlled evaluation. We report offline metrics and distinguish measured results from qualitative closed-loop observations. We release the code, trained checkpoint, ONNX model, data sample, and an evidence audit for the reported claims.