潜在预测车辆表征保留了什么？测量状态、几何与局部响应
What Do Latent Predictive Vehicle Representations Retain? Measuring State, Geometry, and Local Response
浏览论文内容
中文总结 AI 辅助
本文提出一种测量协议，分别测试动作条件潜在预测器的保留、预测和局部响应能力，案例研究显示其保留物理输出但响应偏离模拟器，为控制应用提供评估基础。
中文摘要 AI 辅助
从记录的状态和指令中学习到的车辆动力学模型补充了基于物理的模型，而潜在世界模型（在学习的表征中进行预测）在其他领域被用于规划和训练控制器。车辆控制器通常以物理术语指定：成本、限制和参考值取决于位置、偏航角、速度和偏航率，优化器会比较或区分邻近指令下的预测结果。因此，置于此类控制器中的潜在模型必须能够恢复这些物理量，并且其预测必须随指令的变化而像车辆一样改变，而仅针对其自身潜在目标的预测误差无法衡量这两点。我们提出了一种针对动作条件潜在预测器的测量协议，该协议带有物理读出，可分别测试保留能力、物理邻域组织、预测能力以及对指令扰动的局部响应，使用未训练编码器作为参考，并采用三条匹配的响应路径来定位表征或预测器中的误差。在一项针对在IPG CarMaker中记录信号上训练的时间联合嵌入预测模型的案例研究中，表征保留了所测量的平面输出，尽管相同架构的未训练编码器略好地保留了它们；未来指令输入改善了一秒预测，而保留能力几乎不变；对小指令脉冲的响应在潜在坐标中已经与模拟器产生分歧，在所有比较中，在邻近指令间选择时都会导致遗憾。根据响应更新预测器可在局部纠正这些响应，但以预测精度为代价。因此，分别测量保留能力、预测能力和局部响应，是使预测性潜在表征成为控制候选模型的条件，该协议为其闭环评估提供了基础。
英文摘要
Models of vehicle dynamics learned from logged states and commands complement physics-based models, and latent world models, which predict in a learned representation, are used to plan and train controllers in other domains. Vehicle controllers are usually specified in physical terms: costs, limits, and references depend on position, yaw angle, speed, and yaw rate, and the optimizer compares or differentiates predicted outcomes across nearby commands. A latent model placed in such a controller must therefore let these quantities be recovered and must change its predictions with commands as the vehicle does, and prediction error on its own latent targets measures neither. We contribute a measurement protocol for action-conditioned latent predictors with a physical readout that separately tests retention, physical-neighborhood organization, forecasting, and local response to command perturbations, using an untrained-encoder reference and three matched response paths that locate errors in the representation or the predictor. In a case study of a temporal joint-embedding predictive model trained on signals logged in IPG CarMaker, the representations retain the measured planar outputs, though an untrained encoder of the same architecture retains them slightly better; future-command input improves one-second forecasts with retention nearly unchanged; and responses to small command pulses diverge from the simulator already in latent coordinates, raising regret when choosing among nearby commands in all comparisons. Updating the predictor on responses corrects them locally at a cost in forecast accuracy. Measuring retention, forecasting, and local response separately is thus what qualifies a predictive latent as a candidate model for control, and the protocol provides the basis for its closed-loop evaluation.
