Papers
arxiv:2609.32512

What Do Latent Predictive Vehicle Representations Retain? Measuring State, Geometry, and Local Response

Published on Sep 26
Authors:
,
,

Abstract

A protocol measures action-conditioned latent predictors for vehicle control by separately assessing retention, physical-neighborhood organization, forecasting, and local command response, showing that a temporal joint-embedding predictive model preserves planar outputs but diverges from simulator responses to small command pulses.

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.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2609.32512
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2609.32512 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2609.32512 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2609.32512 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.