Safety-Critical Contextual Control via Online Riemannian Optimization with World Models

arXiv:2604.19639v1 Announce Type: cross
Abstract: Modern world models are becoming too complex to admit explicit dynamical descriptions. We study safety-critical contextual control, where a Planner must optimize a task objective using only feasibility samples from a black-box Simulator, conditioned on a context signal $xi_t$. We develop a sample-based Penalized Predictive Control (PPC) framework grounded in online Riemannian optimization, in which the Simulator compresses the feasibility manifold into a score-based density $hatp(u mid xi_t)$ that endows the action space with a Riemannian geometry guiding the Planner’s gradient descent. The barrier curvature $kappa(xi_t)$, the minimum curvature of the conditional log-density $-lnhatp(cdotmidxi_t)$, governs both convergence rate and safety margin, replacing the Lipschitz constant of the unknown dynamics. Our main result is a contextual safety bound showing that the distance from the true feasibility manifold is controlled by the score estimation error and a ratio that depends on $kappa(xi_t)$, both of which improve with richer context. Simulations on a dynamic navigation task confirm that contextual PPC substantially outperforms marginal and frozen density models, with the advantage growing after environment shifts.