arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.19639eess.SYcs.AIcs.SY
收藏

安全关键的上下文控制 via 在线黎曼优化与世界模型

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

Tongxin Li(李通心)

Tongxin Li

AI总结:

本文研究安全关键的上下文控制问题,提出基于在线黎曼优化的样本惩罚预测控制框架,通过世界模型压缩可行性流形为密度,指导规划器梯度下降,建立基于曲率的安全界限。

摘要:

现代世界模型变得过于复杂,无法允许显式的动态描述。我们研究安全关键的上下文控制,其中规划器必须仅使用黑盒模拟器的可行性样本来优化任务目标,条件于上下文信号ξ_t。我们开发了一个基于样本的惩罚预测控制(PPC)框架,该框架基于在线黎曼优化,在其中模拟器将可行性流形压缩为基于分数的密度̂p(u|ξ_t),从而为动作空间赋予黎曼几何,指导规划器的梯度下降。屏障曲率κ(ξ_t),即条件对数密度- ln̂p(·|ξ_t)的最小曲率,同时控制收敛速度和安全边际,取代未知动态的利普希茨常数。我们的主要结果是一个上下文安全界限,表明真实可行性流形与距离受分数估计误差和依赖于κ(ξ_t)的比率控制,两者在更丰富的上下文下得到改善。在动态导航任务上的模拟证实,上下文PPC在动态环境中显著优于边缘和冻结密度模型,优势在环境变化后增长。

英文摘要:

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 $ξ_t$. 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 $\hat{p}(u \mid ξ_t)$ that endows the action space with a Riemannian geometry guiding the Planner's gradient descent. The barrier curvature $κ(ξ_t)$, the minimum curvature of the conditional log-density $-\ln\hat{p}(\cdot\midξ_t)$, 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 $κ(ξ_t)$, 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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑