2026· IEEE Control Systems Letters· Vol 10, pp. 1939-1944· 0 citations· 19 references
Computer Science
Abstract
This work studies the synthesis of active perception policies for predictive safety monitoring in partially observable stochastic systems. Operating under sensing and communication budgets, the proposed monitor dynamically schedules sensor queries to maximize information gain about the safety of future states. The underlying stochastic dynamics are captured by a labeled hidden Markov model, with safety requirements defined by a deterministic finite automaton. To enable active information acquisition, we introduce minimizing <inline-formula> <tex-math notation="LaTeX">$k$ </tex-math></inline-formula>-step Shannon conditional entropy of the safety of future states as a planning objective, under the constraint of a limited sensor query budget. Using observable operators, we derive an efficient algorithm to compute the <inline-formula> <tex-math notation="LaTeX">$k$ </tex-math></inline-formula>-step conditional entropy and analyze key properties of the conditional entropy gradient with respect to policy parameters. We validate the effectiveness of the method for predictive safety monitoring through a dynamic congestion game example.
We study data-driven computation of <italic>probabilistic controlled invariant sets</italic> (PCIS) for safety-critical reinforcement learning under unknown dynamics. Assuming a linear MDP model, we use regularized least squares and self-normalized confidence bounds to construct a conservative estimate of the states fr...
Kazumune Hashimoto, Shun Kimura, Junya Ikemoto et al.· IEEE Open Journal of Control...· 0 citations
We study infinite-horizon average-reward constrained Markov decision processes (CMDPs) under the weakly communicating assumption. Existing high-probability guarantees for this setting either require computationally inefficient algorithms or have suboptimal dependence on the number of interactions $T$. We propose, to th...
A two-step strategy for correcting ML-based state estimation, where an offline computation is used to characterize the uncertainties resulting from the ML module's state estimation, using preimages of perception contracts at runtime, using a risk heuristic.
Multimodal inference in safety-critical applications, such as autonomous driving and robot navigation, requires heterogeneous sensor observations to reach an edge server within a task-prescribed temporal window. Referenced to the event or state being inferred, this window ends at the latest time an observation remains...
A. Compagnoni, A. Mishra, C. Chiasserini et al.· 0 citations
In this paper, we present an approach for combining stochastic nonlinear model predictive control (SNMPC) and reinforcement learning (RL) to enable probabilistically-safe perception-based navigation in unknown environments. Our method first uses RL to train probabilistic actor-critic and sensor prediction models. We th...
A. Polevoy, Dillon Capalongo, Katherine Tang et al.· 0 citations
A Predictive Zonotope Reduction (PZR) approach, which frames reducer selection as an optimal control problem and solves it using beam-search model predictive control using beam-search model predictive control, enabling uncertainty-aware runtime monitoring on resource-constrained real-time systems.
Vladimir Krsmanovic, Florian Kohn, Bernd Finkbeiner et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
