arXiv subjects

Kazunobu Serizawa

Publications and source records attributed to Kazunobu Serizawa.

4 recordsLinked to original sources

arXiv2026

Receding-Horizon Maximum-Likelihood Estimation of Neural-ODE Dynamics and Thresholds from Event Cameras

Event cameras emit asynchronous brightness-change events where each pixel triggers an event when the last event exceeds a threshold, yielding a history-dependent measurement model. We address online maximum-likelihood identification of continuous-time dynamics from such streams. The latent state follows a Neural ODE and is mapped to predicted log-intensity through a differentiable state-to-image model. We model events with a history-dependent marked point process whose conditional intensity is a smooth surrogate of contrast-threshold triggering, treating the contrast threshold as an unknown parameter. The resulting log-likelihood consists of an event term and a compensator integral. We propose a receding-horizon estimator that performs a few gradient steps per update on a receding horizon window. For streaming evaluation, we store two scalars per pixel (last-event time and estimated log-intensity at that time) and approximate the compensator via Monte Carlo pixel subsampling. Synthetic experiments demonstrate joint recovery of dynamics parameters and the contrast threshold, and characterize accuracy--latency trade-offs with respect to the window length.

eess.SY↗

arXiv2026

Data-Driven Synthesis of Probabilistic Controlled Invariant Sets for Linear MDPs

We study data-driven computation of probabilistic controlled invariant sets (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 from which the system can be kept inside a prescribed safe region over an $N$-step horizon, together with the corresponding set-valued safe action map. This construction is obtained through a backward recursion and can be interpreted as a conservative approximation of the $N$-step safety predecessor operator. When the associated conservative-inclusion event holds, a conservative fixed point of the approximate recursion can be certified as an $(N,ε)$-PCIS with confidence at least $η$. For continuous state spaces, we introduce a lattice abstraction and a Lipschitz-based discretization error bound to obtain a tractable approximation scheme. Finally, we use the resulting conservative fixed-point approximation as a runtime candidate PCIS in a practical shielding architecture with iterative updates, and illustrate the approach on a numerical experiment.

eess.SY↗

arXiv2026

Structural-Ambiguity-Aware Translation from Natural Language to Signal Temporal Logic

Signal Temporal Logic (STL) is widely used to specify timed and safety-critical tasks for cyber-physical systems, but writing STL formulas directly is difficult for non-expert users. Natural language (NL) provides a convenient interface, yet its inherent structural ambiguity makes one-to-one translation into STL unreliable. In this paper, we propose an \textit{ambiguity-preserving} method for translating NL task descriptions into STL candidate formulas. The key idea is to retain multiple plausible syntactic analyses instead of forcing a single interpretation at the parsing stage. To this end, we develop a three-stage pipeline based on Combinatory Categorial Grammar (CCG): ambiguity-preserving $n$-best parsing, STL-oriented template-based semantic composition, and canonicalization with score aggregation. The proposed method outputs a deduplicated set of STL candidates with plausibility scores, thereby explicitly representing multiple possible formal interpretations of an ambiguous instruction. In contrast to existing one-best NL-to-logic translation methods, the proposed approach is designed to preserve attachment and scope ambiguity. Case studies on representative task descriptions demonstrate that the method generates multiple STL candidates for genuinely ambiguous inputs while collapsing unambiguous or canonically equivalent derivations to a single STL formula.

cs.CL↗

arXiv2025

Clustering-based Recurrent Neural Network Controller synthesis under Signal Temporal Logic Specifications

Autonomous robotic systems require advanced control frameworks to achieve complex temporal objectives that extend beyond conventional stability and trajectory tracking. Signal Temporal Logic (STL) provides a formal framework for specifying such objectives, with robustness metrics widely employed for control synthesis. Existing optimization-based approaches using neural network (NN)-based controllers often rely on a single NN for both learning and control. However, variations in initial states and obstacle configurations can lead to discontinuous changes in the optimization solution, thereby degrading generalization and control performance. To address this issue, this study proposes a method to enhance recurrent neural network (RNN)-based control by clustering solution trajectories that satisfy STL specifications under diverse initial conditions. The proposed approach utilizes trajectory similarity metrics to generate clustering labels, which are subsequently used to train a classification network. This network assigns new initial states and obstacle configurations to the appropriate cluster, enabling the selection of a specialized controller. By explicitly accounting for variations in solution trajectories, the proposed method improves both estimation accuracy and control performance. Numerical experiments on a dynamic vehicle path planning problem demonstrate the effectiveness of the approach.

eess.SY↗