Always-on sensors are increasingly expected to embark a variety of tiny neural networks and to continuously perform inference on time-series of the data they sense. In order to fit lifetime and energy consumption requirements when operating on battery, such hardware uses microcontrollers (MCUs) with tiny memory budget e.g., 128kB of RAM. In this context, optimizing data flows across neural network layers becomes crucial. In this paper, we introduce TinyDéjàVu, a new framework and novel algorithms we designed to drastically reduce the RAM footprint required by inference using various tiny ML models for sensor data time-series on typical microcontroller hardware. We publish the implementation of TinyDéjàVu as open source, and we perform reproducible benchmarks on hardware. We show that TinyDéjàVu can save more than 60% of RAM usage and eliminate up to 90% of redundant compute on overlapping sliding window inputs.

We investigate the task and motion planning problem for Signal Temporal Logic (STL) specifications in robotics. Existing STL methods rely on pre-defined maps or mobility representations, which are ineffective in unstructured real-world environments. We propose the \emph{Structured-MoE STL Planner} (\textbf{S-MSP}), a differentiable framework that maps synchronized multi-view camera observations and an STL specification directly to a feasible trajectory. S-MSP integrates STL constraints within a unified pipeline, trained with a composite loss that combines trajectory reconstruction and STL robustness. A \emph{structure-aware} Mixture-of-Experts (MoE) model enables horizon-aware specialization by projecting sub-tasks into temporally anchored embeddings. We evaluate S-MSP using a high-fidelity simulation of factory-logistics scenarios with temporally constrained tasks. Experiments show that S-MSP outperforms single-expert baselines in STL satisfaction and trajectory feasibility. A rule-based \emph{safety filter} at inference improves physical executability without compromising logical correctness, showcasing the practicality of the approach.

The library implements a flexible architecture that supports: (1) various environments connected by an Application Programming Interface (API) in Python, (2) various flavors of temporal logic specification and robustness notion such as STL, including an interface-aware variant that distinguishes between input and output variables, and (3) discrete-time and dense-time interpretation of STL with generation of online and offline monitors. We specifically focus on robotics and Cyber-Physical Systems (CPSs) applications, showing how to integrate RTAMT with (1) the Robot Operating System (ROS) and (2) MATLAB/Simulink environments. We evaluate the tool by demonstrating several use scenarios involving service robotic and avionic applications.

DatalogMTL is a powerful rule-based language for temporal reasoning. Due to its high expressive power and flexible modeling capabilities, it is suitable for a wide range of applications, including tasks from industrial and financial sectors. However, due its high computational complexity, practical reasoning in DatalogMTL is highly challenging. To address this difficulty, we introduce a new reasoning method for DatalogMTL which exploits the magic sets technique -- a rewriting approach developed for (non-temporal) Datalog to simulate top-down evaluation with bottom-up reasoning. We implement this approach and evaluate it on several publicly available benchmarks, showing that the proposed approach significantly and consistently outperforms performance of the state-of-the-art reasoning techniques.

Traditional conformance checking tasks assume that event data provide a faithful and complete representation of the actual process executions. This assumption has been recently questioned: more and more often events are not traced explicitly, but are instead indirectly obtained as the result of event recognition pipelines, and thus inherently come with uncertainty. In this work, differently from the typical probabilistic interpretation of uncertainty, we consider the relevant case where uncertainty refers to which activity is actually conducted, under a fuzzy semantics. In this novel setting, we consider the problem of checking whether fuzzy event data conform with declarative temporal rules specified as Declare patterns or, more generally, as formulae of linear temporal logic over finite traces (LTLf). This requires to relax the assumption that at each instant only one activity is executed, and to correspondingly redefine boolean operators of the logic with a fuzzy semantics. Specifically, we provide a threefold contribution. First, we define a fuzzy counterpart of LTLf tailored to our purpose. Second, we cast conformance checking over fuzzy logs as a verification problem in this logic. Third, we provide a proof-of-concept, efficient implementation based on the PyTorch Python library, suited to check conformance of multiple fuzzy traces at once.

Traffic rules formalization is crucial for verifying the compliance and safety of autonomous vehicles (AVs). However, manual translation of natural language traffic rules as formal specification requires domain knowledge and logic expertise, which limits its adaptation. This paper introduces TR2MTL, a framework that employs large language models (LLMs) to automatically translate traffic rules (TR) into metric temporal logic (MTL). It is envisioned as a human-in-loop system for AV rule formalization. It utilizes a chain-of-thought in-context learning approach to guide the LLM in step-by-step translation and generating valid and grammatically correct MTL formulas. It can be extended to various forms of temporal logic and rules. We evaluated the framework on a challenging dataset of traffic rules we created from various sources and compared it against LLMs using different in-context learning methods. Results show that TR2MTL is domain-agnostic, achieving high accuracy and generalization capability even with a small dataset. Moreover, the method effectively predicts formulas with varying degrees of logical and semantic structure in unstructured traffic rules.

This work addresses maximally robust control synthesis under unknown disturbances. We consider a general nonlinear system, subject to a Signal Temporal Logic (STL) specification, and wish to jointly synthesize the maximal possible disturbance bounds and the corresponding controllers that ensure the STL specification is satisfied under these bounds. Many works have considered STL satisfaction under given bounded disturbances. Yet, to the authors' best knowledge, this is the first work that aims to maximize the permissible disturbance set and find the corresponding controllers that ensure satisfying the STL specification with maximum disturbance robustness. We extend the notion of disturbance-robust semantics for STL, which is a property of a specification, dynamical system, and controller, and provide an algorithm to get the maximal disturbance robust controllers satisfying an STL specification using Hamilton-Jacobi reachability. We show its soundness and provide a simulation example with an Autonomous Underwater Vehicle (AUV).

Temporal Knowledge Graph Question Answering (TKGQA) aims to answer questions with temporal intent over Temporal Knowledge Graphs (TKGs). The core challenge of this task lies in understanding the complex semantic information regarding multiple types of time constraints (e.g., before, first) in questions. Existing end-to-end methods implicitly model the time constraints by learning time-aware embeddings of questions and candidate answers, which is far from understanding the question comprehensively. Motivated by semantic-parsing-based approaches that explicitly model constraints in questions by generating logical forms with symbolic operators, we design fundamental temporal operators for time constraints and introduce a novel self-improvement Programming method for TKGQA (Prog-TQA). Specifically, Prog-TQA leverages the in-context learning ability of Large Language Models (LLMs) to understand the combinatory time constraints in the questions and generate corresponding program drafts with a few examples given. Then, it aligns these drafts to TKGs with the linking module and subsequently executes them to generate the answers. To enhance the ability to understand questions, Prog-TQA is further equipped with a self-improvement strategy to effectively bootstrap LLMs using high-quality self-generated drafts. Extensive experiments demonstrate the superiority of the proposed Prog-TQA on MultiTQ and CronQuestions datasets, especially in the Hits@1 metric.

In the field of control engineering, the connection between Signal Temporal Logic (STL) and time-varying Control Barrier Functions (CBF) has attracted considerable attention. CBFs have demonstrated notable success in ensuring the safety of critical applications by imposing constraints on system states, while STL allows for precisely specifying spatio-temporal constraints on the behavior of robotic systems. Leveraging these methodologies, this paper addresses the safety-critical navigation problem, in Socially Responsible Navigation (SRN) context, presenting a CBF-based STL motion planning methodology. This methodology enables task completion at any time within a specified time interval considering a dynamic system subject to velocity constraints. The proposed approach involves real-time computation of a smooth CBF, with the computation of a dynamically adjusted parameter based on the available path space and the maximum allowable velocity. A simulation study is conducted to validate the methodology, ensuring safety in the presence of static and dynamic obstacles and demonstrating its compliance with spatio-temporal constraints under non-linear velocity constraints.

The unprecedented surge in video data production in recent years necessitates efficient tools to extract meaningful frames from videos for downstream tasks. Long-term temporal reasoning is a key desideratum for frame retrieval systems. While state-of-the-art foundation models, like VideoLLaMA and ViCLIP, are proficient in short-term semantic understanding, they surprisingly fail at long-term reasoning across frames. A key reason for this failure is that they intertwine per-frame perception and temporal reasoning into a single deep network. Hence, decoupling but co-designing semantic understanding and temporal reasoning is essential for efficient scene identification. We propose a system that leverages vision-language models for semantic understanding of individual frames but effectively reasons about the long-term evolution of events using state machines and temporal logic (TL) formulae that inherently capture memory. Our TL-based reasoning improves the F1 score of complex event identification by 9-15% compared to benchmarks that use GPT4 for reasoning on state-of-the-art self-driving datasets such as Waymo and NuScenes.