Validating Automated Driving Systems (ADS) requires generating various kinematically executable traffic scenarios. The grounding of qualitative descriptions into concrete trajectories is a combinatorial task poorly addressed by learning-based methods. We propose ScenaGen, a CP model operating on qualitative explainable graphs (QXGs) to encode spatio-temporal relations between traffic entities. Formulated over integer position variables, ScenaGen enforces qualitative spatial constraints, distance thresholds, and inter-frame kinematic consistency. A single QXG acts as a formal template for systematically enumerating distinct, quantitatively varied concrete scenarios. Evaluation of synthetic and real-world benchmarks demonstrates that ScenaGen provides a robust and efficient alternative for scenario instantiation, outperforming standard search baselines in both scalability and solution diversity.

High-Utility Itemset Mining (HUIM) aims to discover itemsets whose utility exceeds a given threshold. While specialized algorithms achieve strong performance, they lack flexibility when additional domain constraints must be incorporated. Constraint Programming (CP) offers a declarative alternative, but requires strong propagation to remain competitive. In this paper, we propose a CP framework for utility-driven pattern mining based on a parameterized global constraint that unifies the enumeration of High-Utility Itemsets (HUIs) and a new condensed representation called Utility-Peak Itemsets (UPIs). A UPI is an itemset whose utility is greater or equal than that of all its immediate subsets and supersets, capturing locally utility-maximal patterns. We study the computational complexity of UPI mining and show that deciding whether a high-utility UPI exists, for a given utility threshold, is NP-complete. Our global constraint, PeakUtility, integrates utility computation and upper-bound pruning through propagation rules. Experiments demonstrate that our approach performs competitively with the state of the art HUIM algorithms while preserving the modelling flexibility of CP.

Software systems usually provide numerous configuration options that can affect performance metrics such as execution time, memory usage, binary size, or bitrate. On the one hand, making informed decisions is challenging and requires domain expertise in options and their combinations. On the other hand, machine learning techniques can search vast configuration spaces, but with a high computational cost, since concrete executions of numerous configurations are required. In this exploratory study, we investigate whether large language models (LLMs) can assist in performance-oriented software configuration through prompts. We evaluate several LLMs on tasks including identifying relevant options, ranking configurations, and recommending performant configurations across various configurable systems, such as compilers, video encoders, and SAT solvers. Our preliminary results reveal both positive abilities and notable limitations: depending on the task and systems, LLMs can well align with expert knowledge, whereas hallucinations or superficial reasoning can emerge in other cases. These findings represent a first step toward systematic evaluations and the design of LLM-based solutions to assist with software configuration.

Road scene understanding in automated driving (AD) aims to build a comprehensive analysis of video sequences taken on the road by embedded or fixed cameras (e.g., mounted on vertical road signals). One goal is to identify the relevant actors in the scene and another goal is to determine the causes that have triggered a specific action of the ego car (i.e., stop, slow down, turn left, etc.). In a complex urban environment, these causes can be multiple, confusing, possibly contradictory to other causes and not easily expressible using simplistic reasoning. Still, providing accurate automatic cause determination supports a) user acceptance by providing appropriate explanations to the car passengers and road users; b) increased road safety by providing detailed road scene understanding to traffic. In this paper, we propose using spatiotemporal reasoning and Belnap's four-valued logic to formulate complex causes of AD action in a road scene. We compute these causes by analysing a Qualitative eXplainable Graph (QXG), which is an abstract representation of the road scene capturing spatiotemporal relations between road entities. Starting from a QXG, our approach called CAIDLOGIC, is targeted to determine complex causes of a selected AD action occurring in a specific frame of a road scene. The usefulness of CAIDLOGIC is demonstrated on several scenes extracted from the well-known NuScene dataset.

This paper investigates the integration of graph neural networks (GNNs) with Qualitative Explainable Graphs (QXGs) for scene understanding in automated driving. Scene understanding is the basis for any further reactive or proactive decision-making. Scene understanding and related reasoning is inherently an explanation task: why is another traffic participant doing something, what or who caused their actions? While previous work demonstrated QXGs' effectiveness using shallow machine learning models, these approaches were limited to analysing single relation chains between object pairs, disregarding the broader scene context. We propose a novel GNN architecture that processes entire graph structures to identify relevant objects in traffic scenes. We evaluate our method on the nuScenes dataset enriched with DriveLM's human-annotated relevance labels. Experimental results show that our GNN-based approach achieves superior performance compared to baseline methods. The model effectively handles the inherent class imbalance in relevant object identification tasks while considering the complete spatial-temporal relationships between all objects in the scene. Our work demonstrates the potential of combining qualitative representations with deep learning approaches for explainable scene understanding in autonomous driving systems.

Space-time prisms provide a framework to model the uncertainty on the space-time points that a moving object may have visited between measured space-time locations, provided that a bound on the speed of the moving object is given. In this model, the alibi query asks whether two moving objects, given by their respective measured space-time locations and speed bound, may have met. An analytical solution to this problem was first given by Othman [Kuijpers et al., 2011]. In this paper, we address the generalised alibi query that asks the same question for an arbitrary number ≥ 2 of moving objects. We provide several solutions (mainly via the spatial and temporal projection) to this query with varying time complexities. These algorithmic solutions rely on techniques from convex and semi-algebraic geometry. We also address variants of the generalised alibi query where the question is asked for a given spatial location or a given moment in time.

This paper targets a new foundation for designing general-purpose learning systems, by establishing a consensus method that facilitates self-adaptation and flexibility to deal with different learning tasks and different data distribution. We present the Shapely Consensus Deep Learning (SCDL) as a consensus method for general-purpose solutions that do not require the help of domain experts. SCDL is two-level based learning process. In the first level, several deep learning models are trained and the Shapley Value is used to determine the contribution of each subset of models in the training. The models are pruned according to their contribution in the learning process. In the second level, the loss information of each data distribution is saved in the knowledge base. Both levels are explored to prune the models for each new observation. We present the evaluation of the generality of SCDL using different datasets with different shapes, and complexities. The results reveal the effectiveness of SCDL for weakly classification. Concretely, SCDL achieved 90% of AUC with less than 86% for the baseline solutions.

Many planning, scheduling or multi-dimensional packing problems involve the design of subtle logical combinations of temporal or spatial constraints. Recently, we introduced GEQCA-I, which stands for Generic Qualitative Constraint Acquisition, as a new active constraint acquisition method for learning qualitative constraints using qualitative queries. In this paper, we revise and extend GEQCA-I to GEQCA-II with a new type of query, universal query, for qualitative constraint acquisition, with a deeper query-driven acquisition algorithm. Our extended experimental evaluation shows the efficiency and usefulness of the concept of universal query in learning randomly-generated qualitative networks, including both temporal networks based on Allen’s algebra and spatial networks based on region connection calculus. We also show the effectiveness of GEQCA-II in learning the qualitative part of real scheduling problems.

Many planning, scheduling or multi-dimensional packing problems involve the design of subtle logical combinations of temporal or spatial constraints. On the one hand, the precise modelling of these constraints, which are formulated in various relation algebras, entails a number of possible logical combinations and requires expertise in constraint-based modelling. On the other hand, active constraint acquisition (CA) has been used successfully to support non-experienced users in learning conjunctive constraint networks through the generation of a sequence of queries. In this paper, we propose GEACQ, which stands for Generic Qualitative Constraint Acquisition, an active CA method that learns qualitative constraints via the concept of qualitative queries. GEACQ combines qualitative queries with time-bounded path consistency (PC) and background knowledge propagation to acquire the qualitative constraints of any scheduling or packing problem. We prove soundness, completeness and termination of GEACQ by exploiting the jointly exhaustive and pairwise disjoint property of qualitative calculus and we give an experimental evaluation that shows (i) the efficiency of our approach in learning temporal constraints and, (ii) the use of GEACQ on real scheduling instances.