arXiv subjects

Filip Dvořák

Publications and source records attributed to Filip Dvořák.

5 recordsLinked to original sources

arXiv2026

Graph-Based Orchestration of Heterogeneous AI Models: A Control Node Approach to Composite Intelligence

We present a graph-based framework for Composite AI systems that integrate multiple AI techniques to address complex problems. We describe an architecture using specialized control nodes to orchestrate diverse models including planning, machine learning, constraint programming, and large language models. The system employs directed acyclic graphs and behavior trees to manage model relationships and execution sequencing. Our methodology encompasses data connectors, computational services, and a containerized deployment framework supporting hierarchical, sequential, and concurrent model composition patterns. Through case studies, we demonstrate how this architecture enables the creation of composite systems that leverage the strengths of multiple AI techniques within a unified operational schema, overcoming the limitations of single-model approaches.

cs.AI↗

arXiv2025

Planning Domain Model Acquisition from State Traces without Action Parameters

Existing planning action domain model acquisition approaches consider different types of state traces from which they learn. The differences in state traces refer to the level of observability of state changes (from full to none) and whether the observations have some noise (the state changes might be inaccurately logged). However, to the best of our knowledge, all the existing approaches consider state traces in which each state change corresponds to an action specified by its name and all its parameters (all objects that are relevant to the action). Furthermore, the names and types of all the parameters of the actions to be learned are given. These assumptions are too strong. In this paper, we propose a method that learns action schema from state traces with fully observable state changes but without the parameters of actions responsible for the state changes (only action names are part of the state traces). Although we can easily deduce the number (and names) of the actions that will be in the learned domain model, we still need to deduce the number and types of the parameters of each action alongside its precondition and effects. We show that this task is at least as hard as graph isomorphism. However, our experimental evaluation on a large collection of IPC benchmarks shows that our approach is still practical as the number of required parameters is usually small. Compared to the state-of-the-art learning tools SAM and Extended SAM our new algorithm is able to provide better results in multiple domains in terms of learning action models more similar to reference models, even though it uses less information and has fewer restrictions on the input traces.

cs.AI↗

arXiv2024

Cloud Kitchen: Using Planning-based Composite AI to Optimize Food Delivery Processes

The global food delivery market provides many opportunities for AI-based services that can improve the efficiency of feeding the world. This paper presents the Cloud Kitchen platform as a decision-making tool for restaurants with food delivery and a simulator to evaluate the impact of the decisions. The platform contains a Technology-Specific Bridge (TSB) that provides an interface for communicating with restaurants or the simulator. TSB uses a planning domain model to represent decisions embedded in the Unified Planning Framework (UPF). Decision-making, which concerns allocating customers' orders to vehicles and deciding in which order the customers will be served (for each vehicle), is done via a Vehicle Routing Problem with Time Windows (VRPTW), an efficient tool for this problem. We show that decisions made by our platform can improve customer satisfaction by reducing the number of delayed deliveries using a real-world historical dataset.

cs.AI↗

arXiv2024

On Automating Video Game Regression Testing by Planning and Learning

In this paper, we propose a method and workflow for automating regression testing of certain video game aspects using automated planning and incremental action model learning techniques. The basic idea is to use detailed game logs and incremental action model learning techniques to maintain a formal model in the planning domain description language (PDDL) of the gameplay mechanics. The workflow enables efficient cooperation of game developers without any experience with PDDL or other formal systems and a person experienced with PDDL modeling but no game development skills. We describe the method and workflow in general and then demonstrate it on a concrete proof-of-concept example -- a simple role-playing game provided as one of the tutorial projects in the popular game development engine Unity. This paper presents the first step towards minimizing or even eliminating the need for a modeling expert in the workflow, thus making automated planning accessible to a broader audience.

cs.HC↗

arXiv2022

Adatom and nanoparticle dynamics on single-atom catalyst substrates

Single-atom catalysts represent an essential and ever-growing family of heterogeneous catalysts. Recent studies indicate that besides the valuable catalytic properties provided by single-atom active sites, the presence of single-atom sites on the catalyst substrates may significantly influence the population of supported metal nanoparticles coexisting with metal single atoms. Treatment of ceria-based single-atom catalysts in oxidizing or reducing atmospheres was proven to provide precise experimental control of the size of the supported Pt nanoparticles, and, correspondingly, control of catalyst activity and stability. Based on dedicated surface science experiments, ab-initio calculations and kinetic Monte-Carlo simulations we demonstrate that the morphology of Pt nanoparticle population on ceria surface is a result of a competition for Pt atoms between Pt single-atom sites and Pt nanoparticles. In oxidizing atmosphere, Pt single-atom sites provide strong bonding to single Pt atoms and Pt nanoparticles shrink. In reducing atmosphere, Pt single atom sites are depopulated and Pt nanoparticles grow. We formulate a generic model of Pt redispersion and coarsening on ceria substrates. Our model provides a unified atomic-level explanation for a variety of metal nanoparticle dynamic processes observed in single-atom catalysts under stationary or alternating oxidizing/reducing atmospheres, and allows to classify the conditions when nanoparticle ensembles on single-atom catalysts substrates can be stabilized against Ostwald ripening.

cond-mat.mtrl-sci↗