Anna Lukina

Anna Lukina
Delft University of Technology | TU · Faculty of Electrical Engineering, Mathematics and Computer Sciences (EEMCS)

PhD

About

20
Publications
5,182
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
153
Citations
Additional affiliations
June 2015 - June 2018
TU Wien
Position
  • Project Assistant

Publications

Publications (20)
Chapter
Neural-network classifiers achieve high accuracy when predicting the class of an input that they were trained to identify. Maintaining this accuracy in dynamic environments, where inputs frequently fall outside the fixed set of initially known classes, remains a challenge. The typical approach is to detect inputs from novel classes and retrain the...
Preprint
Full-text available
Machine-learning techniques achieve excellent performance in modern applications. In particular, neural networks enable training classifiers, often used in safety-critical applications, to complete a variety of tasks without human supervision. Neural-network models have neither the means to identify what they do not know nor to interact with the hu...
Preprint
Decision tree learning is a widely used approach in machine learning, favoured in applications that require concise and interpretable models. Heuristic methods are traditionally used to quickly produce models with reasonably high accuracy. A commonly criticised point, however, is that the resulting trees may not necessarily be the best representati...
Preprint
Full-text available
Machine learning and formal methods have complimentary benefits and drawbacks. In this work, we address the controller-design problem with a combination of techniques from both fields. The use of black-box neural networks in deep reinforcement learning (deep RL) poses a challenge for such a combination. Instead of reasoning formally about the outpu...
Preprint
Full-text available
We present recent results that demonstrate the power of viewing the problem of V-formation in a flock of birds as one of Model Predictive Control (MPC). The V-formation-MPC marriage can be understood in terms of the problem of synthesizing an optimal plan for a continuous-space and continuous-time Markov decision process (MDP), where the goal is to...
Preprint
Full-text available
Neural networks have demonstrated unmatched performance in a range of classification tasks. Despite numerous efforts of the research community, novelty detection remains one of the significant limitations of neural networks. The ability to identify previously unseen inputs as novel is crucial for our understanding of the decisions made by neural ne...
Article
Full-text available
The main focus of this work is an optimization-based framework for control of multi-agent systems that synthesizes actions steering a given system towards a specified state. The primary motivation for the research presented is a fascination with birds, which save energy on long-distance flights via forming a V-shape. We ask the following question:...
Conference Paper
Full-text available
We present DAMPC, a distributed, adaptive-horizon and adaptive-neighborhood algorithm for solving the stochastic reachability problem in multi-agent systems, in particular, flocking modeled as a Markov decision process. At each time step, every agent first calls a centralized, adaptive-horizon model-predictive control (AMPC) algorithm to obtain an...
Chapter
We highlight the contributions made in the field of Statistical Model Checking (SMC) since its inception in 2002. As the formal setting, we use a very general model of Stochastic Systems (an SS is simply a family of time-indexed random variables), and Bounded LTL (BLTL) as the temporal logic. Let S be an SS and \(\varphi \) a BLTL formula. Our surv...
Preprint
Full-text available
We present DAMPC, a distributed, adaptive-horizon and adaptive-neighborhood algorithm for solving the stochastic reachability problem in multi-agent systems, in particular flocking modeled as a Markov decision process. At each time step, every agent calls a centralized, adaptive-horizon model-predictive control (AMPC) algorithm to obtain an optimal...
Conference Paper
Full-text available
Inspired by the emerging problem of CPS security, we introduce the concept of controller-attacker games. A controller-attacker game is a two-player stochastic game, where the two players, a controller and an attacker, have antagonistic objectives. A controller-attacker game is formulated in terms of a Markov Decision Process (MDP), with the control...
Conference Paper
Full-text available
I develop novel intelligent approximation algorithms for solving modern problems of CPSs, such as control and verification, by combining advanced statistical methods. it is important for the control algorithms underlying the class of multi-agent CPSs to be resilient to various kinds of attacks, and so it is for my algorithms. I have designed a very...
Conference Paper
Full-text available
We introduce ARES, an efficient approximation algorithm for generating optimal plans (action sequences) that take an initial state of a Markov Decision Process (MDP) to a state whose cost is below a specified (convergence) threshold. ARES uses Particle Swarm Optimization, with adaptive sizing for both the receding horizon and the particle swarm. In...
Article
Full-text available
We introduce the concept of a V-formation game between a controller and an attacker, where controller's goal is to maneuver the plant (a simple model of flocking dynamics) into a V-formation, and the goal of the attacker is to prevent the controller from doing so. Controllers in V-formation games utilize a new formulation of model-predictive contro...
Article
Full-text available
We introduce ARES, an efficient approximation algorithm for generating optimal plans (action sequences) that take an initial state of a Markov Decision Process (MDP) to a state whose cost is below a specified (convergence) threshold. ARES uses Particle Swarm Optimization, with adaptive sizing for both the receding horizon and the particle swarm. In...
Conference Paper
We introduce feedback-control statistical system checking (FC-SSC), a new approach to statistical model checking that exploits principles of feedback-control for the analysis of cyber-physical systems (CPS). FC-SSC uses stochastic system identification to learn a CPS model, importance sampling to estimate the CPS state, and importance splitting to...

Network

Cited By

Projects