Michal Jakob

Autonomous UAV Surveillance in Complex Urban Environments

We address the problem of multi-UAV-based surveillance in complex urban environments with occlusions. The problem consists of controlling the flight of UAVs with on-board cameras so that the coverage and recency of the information about the designated area is maximized. In contrast to the existing work, sensing constraints due to occlusions and UAV motion constraints are modeled realistically and taken into account. We propose a novel \emph{occlusion-aware} surveillance algorithm based on a decomposition of the surveillance problem into a variant of the 3D art gallery problem and an instance of traveling salesman problem for Dubins vehicles. The algorithm is evaluated on the high-fidelity \textsc{AgentFly} UAV simulation testbed which accurately models all constraints and effects involved. The results confirm the importance of occlusion-aware flight path planning, in particular in the case of narrow-street areas and low UAV flight altitudes.

Using Agents to Improve International Maritime Transport Security

Agent-based techniques have the potential to improve the security of international maritime transport threatened by a steep rise of maritime piracy. We have demonstrated that a randomized route-selection strategy resulting from a normal two-player game formulation of the transit problem can decrease the number of attacks and the payoff accumulated by pirates. Coordinating the movement of patrol and transit vessels without a central authority requires techniques for semi-cooperative planning and coalition formation. With regard to existing applications of agent-based techniques, the maritime domain seems currently under-represented compared to other traffic and transportation domains. This work is a first step in addressing the situation and bringing this important domain into the focus of researchers in the multiagent systems field.

Transiting areas patrolled by a mobile adversary

We study the problem of a mobile agent trying to cross an area patrolled by a mobile adversary. The transiting agent aims to choose its route so as to minimize the probability of hostile encounter; the patroller agent, controlling one or more patrol units, aims at the opposite. We model the problem as a two-player zero-sum game (termed transit game) and search for an optimum route selection strategy as a mixed Nash equilibrium of the game. In contrast to existing game-theoretic models of this kind, we explicitly consider the limited endurance of patrols and the notion of bases to which the patrols need to repeatedly return. Noting the prohibitive size of the transit game, we employ two techniques for reducing the complexity of finding Nash equilibria - a compact network-flow-based representation of transit routes and iterative single- and double-oracle algorithms for incremental game matrix construction. We measure the computational time of all the methods on a range of transit game instances. In order to assess the practical relevance of the approach, we apply the transit game model and its solution to the real-world case of ship transit through areas affected by piracy. The results obtained using an agent-based simulation of maritime traffic show that the randomized game-theoretic transit routing strategy results in a lower number of pirate attacks than the currently employed method based on static transit corridors.

Using multi-agent simulation to improve the security of maritime transit

Despite their use for modeling traffic in ports and regional waters, multi-agent simulations have not yet been applied to model maritime traffic on a global scale. We therefore propose a fully agent-based, data-driven model of global maritime traffic, focusing primarily on modeling transit through piracy-affected waters. The model employs finite state machines to represent the behavior of several classes of vessels and can accurately replicate global shipping patterns and approximate real-world distribution of pirate attacks. We apply the model to the problem of optimizing the Gulf of Aden group transit. The results demonstrate the usefulness of agent-based modeling for evaluating and improving operational counter-piracy policies and measures.

Mixed-reality testbeds for incremental development of HART applications

An incremental process for developing human-agent-robot applications uses mixed-reality testbeds of varying fidelity and size.

Distributed Platform for Large-Scale Agent-Based Simulations

We describe a distributed architecture for situated large-scale agent-based simulations with predominately local interactions. The approach, implemented in AglobeX Simulation platform, is based on a spatially partitioned simulated virtual environment and allocating a dedicated processing core to the environment simulation within each partition. In combination with dynamic load-balancing, such partitioning enables virtually unlimited scalability of the simulation platform. The approach has been used to extend the AgentFly air-traffic test-bed to support simulation of a complete civilian air-traffic touching National Air-Space of United States. Thorough evaluation of the system has been performed, confirming that it can scale up to a very high number of complex agents operating simultaneously (thousands of aircraft) and determining the impact of different configurations of the simulation architecture on its overall performance.

Generalised time-dependent graphs for fully multimodal journey planning

We solve the fully multimodal journey planning problem, in which journey plans can employ any combination of scheduled public transport (e.g., bus, tram and underground), individual (e.g., walk, bike, shared bike and car), and on-demand (e.g., taxi) transport modes. Our solution is based on a generalised time-dependent graph that allows representing the fully multimodal earliest arrival problem as a standard graph search problem and consequently using general shortest path algorithms to solve it. In addition, to allow users to express their journey planning preferences and to speed up the search process, flexible journey plan templates can be used in our approach to restrict the transport modes and mode combinations permitted in generated journey plans. We have evaluated our solution on a real-world transport network of the city of Helsinki and achieved practically usable search runtimes in the range of hundreds of milliseconds.

Modular framework for simulation modelling of interaction-rich transport systems

The increasing pervasiveness of information and communication technology (ICT) in transport systems changes the requirements on techniques and tools for transport simulation modelling. Novel ICT-powered responsive mobility services, such as real-time on-demand transport, are interaction-rich in a sense that they rely on frequent, ad hoc interactions between various entities of the transport system. These interactions have to be properly captured in the model if it is to accurately represent the dynamics of the modelled transport system. Unfortunately, existing modelling tools are not well suited for modelling interaction-rich transport systems. We have therefore developed a novel modular simulation framework designed specifically for modelling transport systems in which ad hoc interactions and decision making play an important role. The framework provides an extensible library of modelling elements based on a unifying ontology of agent-based modelling abstractions, a high-performance discrete-event simulation engine and suite of tools supporting real-world deployment and utilization of implemented models. By fully leveraging the conceptual foundation of multiagent systems, our framework provides flexibility and extensibility that is difficult to achieve by existing approaches. We demonstrate the applicability of the framework on the models of five distinct interaction-rich transport systems.

Market-Inspired approach to collaborative learning

The paper describes a decentralized peer-to-peer multi-agent learning method based on inductive logic programming and knowledge trading. The method uses first-order logic for model representation. This enables flexible sharing of learned knowledge at different levels of abstraction as well as seamless integration of models created by other agents. A market-inspired mechanism involving knowledge trading is used for inter-agent coordination. This allows for decentralized coordination of learning activity without the need for a central control element. In addition, agents can participate in collaborative learning while pursuing their individual goals and maintaining full control over the disclosure of their private information. Several different types of agents differing in the level and form of knowledge exchange are considered. The mechanism is evaluated using a set of performance criteria on several scenarios in a realistic logistic domain extended with adversary behavior. The results show that using the proposed method agents can collaboratively learn properties of their environment, and consequently significantly improve their operation.

Agent-based Simulation Testbed for On-demand Mobility Services☆

Abstract New markets for personalized and efficient transport are creating a need for on-demand mobility services. To rigorously analyse new control mechanisms for these services, we introduce an open-source agent-based simulation testbed that allows users to eva- luate the performance of multi-agent, on-demand transport schemes. In particular, our testbed provides a framework to compare both centralized and decentralized, static and dynamic passenger allocation and vehicle routing mechanisms under various con- ditions; including varying vehicle fleets, road network topologies and passenger demands. Our testbed supports all stages of the experimental process; from the implementation of control mechanisms and the definition of experiment scenarios, through to simu- lation execution, analysis, and interpretation of results. Ultimately, the testbed accelerates the development of control mechanisms for emerging on-demand mobility services and facilitates their comparison using well-defined benchmarks.