Search

Social robot in service is radically changing the ways of performing tasks and it becomes a distinct and valuable nascent. To achieve persist autonomy, robotic systems implement a closed-loop consisting of at least planning, reasoning and acting phases. From the continual loop perspective, this paper presents the ROSPlan framework, as a task planning and executing platform, and it introduces the integration of the ROSPlan framework in a service robotic system. Moreover, it discusses the planning, observing, monitoring, and executing processes in detail. A use case scenario is proposed which is suitable for the experiment requirements, and it presents a service robot accomplishing an assistant task in educational campus. Considering the implementation of the ROSPlan framework, TurtleBot3 robot using Gazebo simulates the execution phase of the proposed scenario. [ABSTRACT FROM AUTHOR]

A hot topic in cyber warfare research is automating cyber operations for speed and agility, typically using Artificial Intelligence (AI) techniques. AI has been used to generate cyber attack plans since 2005, albeit for defensive purposes. This paper reports on work in progress aimed at developing a set of AI planning operators for generating attack plans for offensive cyber operations (OCO). The ultimate research goal is to develop an operator-set for the complete attack process, including foot-printing, reconnaissance, planning, target access, penetration, payload delivery, and after action review, that complies with the legal requirement to minimize collateral damage. The development of planning operators is greatly aided by first creating a formal ontology of the objects and relationships in the planning domain. There is a substantial literature on cyber attack ontologies. This literature was surveyed, showing that most ontologies are intended to help defenders classify incoming attacks. Consequently, they cover only the penetration and payload delivery phases of an attack, with the vulnerabilities exploited, attack goals, and effects being only represented in abstract terms. Only one ontology was found which modelled an attacker planning an attack. While classes representing ethical, legal, military, and physical constraints were included in the ontology, collateral effects were not represented. Accordingly, two supplementary literature surveys were done, one on ontologies for intelligence, surveillance, target acquisition, and reconnaissance (ISTAR), and the other on means for controlling collateral damage in OCO. The purpose of this paper is to summarize the results of surveying the literature on cyber attack ontologies, on ontologies for ISTAR, and on means for controlling collateral damage in OCO. The three literature surveys are described. The results show that there is a need to construct an ontology for cyber ISTAR and to detail payload delivery and execution in existing cyber attack ontologies. The requirements for such an ontology are outlined. [ABSTRACT FROM AUTHOR]

Constructing and adapting process models is highly relevant in today's business world, but time-consuming and error-prone. Several approaches address these issues by manual tasks or making use of automation in the past years. Especially the research field Automated Planning envisions a (semi-)automated construction of process models by using semantic annotations and planning techniques. We aim at an empirical analysis of the influence of Automated Planning on the task performance of process modelers compared to the task performance when using common process modeling tools. We analyze the invested effort in terms of the required time for modeling tasks and the outcome in terms of the quality of the constructed process models by means of a laboratory experiment. Our findings indicate that Automated Planning significantly improves the task performance. The quality of constructed process models is increased, and especially for larger process models, the required time for modeling tasks could be decreased. [ABSTRACT FROM AUTHOR]

In cyber warfare, launching a counter-attack should be done as fast as possible after an incoming attack, ideally cutting it short. This places severe demands on detecting the incoming attack, assessing damage, identifying the attacker, obtaining approval for a counter-attack, planning it, and preparing the resources needed. These processes take weeks or months at present, when hours or minutes are desired. Previous papers have assessed the feasibility of speeding up the digital forensics and parliamentary approval processes. This paper focuses on attack planning, assessing the state of the art in applying Artificial Intelligence (AI) techniques to automate this process. AI researchers began studying the automated generation of plans in the late 1960s. The first successful system was the Stanford Research Institute Planning System (STRIPS), developed in 1971. Since then, research into AI planning and scheduling has flourished. Milestones include the widespread use of the Planning Domain Description Language and the publication of a textbook in 2004. The technology has matured, with commercial applications in logistics, airline operations, and space exploration. The first known application to cyber operations came in 2005, when Boddy and co-workers applied AI planning techniques to generate cyber-attack plans to assess the vulnerability of information systems. The purpose of this paper is to assess the state of the art in applying AI techniques to speed up cyber-attack planning. There are five sections. After the introduction, the second section outlines the relevant literature on offensive cyber and classical AI planning. The third section focuses on adapting the military operation planning process to cyber operations. The fourth section assesses what has been achieved in applying AI techniques and what gaps remain. The fifth section draws conclusions and recommends further research. [ABSTRACT FROM AUTHOR]

The paper presents result from an NSF funded project on the design and development of control systems for ocean power plants involving moored hydrokinetic turbines. The envisioned hydrokinetic turbines are flying tethered and submerged in ocean currents. Effective energy harvesting requires active control of heading, attitude, and other operational parameters of the turbine(s).Underwater or tidal turbines are nowadays a cutting-edge technology in terms of energy harvesting. Kinetic energy of moving water masses is been transformed in electricity following basic principles of power generation. A novel approach towards a more efficient energy management, dictates the usage of electrolyzing units in order to store hydrogen and oxygen rather than the direct supply of cable connected loads. The electrolysis products when present in the correct amounts can serve external users and at the same time activate fuel cells in order to sustain autonomous operations of the power architecture. This paper presents a model and simulation of a hybrid system coupling the tidal turbines, a regenerative fuel cell and an electrolyzer. A simple electrolysis model, utilizing the power generated by the turbines and capable of providing the input parameters to the fuel cell system is been developed in this regard. Main objective of the fuel cell is to provide enough energy to the architecture to guarantee autonomous operations. A model devoted to the fuel cell operation is been implemented. The model is capable to capture both the steady state and dynamic behavior of the cell. Dynamic behaviors are of particular interest since loads can exhibit significant variations, reflected then in large fluctuations of the cell output, thus in fuel consumption. The two systems are then interconnected by means of a controller. The abundance of fuel in the storage tanks must be managed in such way that is always available to the user and the power system. Larger demand on the turbines side will activate generation on the fuel cell side, thus hydrogen and oxygen consumption. On the other hand small demand will result in a higher fuel stock inside the tanks. Thus the energy flow is regulated to guarantee optimal fuel reserve inside the tanks at all times by means of availability to the user and the system itself. The simulation results show the viability of the power architecture in terms of requirements. The output of the cell can be adapted to the demand taking into account at all times the availability of the electrolysis products. [ABSTRACT FROM AUTHOR]

This paper presents a planning simulation system that allows automated planning practitioners to experiment with planning domains, defined using the PDDL language. The proposed system has a modular architecture including a SAT planner (PDDL parser, SAT encoder and SAT solver), a plan simulator and a 3D view user interface. Most of these modules can be changed with other with similar purpose. This system allows users to test and validate PDDL domains and solutions, using an attractive user interface that includes the simulation of the execution of the plan on a 3D view as an animation. [ABSTRACT FROM AUTHOR]

This paper presents a planning simulation system that allows automated planning practitioners to experiment with planning domains, defined using the PDDL language. The proposed system has a modular architecture including a SAT planner (PDDL parser, SAT encoder and SAT solver), a plan simulator and a 3D view user interface. Most of these modules can be changed with other with similar purpose. This system allows users to test and validate PDDL domains and solutions, using an attractive user interface that includes the simulation of the execution of the plan on a 3D view as an animation. [ABSTRACT FROM AUTHOR]

The Sentential Decision Diagram (SDD) is a novel data structure that compactly represents Boolean functions, like Binary Decision Diagrams (BDDs), but with a theoretical advantage in some classes of functions, when SDDs may be exponentially smaller than BDDs. Algebraic Decision Diagrams (ADDs) are an extension of BDDs which allows numeric values in terminal nodes, for representing factored case functions onto real numbers. In this paper, we propose an algebraic extension of SDDs, the Algebraic SDD (ASDD), and examine its suitability in probabilistic planning using a symbolic value iteration algorithm that employs ASDDs to maintain and manipulate its functions when solving Markov Decision Problems (MDPs). [ABSTRACT FROM PUBLISHER]

Change Management, a core process of the Information Technology Infrastructure Library (ITIL), is concerned with the management of changes to networks and services to minimize costly disruptions on the business. As part of Change Management, IT changes need to be planned. Previous approaches to automatically generate IT change plans struggle, in terms of scalability, to properly deal with large Configuration Management Databases (CMDBs). To enable IT change planning in the large, in this paper we discuss and analyze optimizations for refinement-based IT change planning over object-oriented CMDBs. Our optimizations reduce the runtime complexity of several key operations part of refinement-based IT change planning algorithms. A sensitivity analysis shows that our optimizations outperform SHOP2 - the winner of a previous comparison among IT change planners - in terms of runtime complexity for several important characteristics of IT changes and CMDBs. A cloud deployment case study of a Three-tier application and a virtual network configuration case study demonstrate the feasibility of our approach and confirm the results from the sensitivity analysis: IT change planning has evolved from planning in the small to planning in the large. [ABSTRACT FROM PUBLISHER]

We propose a method for learning interactions among objects when intermediate state information is not available. Learning is accomplished by observing a given sequence of actions on different objects. We have selected the Incredible Machine game as a suitable domain for analyzing and learning object interactions. We first present how behaviors are represented by finite state machines using the given input. Then, we analyze the impact of the knowledge about relations on the overall performance. Our analysis includes four different types of input: a knowledge base including part relations; spatial information; temporal information; and spatio-temporal information. We show that if a knowledge base about relations is provided, learning is accomplished to a desired extent. Our analysis also indicates that the spatio-temporal approach is superior to the spatial and the temporal approaches and gives close results to that of the knowledge-based approach. [ABSTRACT FROM PUBLISHER]