Добірка наукової літератури з теми "Event Detection, Event Calculus, Answer Set Programming"

Circumscription and logic programs under the stable model semantics are two well-known nonmonotonic formalisms. The former has served as a basis of classical logic based action formalisms, such as the situation calculus, the event calculus and temporal action logics; the latter has served as a basis of a family of action languages, such as language A and several of its descendants. Based on the discovery that circumscription and the stable model semantics coincide on a class of canonical formulas, we reformulate the situation calculus and the event calculus in the general theory of stable models. We also present a translation that turns the reformulations further into answer set programs, so that efficient answer set solvers can be applied to compute the situation calculus and the event calculus.

AbstractAutomated commonsense reasoning (CR) is essential for building human-like AI systems featuring, for example, explainable AI. Event calculus (EC) is a family of formalisms that model CR with a sound, logical basis. Previous attempts to mechanize reasoning using EC faced difficulties in the treatment of the continuous change in dense domains (e.g. time and other physical quantities), constraints among variables, default negation, and the uniform application of different inference methods, among others. We propose the use of s(CASP), a query-driven, top-down execution model for Predicate Answer Set Programming with Constraints, to model and reason using EC. We show how EC scenarios can be naturally and directly encoded in s(CASP) and how it enables deductive and abductive reasoning tasks in domains featuring constraints involving both dense time and dense fluents.

AbstractThe quality of robot-assisted surgery can be improved and the use of hospital resources can be optimized by enhancing autonomy and reliability in the robot’s operation. Logic programming is a good choice for task planning in robot-assisted surgery because it supports reliable reasoning with domain knowledge and increases transparency in the decision making. However, prior knowledge of the task and the domain is typically incomplete, and it often needs to be refined from executions of the surgical task(s) under consideration to avoid sub-optimal performance. In this paper, we investigate the applicability of inductive logic programming for learning previously unknown axioms governing domain dynamics. We do so under answer set semantics for a benchmark surgical training task, the ring transfer. We extend our previous work on learning the immediate preconditions of actions and constraints, to also learn axioms encoding arbitrary temporal delays between atoms that are effects of actions under the event calculus formalism. We propose a systematic approach for learning the specifications of a generic robotic task under the answer set semantics, allowing easy knowledge refinement with iterative learning. In the context of 1000 simulated scenarios, we demonstrate the significant improvement in performance obtained with the learned axioms compared with the hand-written ones; specifically, the learned axioms address some critical issues related to the plan computation time, which is promising for reliable real-time performance during surgery.

Abstract Complex Event Recognition (CER) systems detect event occurrences in streaming time-stamped input using predefined event patterns. Logic-based approaches are of special interest in CER, since, via Statistical Relational AI, they combine uncertainty-resilient reasoning with time and change, with machine learning, thus alleviating the cost of manual event pattern authoring. We present a system based on Answer Set Programming (ASP), capable of probabilistic reasoning with complex event patterns in the form of weighted rules in the Event Calculus, whose structure and weights are learnt online. We compare our ASP-based implementation with a Markov Logic-based one and with a number of state-of-the-art batch learning algorithms on CER data sets for activity recognition, maritime surveillance and fleet management. Our results demonstrate the superiority of our novel approach, both in terms of efficiency and predictive performance. This paper is under consideration for publication in Theory and Practice of Logic Programming (TPLP).

Cette thèse s’inscrit dans le cadre du projet ANR eThicAa, dont les ambitions ont été : de définir ce que sont des agents autonomes éthiques, de produire des représentations formelles des conflits éthiques et de leurs objets (au sein d’un seul agent autonome, entre un agent autonome et le système auquel il appartient, entre un agent autonome et un humain, entre plusieurs agents autonomes) et d’élaborer des algorithmes d’explication pour les utilisateurs humains. L’objet de la thèse plus particulièrement a été d’étudier la modélisation de conflits éthiques au sein d’un seul agent, ainsi que la production d’algorithmes explicatifs. Ainsi, le travail présenté ici décrit l’utilisation de langages de haut niveau dans la conception d’agents autonomes éthiques. Il propose un cadre logique nouveau et modulaire pour représenter et raisonner sur une variété de théories éthiques, sur la base d’une version modifiée du calcul des événements, implémentée en Answer Set Programming. Le processus de prise de décision éthique est conçu comme une procédure en plusieurs étapes, capturée par quatre types de modèles interdépendants qui permettent à l’agent d’évaluer son environnement, de raisonner sur sa responsabilité et de faire des choix éthiquement informés. En particulier, un modèle d’action permet à l’agent de représenter des scénarios et les changements qui s’y déroulent, un modèle causal piste les conséquences des décisions prises dans les scénarios, rendant possible un raisonnement sur la responsabilité et l’imputabilité des agents, un modèle du Bien donne une appréciation de la valeur éthique intrinsèque de finalités ou d’évènements, un modèle du Juste détermine les décisions acceptables selon des circonstances données. Le modèle causal joue ici un rôle central, car il permet d’identifier des propriétés que supposent les relations causales et qui déterminent comment et dans quelle mesure il est possible d’en inférer des attributions de responsabilité. Notre ambition est double. Tout d’abord, elle est de permettre la représentation systématique d’un nombre illimité de processus de raisonnements éthiques, à travers un cadre adaptable et extensible en vertu de sa hiérarchisation et de sa syntaxe standardisée. Deuxièmement, elle est d’éviter l’écueil de certains travaux d’éthique computationnelle qui directement intègrent l’information morale dans l’engin de raisonnement général sans l’expliciter – alimentant ainsi les agents avec des réponses atomiques qui ne représentent pas la dynamique sous-jacente. Nous visons à déplacer de manière globale le fardeau du raisonnement moral du programmeur vers le programme lui-même
This thesis is part of the ANR eThicAa project, which has aimed to define moral autonomous agents, provide a formal representation of ethical conflicts and of their objects (within one artificial moral agent, between an artificial moral agent and the rules of the system it belongs to, between an artificial moral agent and a human operator, between several artificial moral agents), and design explanation algorithms for the human user. The particular focus of the thesis pertains to exploring ethical conflicts within a single agent, as well as designing explanation algorithms. The work presented here investigates the use of high-level action languages for designing such ethically constrained autonomous agents. It proposes a novel and modular logic-based framework for representing and reasoning over a variety of ethical theories, based on a modified version of the event calculus and implemented in Answer Set Programming. The ethical decision-making process is conceived of as a multi-step procedure captured by four types of interdependent models which allow the agent to represent situations, reason over accountability and make ethically informed choices. More precisely, an action model enables the agent to appraise its environment and the changes that take place in it, a causal model tracks agent responsibility, a model of the Good makes a claim about the intrinsic value of goals or events, and a model of the Right considers what an agent should do, or is most justified in doing, given the circumstances of its actions. The causalmodel plays a central role here, because it permits identifying some properties that causal relations assume and that determine how, as well as to what extent, we may ascribe ethical responsibility on their basis. The overarching ambition of the presented research is twofold. First, to allow the systematic representation of an unbounded number of ethical reasoning processes, through a framework that is adaptable and extensible by virtue of its designed hierarchisation and standard syntax. Second, to avoid the pitfall of some works in current computational ethics that too readily embed moralinformation within computational engines, thereby feeding agents with atomic answers that fail to truly represent underlying dynamics. We aim instead to comprehensively displace the burden of moral reasoning from the programmer to the program itself

In this age of the digital era, the rapid growth of video content is a common trend. Automated analysis for video content understanding is one of the most challenging and well researched area in the domain of artificial intelligence. In this thesis, we address this issue by analyzing and detecting events in videos. The automatic recognition of events in videos can be formally defined as: "detecting interactions between human-object, object-object or human-human activity in a certain scene". Such events are often referred to as simple events, whereas, complex event detection is even more demanding as it involves complicated interactions among objects in the scene. Complex event detection often provides rich semantic understanding in videos, and thus has excellent prospective for many practical applications, such as entertainment industry, sports analytic, surveillance video analysis, video indexing and retrieval, and many more. In the context of computer vision, most of the traditional action recognition techniques assign a single label to a video after analyzing the whole video. They use various low-level features with learning models and achieve promising performance. In the past few years, there has been significant progress in the domain of video understanding. For example, supervised learning and efficient deep learning models have been used to classify several possible actions in videos, representing the whole clip with a single label. However, applying supervised learning to understand each frame in a video is time-consuming and expensive, since it requires per-frame labels in videos of the event of interest. To accomplish this task, annotators apply fine-grained labels to videos by manually adding precise labels to every frame in each video. Only then can the model be trained, and that also mostly on atomic action. Training on new event requires the process to be repeated. Also, such approaches lack the potential of interpreting the semantic content associated with complex video events. To sum up, we believe that understanding of the visual world is not limited to recognizing a specific action class or individual object instances, but also extends to how those objects interact in the scene, which implies recognizing simple and complex events happening in the scene. In this thesis we present an approach for identifying complex events in videos, starting from detection of objects and simple events using a state-of-the-art object detector (YOLO). It is used both to detect and to track objects in video frames. In this way, it is possible to locate moving objects in a video over time in order to enhance both the definition of events involving the objects considered and the activity of event detection. We provide a logic based representation of events by using a realization of the Event calculus that allows us to define complex events in terms of logical rules. Axioms of the calculus are encoded in a logic program under Answer Set semantics in order to reason and formulate queries over the extracted events. The applicability of the framework is demonstrated over scenarios like "occupancy of the handicap slot", recognizing different kinds of "kick" events in soccer videos. The results compare favorably with those achieved by the use of deep neural networks.

Complex Event Recognition (CER) systems detect event occurrences in streaming time-stamped input using predefined event patterns. Logic-based approaches are of special interest in CER, since, via Statistical Relational AI, they combine uncertainty-resilient reasoning with time and change, with machine learning, thus alleviating the cost of manual event pattern authoring. We present WOLED, a system based on Answer Set Programming (ASP), capable of probabilistic reasoning with complex event patterns in the form of weighted rules in the Event Calculus, whose structure and weights are learnt online. We compare our ASP-based implementation with a Markov Logic-based one and with a crisp version of the algorithm that learns unweighted rules, on CER datasets for activity recognition, maritime surveillance and fleet management. Our results demonstrate the superiority of our novel implementation, both in terms of efficiency and predictive performance.