This book presents a methodology and philosophy of empirical science based on large scale lossless data compression. In this view a theory is scientific if it can be used to build a data compression program, and it is valuable if it can compress a standard benchmark database to a small size, taking into account the length of the compressor itself. This methodology therefore includes an Occam principle as well as a solution to the problem of demarcation. Because of the fundamental difficulty of lossless compression, this type of research must be empirical in nature: compression can only be achieved by discovering and characterizing empirical regularities in the data. Because of this, the philosophy provides a way to reformulate fields such as computer vision and computational linguistics as empirical sciences: the former by attempting to compress databases of natural images, the latter by attempting to compress large text databases. The book argues that the rigor and objectivity of the compression principle should set the stage for systematic progress in these fields. The argument is especially strong in the context of computer vision, which is plagued by chronic problems of evaluation. The book also considers the field of machine learning. Here the traditional approach requires that the models proposed to solve learning problems be extremely simple, in order to avoid overfitting. However, the world may contain intrinsically complex phenomena, which would require complex models to understand. The compression philosophy can justify complex models because of the large quantity of data being modeled (if the target database is 100 Gb, it is easy to justify a 10 Mb model). The complex models and abstractions learned on the basis of the raw data (images, language, etc) can then be reused to solve any specific learning problem, such as face recognition or machine translation.

Most current planners assume complete domain models and focus on generating correct plans. Unfortunately, domain modeling is a laborious and error-prone task. While domain experts cannot guarantee completeness, often they are able to circumscribe the incompleteness of the model by providing annotations as to which parts of the domain model may be incomplete. In such cases, the goal should be to generate plans that are robust with respect to any known incompleteness of the domain. In this paper, we first introduce annotations expressing the knowledge of the domain incompleteness, and formalize the notion of plan robustness with respect to an incomplete domain model. We then propose an approach to compiling the problem of finding robust plans to the conformant probabilistic planning problem. We present experimental results with Probabilistic-FF, a state-of-the-art planner, showing the promise of our approach.

We describe Cobot, a mixed initiative socio-semantic conversational search and recommendation system for finding health information. With Cobot, users can start a real time conversation about their health concerns. Cobot then connects relevant users together in the conversation also providing contextual recommendations relevant to the conversation. Conventional search engines and content portals provide a solitary search experience inundating the health information seeker with a hoard of information often confusing and frustrating them. Cobot brings relevant healthcare information directly or through other users without any search through natural language conversation.

Commonsense is a challenge not only for representation and reasoning but also for large scale knowledge engineering required to capture the breadth of our "everyday" world. One approach to knowledge engineering is to "outsource" the effort to the public through games that generate structured commonsense knowledge from user play. To date, such games have focused on symbolic and textual knowledge. However, an effective commonsense reasoning system will require spatial and physical reasoning capabilities. In this paper, I propose a tool for gathering commonsense information from ordinary people. It is a user-friendly 3D sculpting tool for modeling and annotating models of physical objects and spaces.

We present an ontology consisting of a theory of spatial dimension and a theory of dimension-independent mereological and topological relations in space. Though both are fairly weak axiomatizations, their interplay suffices to define various mereotopological relations and to make any necessary dimension constraints explicit. We show that models of the INCH Calculus and the Region-Connection Calculus (RCC) can be obtained from extensions of the proposed ontology.

Sustainability requires emphasizing the importance of environmental causes and effects among design knowledge from heterogeneous stakeholders to make a sustainable decision. Recently, such causes and effects have been well developed in ontological representation, which has been challenged to generate and integrate multiple domain knowledge due to its domain specific characteristics. Moreover, it is too challengeable to represent heterogeneous, domain-specific design knowledge in a standardized way. Causal knowledge can meet the necessity of knowledge integration in domains. Therefore, this paper aims to develop a causal knowledge integration system with the authors’ previous mathematical causal knowledge representation.

We apply artificial intelligence techniques to perform data analysis and activity recognition in smart homes. Sensors embedded in smart home provide primary data for reasoning about observations. The final goal is to provide appropriate assistance for residents to complete their Daily living Activities. Here, we introduce a qualitative approach that considers spatiotemporal specifications of activities in the Activity Recognition Agent to do knowledge representation and reasoning about the observations. We consider different existing uncertainties within sensors observations and Observed Agent’s activities. In the introduced approach, the more details about environment context would cause the less activity recognition process complexity and more precise functionality. To represent the knowledge, we apply the fuzzy logic to represent the world state by the fuzzified received values from sensors. The knowledge would be represented in the fuzzy context frame. To reduce the amount of collected data, meaningful changes in sensors generated values are considered to do Activity Recognition. Applying possibility distributions for event occurrence orders and sequences within different scenarios of activities realization, we are able to generate hypotheses about future possible occur-able events. The possible occur-able events and fuzzy digit parameters of their possible happening moments are represented in matrix format. The hypotheses about possible future observable contexts are generated considering spatial, temporal and other environmental parameters and then they would be ranked. Our final goal is to better explain the observations. If no possible explanation about observation be found, it would be recognized as abnormal behavior. In the case that no expected event be observed, we can reason that maybe event has occurred but not triggered and so next available events in previously learned scenarios would be expected. The system patience for number of possible missed events depends to trade-off between the degrees of resident's forgetfulness and probability of events trigger by applied sensors.

An intelligent system of the future should make its user feel comfortable, which is impossible without understanding context they coexist in. However, our past research did not treat language information as a part of the context a robot works in, and data about reasons why the user had made his decisions was not obtained. Therefore, we decided to utilize the Web as a knowledge source to discover context information that could suggest a robot's behavior when it acquires verbal information from its user or users. By comparing user utterances (blogs, Twitter or Facebook entries, not direct orders) with other people's written experiences (mostly blogs), a system can judge whether it is a situation in which the robot can perform or improve its performance. In this paper we introduce several methods that can be applied to a simple floor-cleaning robot. We describe basic experiments showing that text processing is helpful when dealing with multiple users who are not willing to give rich feedback. For example, we describe a method for finding usual reasons for cleaning on the Web by using Okapi BM25 to extract feature words from sentences retrieved by the query word "cleaning". Then, we introduce our ideas for dealing with conflicts of interest in multiuser environments and possible methods for avoiding such conflicts by achieving better situation understanding. Also, an emotion recognizer for guessing user needs and moods and a method to calculate situation naturalness are described.

Recently, several researchers have found that cost-based satisficing search with A* often runs into problems. Although some "work arounds" have been proposed to ameliorate the problem, there has not been any concerted effort to pinpoint its origin. In this paper, we argue that the origins can be traced back to the wide variance in action costs that is observed in most planning domains. We show that such cost variance misleads A* search, and that this is no trifling detail or accidental phenomenon, but a systemic weakness of the very concept of "cost-based evaluation functions + systematic search + combinatorial graphs". We show that satisficing search with sized-based evaluation functions is largely immune to this problem.

We present a case study of artificial intelligence techniques applied to the control of production printing equipment. Like many other real-world applications, this complex domain requires high-speed autonomous decision-making and robust continual operation. To our knowledge, this work represents the first successful industrial application of embedded domain-independent temporal planning. Our system handles execution failures and multi-objective preferences. At its heart is an on-line algorithm that combines techniques from state-space planning and partial-order scheduling. We suggest that this general architecture may prove useful in other applications as more intelligent systems operate in continual, on-line settings. Our system has been used to drive several commercial prototypes and has enabled a new product architecture for our industrial partner. When compared with state-of-the-art off-line planners, our system is hundreds of times faster and often finds better plans. Our experience demonstrates that domain-independent AI planning based on heuristic search can flexibly handle time, resources, replanning, and multiple objectives in a high-speed practical application without requiring hand-coded control knowledge.