Research effort, with its emphasis on evaluation and measurable progress, things began to change. Instead SHRDLU (WIN72) is perhaps the canonical example. of systems whose architecture and vocabulary were The rapid growth of efforts to found the next generation of based on linguistic theory (in this case acoustic phonetics), systems on general-purpose knowledge representation languages new approaches based on statistical modelling and Bayesian (I'm thinking of several varieties of semantic nets, probability emerged and quickly spread. "Every time I fire a from plain to partitioned, as well as KRL, KL-ONE and linguist my system's performance improves" (Fred Jellinek, their successors, ending (not yet, of course) with CYC (See head of speech recognition at IBM, c. 1980, latterly repudiated (BRA08) for all these) stumbled to a halt once their failure by Fred but widely attested). As advanced from resolution theorem provers through a number more and more problems are re-conceived as instances of of stages to the current proliferation of a range of Description the noisy channel model, the empiricist paradigm continually Logic'reasoners'; Whereas in the 1970s and 1980s there grew, so did the need to manage the impact of change and was real energy and optimism at the interface between computational conflict: enter'truth maintenance', subsequently renamed and theoretical linguistics, the overwhelming success'reason maintenance'. While still using some of But outflanking these'normal science' advances of AI, the terminology of linguistic theory, computational linguistics the paradigm shifters were coming up fast on the outside: practioners are increasingly detached from theory itself, over the last ten years machine learning has spread from which has suffered a, perhaps connected, loss of energy and small specialist niches such as speech recognition to become sense of progress.

This paper presents an approach to integrating planning and execution in time-sensitive environments. We present a simple setting in which to consider the issue, that we call continual on-line planning. New goals arrive stochastically during execution, the agent issues actions for execution one at a time, and the environment is otherwise deterministic. We take the objective to be a form of time-dependent partial satisfaction planning reminiscent of discounted MDPs: goals offer reward that decays over time, actions incur fixed costs, and the agent attempts to maximize net utility. We argue that this setting highlights the central challenge of time-aware planning while excluding the complexity of non-deterministic actions. Our approach to this problem is based on real-time heuristic search. We view the two central issues as the decision of which partial plans to elaborate during search and the decision of when to issue an action for execution. We propose an extension of Russell and Wefald's decision-theoretic A* algorithm that can cope with our inadmissible heuristic. Our algorithm, DTOCS, handles the complexities of the on-line setting by balancing deliberative planning and real-time response.

Sensor-to-symbol conversion lies at the heart of all embedded intelligent systems. The everyday world occupied by human stakeholders is dominated by objects that have symbolic labels. For an embedded intelligent system to operate in such a world it must also be able to segment its sensory stream into objects and label those objects appropriately. It is our position that development of a consistent and flexible sensor-to-symbol reasoning system (or architecture) is a key component of embedded intelligence.

Integrating robotics activities in science curriculum provides rich opportunities to engage students in real world science and help them to develop conceptual understanding of physics principles through the process of investigation, data analysis, engineering design, and construction. In addition, students become more confident learners and develop better problem-solving and teamwork skills. In this paper we describe a successful use of LEGO® MINDSTORMS® in designing robotics-based activities for teaching high school physics classes. Students design and perform novel science investigations with a toolset that helps them achieve a high reproducibility in their experimental designs. Several example projects that utilize LEGO MINDSTORMS are presented.

This paper presents a brief summary of a number of different approaches to the semantic representation and automated interpretation of engineering data. In this context, engineering data is represented as Computer-Aided Design (CAD) files, 3D models or assemblies. Representing and reasoning about these objects is a highly interdisciplinary problem, requiring techniques that can handle the complex interactions and data types that occur in the engineering domain. This paper presents several examples, taken from different problem areas that have occupied engineering and computer science researchers over the past 15 years. Many of the issues raised by these problems remain open, and the experience of past efforts can serve to identify fertile opportunities for investigation today.

The Web of Data (WoD) is growing at an amazing rate and it will no longer be feasible to deal with it in a global way, by centralising the data or reasoning processes making use of that data. We believe that Computational Intelligence techniques provides the adaptiveness, robustness and scalability that will be required to exploit the full value of ever growing amounts of dynamic Semantic Web data.

For autonomous systems such as unmanned aerial vehicles tosuccessfully perform complex missions, a great deal of embedded reasoning is required at varying levels of abstraction. In order to make use of diverse reasoning modules in such systems, issues ofintegration such as sensor data flow and information flow between such modules has to be taken into account. The DyKnow framework is a tool with a formal basis that pragmatically deals with many of the architectural issues which arise in such systems. This includes a systematic stream-based method for handling the sense-reasoning gap,caused by the wide difference in abstraction levels between the noisy data generally available from sensors and the symbolic, semantically meaningful information required by many high-level reasoning modules. DyKnow has proven to be quite robust and widely applicable to different aspects of hybrid software architectures forrobotics. In this paper, we describe the DyKnow framework and show how it is integrated and used in unmanned aerial vehicle systems developed in our group. In particular, we focus on issues pertaining to the sense-reasoning gap and the symbol grounding problem and the use of DyKnow as a means of generating semantic structures representing situational awareness for such systems. We also discuss the use of DyKnow in the context of automated planning, in particular execution monitoring.

In this paper we address an issue that has been brought to the attention of the database community with the advent of the Semantic Web, i.e. the issue of how ontologies (and semantics conveyed by them) can help solving typical database problems, through a better understanding of KR aspects related to databases. In particular, we investigate this issue from the ILP perspective by considering two database problems, (i) the definition of views and (ii) the definition of constraints, for a database whose schema is represented also by means of an ontology. Both can be reformulated as ILP problems and can benefit from the expressive and deductive power of the KR framework DL+log. We illustrate the application scenarios by means of examples. Keywords: Inductive Logic Programming, Relational Databases, Ontologies, Description Logics, Hybrid Knowledge Representation and Reasoning Systems. Note: To appear in Theory and Practice of Logic Programming (TPLP).

Korf, Reid, and Edelkamp introduced a formula to predict the number of nodes IDA* will expand on a single iteration for a given consistent heuristic, and experimentally demonstrated that it could make very accurate predictions. In this paper we show that, in addition to requiring the heuristic to be consistent, their formula's predictions are accurate only at levels of the brute-force search tree where the heuristic values obey the unconditional distribution that they defined and then used in their formula. We then propose a new formula that works well without these requirements, i.e., it can make accurate predictions of IDA*'s performance for inconsistent heuristics and if the heuristic values in any level do not obey the unconditional distribution. In order to achieve this we introduce the conditional distribution of heuristic values which is a generalization of their unconditional heuristic distribution. We also provide extensions of our formula that handle individual start states and the augmentation of IDA* with bidirectional pathmax (BPMX), a technique for propagating heuristic values when inconsistent heuristics are used. Experimental results demonstrate the accuracy of our new method and all its variations.

In this paper we introduce a new algorithm for updating the parameters of a heuristic evaluation function, by updating the heuristic towards the values computed by an alpha-beta search. Our algorithm differs from previous approaches to learning from search, such as Samuels checkers player and the TD-Leaf algorithm, in two key ways. First, we update all nodes in the search tree, rather than a single node. Second, we use the outcome of a deep search, instead of the outcome of a subsequent search, as the training signal for the evaluation function. We implemented our algorithm in a chess program Meep, using a linear heuristic function. After initialising its weight vector to small random values, Meep was able to learn high quality weights from self-play alone. When tested online against human opponents, Meep played at a master level, the best performance of any chess program with a heuristic learned entirely from self-play.