This article was reprinted with permission from "ACM Computing Surveys: 28(4): December 1996, 653-670. original is available from ACM.

The team's robot software was nicknamed Their project was to develop software on the Nomad 200 robot for tasks such as maze following, office delivery, and office navigation. In both the second for the competition's Office Navigation and the final rounds, the software achieved event. The perfectly complete the task. It is equipped with 2 sonar route from the director's office to the conference rings of 16 sonars each and with 2 charge-coupled rooms, directed the robot to each of the device (CCD) cameras. The robot has a two conference rooms, correctly determined 486 processor on board with a hard drive and which conference room was not occupied, 16 megabytes of memory. The behaviors at the bottom level needed to worry about low-level responsibilities, such as avoiding obstacles and not hitting walls but did not need to know about the overall strategy for solving the task.

This article is the content of an invited talk given by the authors at the Thirteenth National Conference on Artificial Intelligence (AAAI-96). The piece begins with a short history of the competition, then discusses the technical challenges and the political and cultural issues associated with bringing it off every year. We also cover the science and engineering involved with the robot tasks and the educational and commercial aspects of the competition. We finish with a discussion of the community formed by the organizers, participants, and the conference attendees. The original talk made liberal use of video clips and slide photographs; so, we have expanded the text and added photographs to make up for the lack of such media.

That the Strong AI is still alive may have a lot to do with its avoidance of true tests. But when I show to win the Simon Newcomb fond) is silly. We would now retract our which runs as follows. P is a precise disproof of p, then upon hearing their beloved m classified P too is silly. Though Strong AI is simply silly, as silly.

This article discusses the use of fast (60 frames per second) object tracking using the COGNACHROME VISION SYSTEM, produced by Newton Research Labs. The authors embedded the vision system in a small robot base to tie for first place in the Clean Up the Tennis Court event at the 1996 Annual AAAI Mobile Robot Competition and Exhibition, held as part of the Thirteenth National Conference on Artificial Intelligence. Of particular interest is that the authors' entry was the only robot capable of using a gripper to capture and pick up the motorized, randomly moving squiggle ball. Other examples of robotic systems using fast vision tracking are also presented, such as a robot arm capable of catching thrown objects and the soccer-playing robot team that won the 1996 Micro Robot World Cup Soccer Tournament in Taejon, Korea.

Most modern formalisms used in Databases and Artificial Intelligence for describing an application domain are based on the notions of class (or concept) and relationship among classes. One interesting feature of such formalisms is the possibility of defining a class, i.e., providing a set of properties that precisely characterize the instances of the class. Many recent articles point out that there are several ways of assigning a meaning to a class definition containing some sort of recursion. In this paper, we argue that, instead of choosing a single style of semantics, we achieve better results by adopting a formalism that allows for different semantics to coexist. We demonstrate the feasibility of our argument, by presenting a knowledge representation formalism, the description logic muALCQ, with the above characteristics. In addition to the constructs for conjunction, disjunction, negation, quantifiers, and qualified number restrictions, muALCQ includes special fixpoint constructs to express (suitably interpreted) recursive definitions. These constructs enable the usual frame-based descriptions to be combined with definitions of recursive data structures such as directed acyclic graphs, lists, streams, etc. We establish several properties of muALCQ, including the decidability and the computational complexity of reasoning, by formulating a correspondence with a particular modal logic of programs called the modal mu-calculus.

Previous approaches of analyzing spontaneously spoken language often have been based on encoding syntactic and semantic knowledge manually and symbolically. While there has been some progress using statistical or connectionist language models, many current spoken- language systems still use a relatively brittle, hand-coded symbolic grammar or symbolic semantic component. In contrast, we describe a so-called screening approach for learning robust processing of spontaneously spoken language. A screening approach is a flat analysis which uses shallow sequences of category representations for analyzing an utterance at various syntactic, semantic and dialog levels. Rather than using a deeply structured symbolic analysis, we use a flat connectionist analysis. This screening approach aims at supporting speech and language processing by using (1) data-driven learning and (2) robustness of connectionist networks. In order to test this approach, we have developed the SCREEN system which is based on this new robust, learned and flat analysis. In this paper, we focus on a detailed description of SCREEN's architecture, the flat syntactic and semantic analysis, the interaction with a speech recognizer, and a detailed evaluation analysis of the robustness under the influence of noisy or incomplete input. The main result of this paper is that flat representations allow more robust processing of spontaneous spoken language than deeply structured representations. In particular, we show how the fault-tolerance and learning capability of connectionist networks can support a flat analysis for providing more robust spoken-language processing within an overall hybrid symbolic/connectionist framework.

Instance-based learning techniques typically handle continuous and linear input values well, but often do not handle nominal input attributes appropriately. The Value Difference Metric (VDM) was designed to find reasonable distance values between nominal attribute values, but it largely ignores continuous attributes, requiring discretization to map continuous values into nominal values. This paper proposes three new heterogeneous distance functions, called the Heterogeneous Value Difference Metric (HVDM), the Interpolated Value Difference Metric (IVDM), and the Windowed Value Difference Metric (WVDM). These new distance functions are designed to handle applications with nominal attributes, continuous attributes, or both. In experiments on 48 applications the new distance metrics achieve higher classification accuracy on average than three previous distance functions on those datasets that have both nominal and continuous attributes.

Often the parameters used in these networks needto be learned from examples. Unfortunately, estimating the parameters via exact probabilistic calculations (i.e, the EMalgorithm) is intractable even for networks with fairly small numbers of hidden units. We propose to avoid the infeasibility of the E step by bounding likelihoods instead of computing them exactly. Weintroduce extended and complementary representations for these networks and show that the estimation of the network parameters can be made fast (reduced to quadratic optimization) by performing the estimation in either of the alternative domains. The complementary networks can be used for continuous density estimation as well. 1 Introduction The appeal of probabilistic networks for knowledge representation, inference, and learning (Pearl, 1988) derives both from the sound Bayesian framework and from the explicit representation of dependencies among the network variables which allows readyincorporation of prior information into the design of the network.

Due to the simplicity and efficiency of its parameter estimation algorithm, the hidden Markov model (HMM) has emerged as one of the basic statistical tools for modeling discrete time series, finding widespread application in the areas of speech recognition (Rabinerand Juang, 1986) and computational molecular biology (Baldi et al., 1994). An HMM is essentially a mixture model, encoding information about the history of a time series in the value of a single multinomial variable (the hidden state). This multinomial assumption allows an efficient parameter estimation algorithm tobe derived (the Baum-Welch algorithm). However, it also severely limits the representational capacity of HMMs.