Commercial AI Trends Seen at AAAI-Extracting the Knowledge of 87 8(4): (Winter 19871, 93-95.

A numeric representation of uncertain and incomplete sensor knowledge called certainty grids was used successfully in several recent mobile robot control programs developed at the Carnegie-Mellon University Mobile Robot Laboratory (MRL). Certainty grids have proven to be a powerful and efficient unifying solution for sensor fusion, motion planning, landmark identification, and many other central problems. MRL had good early success with ad hoc formulas for updating grid cells with new information. A new Bayesian statistical foundation for the operations promises further improvement. MRL proposes to build a software framework running on processors onboard the new Uranus mobile robot that will maintain a probabilistic, geometric map of the robot's surroundings as it moves. The certainty grid representation will allow this map to be incrementally updated in a uniform way based on information coming from various sources, including sonar, stereo vision, proximity, and contact sensors. The approach can correctly model the fuzziness of each reading and, at the same time, combine multiple measurements to produce sharper map features; it can also deal correctly with uncertainties in the robot's motion. The map will be used by planning programs to choose clear paths, identify locations (by correlating maps), identify well-known and insufficiently sensed terrain, and perhaps identify objects by shape. The certainty grid representation can be extended in the time dimension and used to detect and track moving objects. Even the simplest versions of the idea allow us to fairly straightforwardly program the robot for tasks that have hitherto been out of reach. MRL looks forward to a program that can explore a region and return to its starting place, using map "snapshots" from its outbound journey to find its way back, even in the presence of disturbances of its motion and occasional changes in the terrain.

Sometimes less ambiguous, are extremely complex.

Subsequent chapters extend these techniques to the recognition of isolated curved objects using a graph model, interpretation of imperfect regions using a scene model, and recognition of multiple objects using Z-D object models. Shirai proceeds in a logical fashion two-dimensional pattern (2-D) recognition, pleted, the author concentrates on the from 2-D analysis, to line drawing such as character recognition 3-D world. The next two chapters deal interpretation, to the analysis of range or the recognition of silhouettes. The chapter on range data irregular objects using fractals and brief description of the field, the processing is a very strong one that superquadrics. This is followed by a reference source for researchers analysis, edge linking and following, chapter on three-dimensional description in 3-D vision.

In this article, principles involving the intrinsic, deictic, and extrinsic use of spatial prepositions are examined from linguistic, psychological, and AI approaches. First, I define some important terms. Second, those prepositions which permit intrinsic, deictic, and extrinsic use are specified. Third, I examine how the frame of reference is determined for all three cases. Fourth, I look at ambiguities in the use of prepositions and how they can be resolved. Finally, I introduce the natural language dialog system CITYTOUR, which can cope with the intrinsic, deictic, and extrinsic use of spatial prepositions, and compare it with the approaches dealt with in the previous sections as well as to some other AI systems.

Review of Expert Systems: Techniques, Tools, and Applications

We propose an approach for meeting real-time constraints in AI systems that views (1) time as a resource that should be considered when making control decisions, (2) plans as ways of expressing control decisions, and (3) approximate processing as a way of satisfying time constraints that cannot be achieved through normal processing.

However, a substantial amount of research is still needed to solve many difficult problems before real-time expert systems can enhance current monitoring and control systems. In this article, we examine how the real-time problem domain is significantly different from those domains which have traditionally been solved by expert systems. The survey is divided into three areas: applications, tools, and theoretic issues. From the results of the survey, we identify a set of real-time research issues that have yet to be solved and point out limitations of current tools for real-time problems.

The second Natural Language Understanding and Logic Programming (NLULP) Workshop was held on 17-19 August 1987 at Simon Fraser University, Vancouver, British Columbia, Canada, (the first NLULP workshop was held three years ago in Rennes, France).

I compare the big problems studied in artificial intelligence and related fields in order to understand some major changes -- both internal and external -- recently suffered by AI. The comparison finds AI with few problems to call its own, and I identify some further major changes that may occur soon.