Technology
Letters to the Editor
Milnes, Brian G., Mettrey, Willliam, Kak, Subhash C., David, Bruce, Tsatsoulis, Costas, Kline, Fred
Letters to the Editor
Review of Three-Dimensional Computer Vision
Review of Three-Dimensional Computer Vision
New Hitech Computer Chess Success
Carnegie-Mellon University's Hitech chess computer scored 5-1 in the National Open Chess Championships held in Chicago March 18-20. The Championship Section in which Hitech competed, had 380 entries. Carnegie-Mellon University's Hitech chess computer scored 5-1 in the National Open Chess Championships held in Chicago March 18-20. The Championship Section in which Hitech competed, had 380 entries.
Sensor Fusion in Certainty Grids for Mobile Robots
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). 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 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.
What AI Pratitioners Should Know about the Law Part Two
This is Part 2 of a two-part article and discusses issues of tort liability and the use of computers in the courtroom. Part 1 of this article, which appeared in the Spring 1988 issue of AI Magazine, discussed steps that developers of AI systems can take to protect their efforts, and the attendant legal ambiguities that must eventually be addressed in order to clarify the scope of such protection. Part 2 explores the prospect of AI systems as subjects of litigation.
Evidence Accumulation and Flow of Control in a Hierarchical Spatial Reasoning System
A fundamental goal of computer vision is the development of systems capable of carrying out scene interpretation while taking into account all the available knowledge. In this article, we focus on how the interpretation task can be aided by the expected scene information (such as map knowledge), which, in most cases, would not be in registration with the perceived scene. The system is implemented as a two-panel, six-level blackboard and uses the Dempster-Shafer formalism to accomplish inexact reasoning in a hierarchical space. Inexact reasoning involves exploiting, at different levels of abstraction, any internal geometric consistencies in the data and between the data and the expected scene.