A system that allows a robot to acquire a model of its environment and to use this model to navigate is described. The system maps the environment as a set of snapshots of the world taken at target locations. The robot uses an image-based local homing algorithm to navigate between neighboring target locations. Features of the approach include an imaging system that acquires a compact, 360 degrees representation of the environment and an image-based, qualitative homing algorithm that allows the robot to navigate without explicitly inferring three-dimensional structure from the image. The results of an experiment in a typical indoor environment are described, and its argued that image-based navigation is a feasible alternative to approaches using three-dimensional models.>

A system able to control the Utah/MIT hand with the VPL DataGlove has been developed. To get the actual joint angles from the DataGlove sensor values, a least-squares fit is used to find the best-fit exponential curve for each sensor, and then the correlation between the sensors is reduced by the iterative correlation elimination procedure. The calibration depends both on the wearer and the particular DataGlove being used. The first level calibration is simple and can be done in under 15 minutes with a little experience. The second level is fixed and requires no adjustments. To control the hand, a mapping from the DataGlove angles to the hand angles is applied, making the hand fingertips follow the DataGlove fingertips. The hand can successfully implement various high-level tasks under the DataGlove wearer's control.>

A study is made of the performance of a real-time system in which jobs all have deadlines for either the beginning or the end of service. In the first case the authors analyze the minimum laxity (ML) scheduling policy when there are c processors, and in the latter case they analyze the preemptive-resume earliest deadline (ED) scheduling policy when there is one server. In both cases, the analysis assumes a Poisson arrival process, exponential service times that are not known to the scheduler, and exponential laxities or deadlines, and families of upper and lower bounds on the fraction of jobs that miss their deadlines are developed. The pessimistic bounds are of special interest because they correspond to a family of implementable policies, ML(n) and ED(n), n a positive integer 1, for which the performance approaches that of ML and ED as n increases, but at the cost of increasing overhead.>

This paper presents new techniques for recog:nition of similarity between shapes under affine transformation. We introduce the canonical form of a shape and give a linear algorithm for transforming a shape to its canonical form. The recognition of similarity between shapes under affine transforination can he done by computing the difference between their canonical forms. Our approach reduces the similarity recognition1 under affine transformation from a search problem in six dimensional space into one dimensional search problem. Furtherm'ore, we apply these techniques to recognition of objects under similarity transformation and problem of point matching. We obtain a linear algorithm for object recognition under similarily transformation and a linear average time algorithm for point matching under affine transformation. Some experimental results are reported.

An approach to planar point pattern matching is presented in which the point sets are first transformed to the canonical forms, under affine transformation, and then two canonical forms are compared directly. A method for transforming a set of n points to a canonical form in O(n) time and an average O(n) time algorithm for finding a matching between canonical forms of two point sets are proposed.>

This paper will focus on the issue of load balancing on a hypercube network of N processors. We will investigate a typical nearest neighbor balancing strategy - in which workloads among neighboring processors are averaged at discrete time steps. The computation model allows tasks, described by independent random variables, to be generated and terminated at all times.