E1AR0002@SMUVM1.BITNET (02/27/86)
:aim 698 :title {Robot Programming} :author Tomas Lozano-Perez :asort Lozano-Perez, T. :date December 1982 :cost $2.75 :pages 57 :ADnum (AD-A127233) :keywords robotics, robot programming :abstract The industrial robot's principal advantage over traditional automation is programmability. Robots can perform arbitrary sequences of pre-stored motions or of motions computed as functions of sensory input. This paper reviews requirements for and developments in robot programming systems. The key requirements for robot programming systems examined in the paper are in the areas of sensing, world modeling, motion specification, flow of control, and programming support. Existing and proposed robot programming systems fall into three broad categories: guiding systems in which the user leads a robot through the motions to be performed, robot-level programming systems in which the user writes a computer program specifying motion and sensing, and task-level programming systems in which the user specifies operations by their desired effect objects. A representative sample of systems in each of these categories is surveyed in the paper. :end :aim 699 :title {The Measurement of Visual Motion} :author Ellen C. Hildreth and Shimon Ullman :asort Hildreth, E.; Ullman, S. :date December 1982 :cost $2.25 :pages 26 :ADnum (AD-A128398) :keywords motion measurement, velocity field, optical flow, zero crossings, motion perception :abstract The analysis of visual motion divides naturally into two stages: the first is the measurement of motion, for example, the assignment of direction and magnitude of velocity to elements in the image, on the basis of the changing intensity pattern; the second is the use of motion measurements, for example, to separate the scene into distinct objects, and infer their three-dimensional structure. In this paper, we present a computational study of the measurement of motion. Similar to other visual processes, the motion of elements is not determined uniquely by information in the changing image; additional constraint is required to compute a unique velocity field. Given this global ambiguity of motion, local measurements from the changing image, such as those provided by directionally-selective simple cells in primate visual cortex, cannot possible specify a unique local velocity vector, and in fact, specify only one component of velocity. Computation of the full two-dimensional velocity field requires the integration of local motion measurements, either over an area, or along contours in the image. We will examine possible algorithms for computing motion, based on a range of additional constraints. Finally, we will present implications for the biological computation of motion. :end :aim 700 :title {Dynamic Scaling of Manipulator Trajectories} :author John M. Hollerbach :asort Hollerbach, J.M. :date January 1983 :cost $1.50 :pages 13 :ADnum (AD-A127074) :keywords manipulators, robotics, trajectory planning, manipulator dynamics :abstract A fundamental time-scaling property of manipulator dynamics has been identified that allows modification of movement speed without complete dynamics recalculation. By exploiting this property, it can be determined whether a planned trajectory is dynamically realizable given actuator torque limits, and if not, how to modify the trajectory to bring it within dynamic and actuating constraints. :end :aim 701 :title {Computational Introspection} :author John Batali :asort Batali, J. :date February 1983 :cost $3.00 :pages 68 :ADnum (AD-A127132) :keywords problem solving, reflection, action, philosophy of mind, introspection, LISP, representation :abstract Introspection is the process of thinking about one's own thoughts and feelings. In this paper, I discuss recent attempts to make computational systems that exhibit introspective behavior: [Smith, 1982], [Weyhrauch, 1978], and [Doyle, 1980]. Each presents a system capable of manipulating representations of its own program and current context. I argue that introspective ability is crucial for intelligent systems -- without it an agent cannot represent certain problems that it must be able to solve. A theory of intelligent action would describe how and why certain actions intelligently achieve an agent's goals. The agent would both embody and represent this theory: it would be implemented as the program for the agent; and the importance of introspection suggests that the agent represent its theory of action to itself. :end :aim 702 :title {Representations for Reasoning About Change} :author Reid G. Simmons and Randall Davis :asort Simmons, R.G.; Davis, R. :date April 1983 :cost $2.75 :pages 54 :reference See SIGART Proc., April 1983, Workshop on Motion, Toronto, Canada, :ADnum (AD-A131649) :keywords processes, action, knowledge representation, expert systems, qualitative reasoning :abstract This paper explores representations used to reason about objects which change over time and the processes which cause changes. Specifically, we are interested in solving a problem known as geologic interpretation. To help solve this problem, we have developed a simulation technique, which we call {\it imagining}. Imagining takes a sequence of events and simulates them by drawing diagrams In order to do this imagining, we have developed two representations of objects, one involving {\it histories} and the other involving {\it diagrams} and two corresponding representations of physical processes, each suited to reasoning about one of the object representations. These representations facilitate both spatial and temporal reasoning. :end :aim 705 :title {Tactile Recognition and Localization Using Object Models: The Case of Po lyhedra on a Plane} :author Peter C. Gaston and Tomas Lozano-Perez :asort Gaston, P.; Lozano-Perez, T. :date March 1983 :cost $2.25 :pages 22 :ADnum (AD-A127228) :keywords tactile sensing, robotics :abstract This paper discusses how data from multiple tactile sensors may be used to identify and locate one object, from among a set of known objects. We use only local information from sensors:(1)the position of contact points, and (2)ranges of surface normals at the contact points. The recognition and localization process is structured as the development and pruning of a tree of consistent hypotheses about pairings between contact points and object surfaces. In this paper, we deal with polyhedral objects constrained to lie on a known plane, i.e., having three degrees of positioning freedom relative to the sensors. :end :aim 706 :title {Computational Studies in the Interpretation of Structure and Motion: Sum mary and Extension} :author Shimon Ullman :asort Ullman, S. :date March 1983 :cost $2.25 :pages 26 :ADnum (AD-A131598) :keywords motion perception, visual motion, optical flow, structure from motion :abstract Computational studies of the interpretation of structure from motion examine the conditions under which three-dimensional structure can be recovered from motion in the image. The first part of this paper summarizes the main results obtained to date in these studies. The second part examines two issues: the robustness of the 3-D interpretation of perspective velocity fields, and the 3-D information contained in orthographic velocity fields. The two are related because, under local analysis, limitations on the interpretation of orthographic velocity fields also apply to perspective projection. The following results are established: (1) When the interpretation is applied locally, the 3-D interpretation of the perspective velocity field is unstable. (2) The orthographic velocity field determines the structure of the inducing object exactly up to a depth-scaling. (3) For planar objects, the orthographic velocity field always admits two distinct solutions up to depth-scaling. (4) The 3-D Structure is determined uniquely by a "view and a half" of the orthographic velocity field. :end :aim 708 :title Solving Uninterpreted Equations with Context Free Expression Grammars :author David McAllester :asort McAllester, D.A. :date May 1983 :cost $2.25 :pages 31 :ADnum AD-A133613 :keywords theorem proving, congruence closure, simplification, automated deduction, context free grammar :abstract It is shown here that the equivalence class of an expression under the congruence closure of any finite set of equations between ground terms is a context free expression language. An expression is either a symbol or an n-tuple of expressions; the difference between expressions and strings is that expressions have inherent phrase structure. The Downey, Sethi, and Tarjan algorithm for computing congruence closures can be used to convert a finite set of equations $\Sigma$ to a context free expression grammar $G$ such that for any expression $u$ the equivalence class of $u$ under $\Sigma$ is precisely the language generated by an expression form $\Gamma(u)$ under the grammar $G$. The fact that context free {\it expression} languages are closed under intersection is used to derive an algorithm for computing a grammar for the equivalence class of a given expression under any finite disjunction of finite sets of equations between ground expressions. This algorithm can also be used to derive a grammar representing the equivalence class of conditional expressions of the form {\bf if} P {\bf then} $u$ {\bf else} $v$. The description of an equivalence class by a context free expression grammar can also be used to simplify expressions under "well behaved" simplicity orders. Specifically if $G$ is a context free expression grammar which generates an equivalence class of expressions then for any well behaved simplicity order there is a subset $G^\prime$ of the productions of $G$ such that the expressions generated by $G$ are exactly those expressions of the equivalence class which are simplicity bounds and whose subterms are also simplicity bounds. Furthermore $G^\prime$ can be computed from $G$ in order $n\log(n)$ comparisons between expressions where $n$ is the size of $G$. :end :aim 710 :title {Symmetric Set Theory: A General Theory of Isomorphism, Abstraction, and Representation} :author David Allen McAllester :asort McAllester, D.A. :date August 1983 :cost $2.25 :pages 30 :ADnum AD-A133630 :abstract It is possible to represent a finite set of points (atoms) by a finite sequence of points. However a finite set of points has no distinguished member and therefore it is impossible to define a function which takes a finite set of points and returns a "first" point in that set. Thus it is impossible to represent a finite sequence of points by a finite set of points. The theory of symmetric sets provides a framework in which this observation about sets and sequences can be proven. The theory of symmetric sets is similar to classical (Zermello-Fraenkel) set theory with the exception that the universe of symmetric sets includes points (ur-elements). Points provide a basis for general notions of isomorphism and symmetry. The general notions of isomorphism and symmetry in turn provide a basis for natural, simple, and universal definitions of abstractness, essential properties and functions, canonicality, and representations. It is expected that these notions will play an important role in the theory of data structures and in the construction of general techniques for reasoning about data structures. :end :aim 711 :title {An Extremum Principle for Shape from Contour} :author Michael Brady and Alan Yuille :asort Brady, M.; Yuille, A.L. :date June 1983 :cost $2.25 :pages 35 :ADnum (AD-A131321) :keywords shape from contour, image understanding, 3-D vision :abstract An extremum principle is developed that determines three-dimensional surface orientation from a two-dimensional contour. The principle maximizes the ratio of the area to the square of the perimeter, a measure of the compactness or symmetry of the three-dimensional surface. The principle interprets regular figures correctly and it interprets skew symmetries as oriented real symmetries. The maximum likelihood method approximates the principle on irregular figures, but we show that it consistently overestimates the slant of an ellipse. :end :aim 712 :title {Information Processing in Dendritic Spines} :author C. Koch and T. Poggio :asort Koch, C.; Poggio, T. :date March 1983 :cost $1.50 :pages 11 :keywords spines, memory, connectivity, neural hardware :abstract Dendritic spines are small twigs on the dendrites of very large class of neurons in the central nervous system. There are between 10/3 and 10/5 spines per neuron, each one including at least one synapse, i.e a connection with other neurons. Thus, spines are usually associated with an important feature of neurons - their high degree of connectivity - one of the most obvious differences between present computers and brains. We have analysed the electrical properties of a cortical (spiny) pyramidal cell on the basis of passive cable theory, from measurements made on histological material, using the solution of the cable equation for an arbitrary branched dendritic tree. As postulated by Rall, we found that the somatic potential induced by a firing synapse on a spine is a very sensitive function of the dimension of the spine. This observation leads to several hypotheses concerning the electrical functions of spines, especially with respect to their role in memory. :end :aim 713 :title {A Theoretical Analysis of Electrical Properties of Spines} :author C. Koch and T. Poggio :asort Koch, C.; Poggio, T. :date April 1983 :cost $2.25 :pages 27 :keywords dendritic spines, nerve cells, information processing, memory :abstract The electrical properties of a cortical (spiny) pyramidal cell were analyzed on the basis of passive cable theory from measurements made on histological material (Koch, Poggio and Torre 1982). The basis of this analysis is the solution of the cable equation for an arbitrary branched dendritic tree. We determined the potential at the soma as a function of the spine neck dimensions. From our investigation four major points emerge: 1. Spines may effectively compress the effect of each single excitatory synapse on the soma, mapping a wide range of inputs onto a limited range of outputs (nonlinear saturation). This is also true for very fast transient inputs, in sharp contrast with the case of a synapse on a dendrite. 2. The somatic depolarization due to an excitatory synapse on a spine is a very sensitive function of the spine neck length and diameter. Thus the spine can effectively control the attenuation of its input via the dimensions of the neck, thereby setting the shape of the resulting saturation curve. This might be the basic mechanism underlying ultra-short memory, long-term potentiation in the hippocampus or learning in the cerebellum. 3. Spines with shunting inhibitory synapses on them are ineffective in reducing the somatic depolarization due to excitatory inputs on the dendritic shaft or on other spines. Thus isolated inhibitory synapses on a spine are not expected to occur. 4. The conjunction of an excitatory synapse with a shunting inhibitory synapse on the same spine may result in a time-discrimination circuit with a temporal resolution of around 100. :end :aim 714 :title {Determining Attitude of Object From Needle Map Using Extended Gaussian I mage} :author Katsushi Ikeuchi :asort Ikeuchi, K. :date April 1983 :cost $2.25 :pages 26 :ADnum (AD-A131617) :keywords computer vision, object attitude, bin picking, Gauss map, least inertia axis, tessellated dome, look-up table :abstract An extended Gaussian image (EGI) is constructed by mapping the surface normals of an object onto the Gaussian sphere. The attitude of an object is greatly constrained by the global distribution of EGI mass over the visible Gaussian hemisphere. Constraints on viewer direction are derived from the position of the EGI mass center, and from the direction of the EGI inertia axis. The algorithm embodying these constraints and the EGI mass distribution are implemented using a lookup table. A function for matching an observed EGI with the prototypical EGIS is also proposed. The algorithm determines the attitude of an object successfully both from a synthesized needle map and a real needle map. :end :aim 716 :title {Understanding Text through Summarization and Analogy} :author Graziella Tonfoni and Richard J. Doyle :asort Tonfoni, G.; Doyle, R.J. :date April 1983 :cost $2.25 :pages 37 :keywords plot units, analogy, summary, text-production :abstract Understanding a text exactly in the way that the Text Producer meant the text to be understood is highly unlikely unless the text interpretation process is constrained. Specific understanding-directing criteria are given in the form of a Premise which is a configuration of plot-units. After performing a Premise-directed text summarization, the Text Receiver will have understood the text as the Text Producer intended and will then be able to replace missing relations within the exercises and produce new texts by applying analogy. :end :aim 717 :title {Wrist-Partitioned Inverse Kinematic Acceleration and Manipulator Dynamic s} :author John M. Hollerbach and Gideon Sahar :asort Hollerbach, J.M.; Sahar, G. :date April 1983 :cost $2.25 :pages 25 :keywords robotics, kinematics, dynamics, control :abstract An efficient algorithm is presented for the calculation of the inverse kinematic accelerations for a 6 degree-of-freedom manipulator with a spherical wrist. The inverse kinematic calculation is shown to work synergistically with the inverse dynamic calculation, producing kinematic parameters needed in the recursive Newton-Euler dynamics formulation. Additional savings in the dynamics computation are noted for a class of kinematically well-structured manipulators such as spherical-wrist arms and for manipulators with simply-structured inertial parameters. :end :aim 718 :author A. Yuille :asort Yuille, A.L. :title Zero-Crossings on Lines of Curvature :date December 1984 :cost $2.25 :pages 23 :Adnum AD-A150171 :keywords photometric invariants, zero crossings, lines of curvature, parabolic lines :abstract We investigate the relations between the structure of the image and events in the geometry of the underlying surface. We introduce some elementary differential geometry and use it to define a coordinate system on the object based on the lines of curvature. Using this coordinate system we can prove results connecting the extrema, ridges and zero-crossings in the image to geometrical features of the object. We show that extrema of the image typically correspond to points on the surface with zero Gaussian curvature and that parabolic lines often give rise to ridges, or valleys, in the image intensity. We show that directional zero-crossings of the image along the lines of curvature generally correspond to extrema of curvature along such lines. :aim 719 :title {Semantic Support for Work in Organizations} :author Gerald Barber, Peter de Jong, and Carl Hewitt :asort Barber, G.; de Jong, P.; Hewitt, C. :date April 1983 :cost $1.50 :pages 14 :ADnum (AD-A130457) :keywords problem solving, office systems, open systems, actors, application systems, message passing semantics, OMEGA, sprites :abstract Present day computer systems cannot implement much of the work carried out in organizations such as: planning, decision making, analysis, and dealing with unanticipated situations. Such organizational activities have traditionally been considered too unstructured to be suitable for automation by computer. We are working on the development of a computer system which is capable of the following: describing the semantics of applications as well as the structure of the organization carrying out the work, aiding workers in carrying out the applications using these descriptions, and acquiring these capabilities in the course of the daily work through a process which is analogous to apprenticeship. :end :aim 721 :title {Maximizing Rigidity: The Incremental Recovery of 3-D Structure From Rigi d and Rubbery Motion} :author Shimon Ullman :asort Ullman, S. :date June 1983 :keywords motion perception, structure from motion, rigidity, rubbery motion, kinetic depth effect :cost $2.25 :pages 30 :abstract The human visual system can extract 3-D shape information of unfamiliar moving objects from their projected transformations. Computational studies of this capacity have established that 3-D shape can be extracted correctly from a brief presentation, provided that the moving objects are rigid. The human visual system requires a longer temporal extension, but it can cope, however, with considerable deviations from rigidity. It is shown how the 3-D structure of rigid and non-rigid objects can be recovered by maintaining an internal model of the viewed object and modifying it at each instant by the minimal non-rigid change that is sufficient to account for the observed transformation. The results of applying this incremental rigidity scheme to rigid and non-rigid objects in motion are described and compared with human perceptions. :end :aim 722 :title {Scaling Theorems for Zero-Crossings} :author A.L. Yuille and T. Poggio :asort Yuille, A.L.; Poggio, T. :date June 1983 :cost $2.25 :pages 25 :ADnum (AD-A131599) :abstract We characterize some properties of the zero-crossings of the laplacian of signals - in particular images - filtered with linear filters, as a function of the scale of the filter (following recent work by A. Witkin, 1983). We prove that in any dimension the only filter that does not create zero-crossings as the scale increases is the gaussian. This result can be generalized to apply to level-crossings of any linear differential operator: it applies in particular to ridges and ravines in the image intensity. In the case of the second derivative along the gradient we prove that there is no filter that avoids creation of zero-crossings. :end :aim 723 :title {Visual Routines} :author Shimon Ullman :asort Ullman, S. :date June 1983 :cost $2.75 :pages 66 :ADnum AD-A133634 :keywords vision, visual routines, pattern recognition, space perception, spatial information processing :abstract This paper examines the processing of visual information beyond the creation of the early representations. A fundamental requirement at this level is the capacity to establish visually abstract shape properties and spatial relations. This capacity plays a major role in object recognition, visually guided manipulation, and more abstract visual thinking. For the human visual system, the perception of spatial properties and relations that are complex from a computational standpoint, nevertheless often appears immediate and effortless. This apparent immediateness and ease of perceiving spatial relations is, however deceiving. It conceals in fact a complex array of processes highly specialized for the task. The proficiency of the human system in analyzing spatial information far surpasses the capacities of current artificial systems. The study of the computations that underlie this competence may therefore lead to the development of new more efficient processors for the spatial analysis of visual information. It is suggested that the perception of spatial relations is achieved by the application to the base representations of visual routines that are composed of sequences of elemental operations. Routines for different properties and relations share elemental operations. Using a fixed set of basic operations, the visual system can assemble different routines to extract an unbounded variety of shape properties and spatial relations. At a more detailed level, a number of pausible basic operations are suggested, based primarily on their potential usefulness, and supported in part by empirical evidence. The operations discussed include shifting of the processing focus, indexing to an odd-man-out location, bounded activation, boundary tracing, and marking. The problem of assembling such elemental operations into meaningful visual routines is discussed briefly. :end :aim 724 :title {The Smoothest Velocity Field and Token Matching} :author A.L. Yuille :asort Yuille, A.L. :date August 1983 :cost $1.50 :pages 10 :ADnum AD-A133633 :keywords motion measurement, velocity field, optical flow, zero crossings, motion perception :abstract This paper presents some mathematical results concerning the measurement of motion of contours. A fundamental problem of motion measurement in general is that the velocity field is not determined uniquely from the changing intensity patterns. Recently Hildreth \& Ullman have studied a solution to this problem based on an Extremum Principle [Hildreth (1983), Ullman \& Hildreth (1983)]. That is, they formulate the measurement of motion as the computation of the smoothest velocity field consistent with the changing contour. We analyze this Extremum Principle and prove that it is closely related to a matching scheme for motion measurement which matches points on the moving contour that have similar tangent vectors. We then derive necessary and sufficient conditions for the principle to yield the correct velocity field. These results have possible implications for the design of computer vision systems, and for the study of human vision. :end :aim 725 :title {Planning Collision Free Motions for Pick and Place Operations} :author Rodney A. Brooks :asort Brooks, R.A. :date May 1983 :cost $2.75 :pages 49 :ADnum (AD-A130448) :keywords find-path, collision free paths, pick and place, collision avoidance :abstract An efficient algorithm which finds collision free paths for a manipulator with 5 or 6 revolute joints is described. It solves the problem for four degree of freedom pick and place operations Examples are given of paths found by the algorithm in tightly cluttered workspaces. The algorithm first describes free space in two ways: as freeways for the hand and payload ensemble and as freeways for the upperarm. Freeways match volumes swept out by manipulator motions and can be "inverted" to find a class of topologically equivalent path segments. The two freeway spaces are searched concurrently under vprojection of constraints determined by motion of the forearm. :end :aim 726 :title {Picking up an Object from a Pile of Objects} :author Katsushi Ikeuchi, Berthold K.P. Horn, Shigemi Nagata, Tom Callahan, and Oded Feingold :asort Ikeuchi, K.; Horn, B.K.P.; Nagata, S.; Callahan, T.; Feingold, O. :date May 1983 :cost $2.25 :pages 27 :ADnum AD-A133631 :keywords photometric stereo, Puma arm, hand-eye system, extended Gaussian image, bin picking, visual guidance :abstract This paper describes a hand-eye system we developed to perform the bin-picking task. Two basic tools are employed: the photometric stereo method and the extended Gaussian image. The photometric stereo method generates the surface normal distribution of a scene. The extended Gaussian image allows us to determine the attitude of the object based on the normal distribution. Visual analysis of an image consists of two stages. The first stage segments the image into regions and determines the target region. The photometric stereo system provides the surface normal distribution of the scene. The system segments the scene into isolated regions using the surface normal distribution rather than the brightness distribution. The second stage determines the object attitude and position by comparing the surface normal distribution with the extended Gaussian image. Fingers, with LED sensor, mounted on the Puma arm can successfully pick an object from a pile based on the information from the vision part. :end :aim 727 :title {Analyzing the Roles of Descriptions and Actions in Open Systems} :author Carl Hewitt and Peter de Jong :asort Hewitt, C.; de Jong, P. :date April 1983 :cost $1.50 :pages 15 :ADnum AD-A133614 :keywords open systems, concurrent system, message passing semantics, distributed systems, lambda calculus, first order logic, actor theory, description and action :abstract This paper analyzes relationships between the roles of descriptions and actions in large scale, open ended, geographically distributed, concurrent systems. Rather than attempt to deal with the complexities and ambiguities of currently implemented descriptive languages, we concentrate our analysis on what can be expressed in the underlying frameworks such as the lambda calculus and first order logic. By this means we conclude that descriptions and actions complement one another; neither being sufficient unto itself. This paper provides a basis to begin the analysis of the very subtle relationships that hold between descriptions and actions in Open Systems. :end :aim 730 :title Fingerprints Theorems for Zero-Crossings :author A.L. Yuille and T. Poggio :asort Yuille, A.L.; Poggio, T. :date October 1983 :cost $2.25 :pages 28 :adnum AD-A139181 :keywords zero crossings, scales, signal reconstruction :abstract We prove that the scale map of the zero-crossings of almost all signals filtered by the second derivative of a gaussian of variable size determines the signal uniquely, up to a constant scaling and a harmonic function. Our proof provides a method for reconstructing almost all signals from knowledge of how the zero-crossing contours of the signal, filtered by a gaussian filter, change with the size of the filter. The proof assumes that the filtered signal can be represented as a polynomial of finite, albeit possibly very high, order. An argument suggests that this restriction is not essential. Stability of the reconstruction scheme is briefly discussed. The result applies to zero- and level-crossings of linear differential operators of gaussian filters. The theorem is extended to two dimensions, that is to images. These results are reminiscent of Logan's theorem. They imply that extrema of derivatives at different scales are a complete representation of a signal. :end :aim 731 :title Structure From Stereo and Motion :author Whitman Richards :asort Richards, W.A. :date September 1983 :cost $1.50 :pages 19 :abstract Stereopsis and motion parallax are two methods for recovering three dimensional shape. Theoretical analyses of each method show that neither alone can recover rigid 3D shapes correctly unless other information, such as perspective, is included. The solutions for recovering rigid structure from motion have a reflection ambiguity; the depth scale of the stereoscopic solution will not be known unless the fixation distance is specified in units of interpupil separation. (Hence the configuation will appear distorted.) However, the correct configuration and disposition of a rigid 3D shape can be recovered if stereopsis and motion are integrated, for then a unique solution follows from a set of linear equations. The correct interpretation requires only three points and two stereo views. :end :aim 732 :title Parts of Recognition :author D.D. Hoffman and Whitman Richards :asort Hoffman, D.D.; Richards, W.A. :date December 1983 :cost $2.25 :pages 35 :abstract A complete theory of object recognition is an impossibility -- not simply because of the multiplicity of visual cues we exploit in elegant coordination to identify an object, but primarily because recognition involves fixation of belief, and anything one knows may be relevant. We finesse this obstacle with two moves. The first restricts attention to one visual cue, the shapes of objects; the second restricts attention to one problem, the initial guess at the identity of an object. We propose that the visual system decomposes a shape into parts, that it does so using a rule defining part boundaries rather than part shapes, that the rule exploits a uniformity of nature -- transversality, and that parts with their descriptions and spatial relations provide a first index into a memory of shapes. These rules lead to a more comprehensive explanation of several visual illusions. The role of inductive inference is stressed in our theory. We conclude with a precis of unsolved problems. :aim 734 :title {The Computation of the Velocity Field} :author Ellen C. Hildreth :asort Hildreth, E. :date September 1983 :cost $2.25 :pages 40 :keywords motion analysis, motion perception, computer vision, image processing, velocity field :abstract The organization of movement in the changing retinal image provides a valuable source of information for analyzing the environment in terms of objects, their motion in space, and their three-dimensional structure. A description of this movement is not provided to our visual system directly, however; it must be inferred from the pattern of changing intensity that reaches the eye. This paper examines the problem of motion measurement, which we formulate as the computation of an instantaneous two-dimensional velocity field from the changing image. Initial measurements of motion take place at the location of significant intensity changes as suggested by Marr and Ullman (1981). These measurements provide only one component of local velocity, and must be integrated to compute the two-dimensional velocity field. A fundamental problem for this integration stage is that the velocity field is not determined uniquely from information available in the changing image. We formulate an additional constraint of smoothness of the velocity field, based on the physical assumption that surfaces are generally smooth, which allows the computation of a unique velocity field. A theoretical analysis of the conditions under which this computation yields the correct velocity field suggests that the solution is physically plausible. Empirical studies show the predictions of this computation to be consistent with human motion perception. :end :aim 736 :title Hypothesizing Channels Through Free-Space In Solving the Findpath Problem :author Bruce R. Donald :asort Donald, B.R. :date June 1983 :cost $2.75 :pages 58 :ADnum AD-A133632 :keywords geometric modelling, robotics, obstacle avoidance, spatial reasoning, computational geometry :abstract Given a polyhedral environment, a technique is presented for hypothesizing a channel volume through the free space containing a class of successful collision-free paths. A set of geometric constructions between obstacle faces is proposed, and we define a mapping from a field of view analysis to a direct local construction of free space. The algorithm has the control structure of a search which propagates construction of a connected channel towards a goal along a frontier of exterior free faces. Thus a channel volume starts out by surrounding the moving object in the initial configuration and "grows" towards the goal. Finally, we show techniques for analyzing the channel decomposition of free space and suggesting a path. :end :aim 737 :title Hidden Clues in Random Line Stereograms :author H.K. Nishihara and T. Poggio :asort Nishihara, H.K.; Poggio, T. :date August 1983 :cost $1.50 :pages 9 :keywords random line stereograms, stereo matching, vision, vernier acuity, frequency tuned channels, parallel processing, computer vision, psychophysics :abstract Successful fusion of random-line stereograms with breaks in the vernier acuity range has been previously interpreted to suggest that the interpolation process underlying hyperacuity is parallel and preliminary to stereomatching. In this paper (a) we demonstrate with computer experiments that vernier cues are not needed to solve the stereomatching problem posed by these stereograms and (b) we provide psychophysical evidence that human stereopsis probably does not use vernier cues alone to achieve fusion of these random-line stereograms. :end :aim 738 :title {Model-Based Recognition and Localization From Sparse Range or Tactile Da ta} :author W. Eric Grimson and Tomas Lozano-Perez :asort Grimson, W.E.L.; Lozano-Perez, T. :date August 1983 :cost $2.75 :pages 54 :keywords tactile recognition, robotics, range data :adnum AD-A135791 :abstract This paper discusses how local measurements of three-dimensional positions and surface normals (recorded by a set of tactile sensors, or by three-dimensional range sensors), may be used to identify and locate objects, from among a set of known objects. The objects are modeled as polyhedra having up to six degrees of freedom relative to the sensors. We show that inconsistent hypotheses about pairings between sensed points and object surfaces can be discarded efficiently by using local constraints on: distances between faces, angles between face normals, and angles (relative to the surface normals) of vectors between sensed points. We show by simulation and by mathematical bounds that the number of hypotheses consistent with these constraints is small. We also show how to recover the position and orientation of the object from the sense data. The algorithm's performance on data obtained from a triangulation range sensor is illustrated. :end :aim 739 :title Diagnostic Reasoning Based On Structure and Behavior :author Randall Davis :asort Davis, R. :date June 1984 ;pages 54 :cost $2.75 :abstract We describe a system that reasons from first principles, i.e., using knowledge of structure and behavior. The system has been implemented and tested on several examples in the domain of troubleshooting digital electronic circuits. We give an example of the system in operation, illustrating that this approach provides several advantages, including a significant degree of device independence, the ability to constrain the hypotheses it considers at the outset, yet deal with a progressively wider range of problems, and the ability to deal with situations that are novel in the sense that their outward manifestations may not have been encountered previously. As background we review our basic approach to describing structure and behavior, then explore some of the technologies used previously in troubleshooting. Difficulties encountered there lead us to a number of new contributions, four of which make up the central focus of this paper. We describe a technique we call {\it constraint suspension} that provides a powerful tool for troubleshooting. We point out the importance of making explicit the assumptions underlying reasoning and describe a technique that helps enumerate assumptions methodically. The result is an overall strategy for troubleshooting based on the progressive relaxation of underlying assumptions. The system can focus its efforts initially, yet will methodically expand its focus to include a broad range of faults. Finally, abstracting from our examples, we find the concept of {\it adjacency} proves to be useful in understanding why some faults are especially difficult and why multiple different representations are useful. :aim 740 :title {Extended Gaussian Images} :author Berthold K.P. Horn :asort Horn, B.K.P. :date July 1983 :cost $2.75 :adnum AD-A135747 :keywords machine vision, attitude in space, shape representation, object recognition, Gaussian image :abstract This is a primer on extended gaussian images. Extended gaussian images are useful for representing the shapes of surfaces. They can be computed easily from: (1) needle maps obtained using photometric stereo, or (2) depth maps generated by ranging devices or stereo. importantly, they can also be determined from geometric models of the objects. Extended gaussian images can be of use in at least two of the tasks facing a machine vision system: (1) recognition, and (2) determining the attitude in space of an object. Here, the extended gaussian image is defined and some of its properties discussed. An elaboration for non-convex objects is presented and several examples are shown. :end :aim 743 :title {Vertical Image Registration in Stereopsis} :author K.R.K. Nielsen and T. Poggio :asort Nielsen, K.; Poggio, T. :date October 1983 :cost $1.50 :pages 13 :keywords stereopsis, image registration, vertical disparity :abstract Most computational theories of stereopsis require a registration stage prior to matching to reduce the matching to a one-dimensional search. Even after registration, it is critical that the stereo matching process tolerate some degree of residual misalignment. In this paper, we study with psychophysical techniques the tolerance to vertical disparity in situations in which false targets abound - as in random dot stereograms - and eye movements are eliminated. Our results show that small amounts of vertical disparity significantly impair depth discrimination in a forced-choice task. :end :aim 744 :title {Reconstructing a Depth Map from Intensity Maps} :author Katsushi Ikeuchi :asort Ikeuchi, K. :date August 1983 :cost $1.50 :pages 19 :adnum AD-A135679 :keywords shape from shading, Marr-Poggio-Grimson stereo, needle map, photometric stereo, depth map, intensity map :abstract This paper describes two methods for constructing a depth map from images. Each method has two stages. First, one or more needle maps are determined using a pair images. This process employs either the Marr-Poggio-Grimson stereo and shape-from-shading, or, instead, photometric stereo. Secondly, a depth map is constructed from the needle map or needle maps computed by the first stage. Both methods make use of an iterative relaxation method to obtain the final depth map. :end :aim 746 :title Picking Parts out of a Bin :author Berthold K.P. Horn and Katsushi Ikeuchi :asort Horn, B.K.P.; Ikeuchi, K. :date October 1983 :cost $2.75 :pages 48 :adnum AD-A139257 :keywords machine vision, bin picking, shape representation, object recognition, hand-eye system, attitude in space, extended Gaussian image :abstract One of the remaining obstacles to the widespread application of industrial robots is their inability to deal with parts that are not precisely positioned. In the case of manual assembly, components are often presented in bins. Current automated systems, on the other hand, require separate feeders which present the parts with carefully controlled position and attitude. Here we show how results in machine vision provide techniques for automatically directing a mechanical manipulator to pick one object at a time out of a pile. The attitude of the object to be picked up is determined using a histogram of the orientations of visible surface patches. Surface orientation, in turn, is determined using photometric stereo applied to multiple images. These images are taken with the same camera but differing lighting. The resulting needle map, giving the orientations of surface patches, is used to create an orientation histogram which is a discrete approximation to the extended Gaussian image. This can be matched against a synthetic orientation histogram obtained from prototypical models of the objects to be manipulated. Such models may be obtained from computer aided design (CAD) databases. The method thus requires that the shape of the objects be described, but it is not restricted to particular types of objects. :aim 747 :unavailable :title A Structural Approach to Analogy :author Hormoz Mansour :asort Mansour, H. :date November 1983 :pages 28 :keywords structural analogy, contextual analogy, knowledge acquisition, nested frames, automatic acquisition :aim 750 :title {Design Issues in Parallel Architecture for Artificial Intelligence} :author Carl Hewitt and Henry Lieberman :asort Hewitt, C.; Lieberman, H. :date November 1983 :cost $1.50 :pages 15 :adnum AD-A142482 :keywords architecture, parallelism, actors, Act2, artificial intelligence, Apiary, message passing, reasoning :abstract Development of highly intelligent computers requires a conceptual foundation that will overcome the limitations of the von Neumann architecture. Architectures for such a foundation should meet the following design goals: *) Address the fundamental organizational issues of large-scale parallelism and sharing in a fully integrated way. This means attention to organizational principles, as well as hardware and software. *) Serve as an experimental apparatus for testing large-scale artificial intelligence systems. *) Explore the feasibility of an architecture based on abstractions, which serve as natural computational primitives for parallel processing. Such abstractions should be logically independent of their software and hardware host implementations. In this paper we lay out some of the fundamental design issues in parallel architectures for Artificial Intelligence, delineate limitations of previous parallel architectures, and outline a new approach that we are pursuing. :aim 751 :title Analog "Neuronal" Networks in Early Vision :author Christof Koch, Jose Marroquin, and Alan Yuille :asort Koch, C.; Marroquin, J.L.; Yuille, A.L. :date June 1985 :pages 17 :cost $1.50 :keywords analogy networks, analog-digital hardware, parallel computers, surface interpolation, surface reconstruction, optimization problem, regularization theory, early vision :abstract Many problems in early vision can be formulated in terms of minimizing an energy or cost function. Examples are shape-from-shading, edge detection, motion analysis, structure from motion and surface inter- polation (Poggio, Torre and Koch, 1985). It has been shown that all quadratic variational problems, an important subset of early vision tasks, can be "solved" by linear, analog electrical or chemical networks (Poggio and Koch, 1985). In a variety of situations the cost function is non-quadratic, however, for instance in the presence of discontinuities. The use of non- quadratic cost functions raises the question of designing efficient algorithms for computing the optimal solution. Recently, Hopfield and Tank (1985) have shown that networks of nonlinear analog "neurons" can be effective in computing the solution of optimization problems. In this paper, we show how these networks can be generalized to solve the non-convex energy functionals of early vision. We illustrate this approach by implementing a specific network solving the problem of reconstructing a smooth surface while preserving its discontinuities from sparsely sampled data (Geman and Geman, 1984; Terzopoulos, 1984). These results suggest a novel computational strategy for solving such problems for both biological and artificial vision systems. -------