Showing papers by "Avinash C. Kak published in 1988"

Structural stereopsis for 3-D vision

Abstract: A novel approach to solving the stereo correspondence problem in computer vision is described. Structural descriptions of two two-dimensional views of a scene are extracted by one of possibly several available low-level processes, and a new theory of inexact matching for such structures is derived. An entropy-based figure of merit for attribute selection and ordering is defined. Experimental results applying these techniques to real image pairs are presented. Some manipulation experiments are briefly presented. >

Planning sensing strategies in a robot work cell with multi-sensor capabilities

Abstract: An approach is presented for planning sensing strategies dynamically on the basis of the system's current best information about the world. The approach is for the system to propose a sensing operation automatically and then to determine the maximum ambiguity which might remain in the world description if that sensing operation were applied. The system then applies that sensing operation which minimizes this ambiguity. To do this, the system formulates object hypotheses and assesses its relative belief in those hypotheses to predict what features might be observed by a proposed sensing operation. Furthermore, since the number of sensing operations available to the system can be arbitrarily large, equivalent sensing operations are grouped together using a data structure that is based on the aspect graph. In order to measure the ambiguity in a set of hypotheses, the authors apply the concept of entropy from information theory. This allows them to determine the ambiguity in a hypothesis set in terms of the number of hypotheses and the system's distribution of belief among those hypotheses. >

Knowledge-based robotics

Abstract: A major hurdle in the development of intelligent robots is that we still do not possess efficient computational and representational methodologies for emulating knowledge and expectation driven behaviour so basic to human cognition and problem solving. Even if we use techniques such as geometric modelling for representing objects in the robot world, we are still lacking in methods for linking such representations with sensory feedback. In this paper, we have proposed the use of intermediate representations—we call them sensor-tuned representations—for linking CSG based solid modelling with sensory information. We also discuss how sensor-tuned representations are constructed from range data and how object recognition can be done with sensor-tuned representations. Finally, we show results of manipulation experiments produced by the current implementation of the system.

A dynamic approach to high-precision parts mating

Abstract: The authors present seldom-discussed sources of error in force-guided motions to execute assemblies. Among these sources are noisy F/T (force/torque) readings, the presence of sliding and sticking frictions, and the possibilities of eccentric oblique impacts. They point out how most of these errors might be reduced or eliminated. The authors introduce the notion of straight line motion goals (SLMGs) and show how SLMGs can be considered as the basic building blocks of a dynamic planning strategy. The steps required to carry out peg-in-hole experiments are examined. It is shown how the torque vector can be used to compute the direction in which the peg should be compliantly moved to align the axes of the peg and the hole. The authors present an error-detection-and-recovery algorithm for these experiments and show the dependence of the success rate on the number of error-detection-and-recovery cycles allowed. >

A rule-based approach to binocular stereopsis

Abstract: Before the famous random-dot stereogram experiments by Julesz [Jul60], it was generally believed that a necessary precursor to binocular fusion was a recognition of monocular cues in each of the two images. The experiments by Julesz caused a paradigm shift of sorts in the psychophysics of the human visual system; suddenly, the preponderance of the research effort shifted toward explaining practically all aspects of human stereopsis in terms of low-level processes, as opposed to high-level cognitive phenomena. One of the high points of this post-Julesz period was the development of the Marr-Poggio paradigm [MP79]. Marr and Poggio presented a computational theory, later implemented by Grimson, that provided successful explanation of the Julesz experiments in terms of the matchings of zerocrossings at different scales, the zero-crossings at each scale corresponding to the filtering of the images with a Laplacian-of-a-Gaussian (LoG) filter [Gri81a].

Applying uncertainty reasoning to planning sensing strategies in a robot workcell with multi-sensor capabilities

Abstract: An approach to planning sensing strategies dynamically on the basis of the system's current best information about the world is described. The approach is for the system to propose a sensing operation automatically and then to determine the maximum ambiguity which might remain in the world description if that sensing operation were applied. When this maximum ambiguity is sufficiently small, the corresponding sensing operation is applied. To do this, the system formulates object hypotheses and assesses its relative belief in those hypotheses to predict what features might be observed by a proposed sensing operation. Furthermore, since the number of sensing operations available to the system can be arbitrarily large, equivalent sensing operations are grouped together using a data structure that is based on the aspect graph. In order to measure the ambiguity in a set of hypotheses, the concept of entropy from information theory is applied. This allows the determination of ambiguity in a hypothesis set in terms of the number of hypotheses and the system's distribution of belief among those hypotheses. >

Task Planner for Simultaneous Fulfillment of Operational, Geometric and Uncertainty-Reduction Goals

Abstract: Our ultimate goal in robot planning is to develop a planner which can create complete assembly plans given as input a high level description of assembly goals, geometric models of the components of the assembly, and a description of the capabilities of the work cell (including the robot and the sensory system). In this paper, we introduce SPAR, a planning system which reasons about high level operational goals, geometric goals and uncertainty-reduction goals in order to create assembly plans which consist of manipulations as well as sensory operations when appropriate. Operational planning is done using a nonlinear, constraint posting planner. Geometric planning is accomplished by constraining the execution of operations in the plan so that geometric goals are satisfied, or, if the geometric configuration of the world prevents this, by introducing new operations into the plan with the appropriate constraints. When the uncer­ tainty in the world description exceeds that specified by the uncertainty-reduction goals, SPAR introduces either sensing operations or manipulations to reduce that uncertainty to acceptable levels. I f SPAR cannot find a way to sufficiently reduce uncertainties, it does not abandon the plan. Instead, it augments the plan with sensing operations to be used to verify the execution of the action, and, when possible, posts possible error recovery plans, although at this point, the verification operations and recovery plans are predefined. This work was supported by the National Science Foundation under Grant CDR 8803017 to the Engineering Research Center for Intelligent Manufacturing Systems.

Planning and Reasoning in Sensor Based Robotics

Abstract: This paper surveys the planning and reasoning research being carried out in the Robot Vision Lab at Purdue. In parlicular, we will describe the workings of a new planning system called SPAR, which uses a constraint posting approach for simultaneously fulfilling the operational, geometric and uncertainly reduction goals, and the PSEIKI system for evidential reasoning in a rangled hierarchy. We will also mention briefly our other relared research in high precision assembly under forceltorque confrol and robotic manipulation with structural stereopsis for depth perception.