SEARCH · Search NASA
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
This report describes the second phase of a series of evaluations of a vision-based welding control sensor for the Space shuttle Main Engine Robotic Welding System. The robotic welding system is presently under development at the Marshall Space Flight Center. This evaluation determines the factors influencing the minimum joint gap required for consistent detection of the weld joint.
The first phase of a series of evaluations of a vision-based welding control sensor for the Space Shuttle Main Engine Robotic Welding System is described. The robotic welding system is presently under development at the Marshall Space Flight Center. This evaluation determines the standard control response parameters necessary for proper trajectory of the welding torch along the joint.
The orbital Maneuvering Vehicle (OMV) is intended to close with orbiting targets for relocation or servicing. It will be controlled via video signals and thruster activation based upon Earth or space station directives. A human operator is squarely in the middle of the control loop for close work. Without directly addressing future, more autonomous versions of a remote servicer, several techniques that will doubtless be important in a future increase of autonomy also have some direct application to the current situation, particularly in the area of image enhancement and predictive analysis. Several techniques are presentet, and some few have been implemented, which support a machine vision capability proposed to be adequate for detection, recognition, and tracking. Once feasibly implemented, they must then be further modified to operate together in real time. This may be achieved by two courses, the use of an array processor and some initial steps toward data reduction. The methodology or adapting to a vector architecture is discussed in preliminary form, and a highly tentative rationale for data reduction at the front end is also discussed. As a by-product, a working implementation of the most advanced graphic display technique, ray-casting, is described.
An overview of artificial intelligence (AI), its core ingredients, and its applications is presented. The knowledge representation, logic, problem solving approaches, languages, and computers pertaining to AI are examined, and the state of the art in AI is reviewed. The use of AI in expert systems, computer vision, natural language processing, speech recognition and understanding, speech synthesis, problem solving, and planning is examined. Basic AI topics, including automation, search-oriented problem solving, knowledge representation, and computational logic, are discussed.
Research on developing an operator capable of performing the various subtasks required of a telerobot's vision sensor is reported. The operator uses a goal-driven matching technique which is an application of a linear programming method that readily adapts to the elastic template matching approach to pattern recognition. Four applications of the operator are discussed: (1) three-space location of an isolated object; (2) shape determination of isolated planar figures; (3) image compression/restoration; and (4) shape decomposition.
Problems which will be encountered by computer vision systems in Space Station operations are discussed, along with solutions be examined at Johnson Space Station. Lighting cannot be controlled in space, nor can the random presence of reflective surfaces. Task-oriented capabilities are to include docking to moving objects, identification of unexpected objects during autonomous flights to different orbits, and diagnoses of damage and repair requirements for autonomous Space Station inspection robots. The approaches being examined to provide these and other capabilities are television IR sensors, advanced pattern recognition programs feeding on data from laser probes, laser radar for robot eyesight and arrays of SMART sensors for automated location and tracking of target objects. Attention is also being given to liquid crystal light valves for optical processing of images for comparisons with on-board electronic libraries of images.
The conference presents papers on segmentation techniques, three-dimensional recognition and representation, processing image sequences, and navigation and mobility. Particular attention is given to determining the pose of an object, adaptive least squares correlation with geometrical constraints, and the reliable formation of feature vectors for two-dimensional shape representation. Other topics include the real-time tracking of a target moving on a natural textured background, computer vision for the guidance of roving robots, and integrating sensory data for object recognition tasks.
For the study of human and animal vision, the video framebuffer is the only technology that is capable of displaying two-dimensional images with precise control of contrast, luminance, and display timing. The video framebuffer also allows precise control of color. However, this device is not designed for precise psychophysical displays, and techniques must be developed to use them in this role. In order to be concrete, an RDS-3000 raster display system (Adage, 1982) is used which is hosted by a PDP-11/73 under the Venix operating system. The principles generalize to other machines. Where it clarifies the issues, the syntax of the software routines involved is shown.
Orientation and brightness varied to suit welding conditions. Commands from vision-system computer drive servomotors on iris and Dove prism, providing proper light level and image orientation. Optical-fiber bundle carries view of weld area as viewed along axis of welding electrode. Image processing described in companion article, "Processing Welding Images for Robot Control" (MFS-26036).
Three dimensional perception is essential to the development of versatile robotics systems in order to handle complex manufacturing tasks in future factories and in providing high accuracy measurements needed in flexible manufacturing and quality control. A program is described which will develop the potential of Moire techniques to provide this capability in vision systems and automated measurements, and demonstrate artificial intelligence (AI) techniques to take advantage of the strengths of Moire sensing. Moire techniques provide a means of optically manipulating the complex visual data in a three dimensional scene into a form which can be easily and quickly analyzed by computers. This type of optical data manipulation provides high productivity through integrated automation, producing a high quality product while reducing computer and mechanical manipulation requirements and thereby the cost and time of production. This nondestructive evaluation is developed to be able to make full field range measurement and three dimensional scene analysis.
The thrust of automation and robotics for space applications has been proposed for increased productivity, improved reliability, increased flexibility, higher safety, and for the performance of automating time-consuming tasks, increasing productivity/performance of crew-accomplished tasks, and performing tasks beyond the capability of the crew. This paper provides a review of efforts currently in progress in the area of robotic vision. Both systems and algorithms are discussed. The evolution of future vision/sensing is projected to include the fusion of multisensors ranging from microwave to optical with multimode capability to include position, attitude, recognition, and motion parameters. The key feature of the overall system design will be small size and weight, fast signal processing, robust algorithms, and accurate parameter determination. These aspects of vision/sensing are also discussed.
A machine vision system is described which is designed to acquire and track polyhedral objects moving and rotating in space by means of two or more cameras, programmable image-processing hardware, and a general-purpose computer for high-level functions. The image-processing hardware is capable of performing a large variety of operations on images and on image-like arrays of data. Acquisition utilizes image locations and velocities of the features extracted by the image-processing hardware to determine the three-dimensional position, orientation, velocity, and angular velocity of the object. Tracking correlates edges detected in the current image with edge locations predicted from an internal model of the object and its motion, continually updating velocity information to predict where edges should appear in future frames. With some 10 frames processed per second, real-time tracking is possible.
A description is given of research that applies techniques from computer vision to automation of rotorcraft navigation. The effort emphasizes the development of a methodology for detecting the ranges to obstacles in the region of interest based on the maximum utilization of passive sensors. The range map derived from the obstacle detection approach can be used as obstacle data for the obstacle avoidance in an automataic guidance system and as advisory display to the pilot. The lack of suitable flight imagery data, however, presents a problem in the verification of concepts for obstacle detection. This problem is being addressed by the development of an adequate flight database and by preprocessing of currently available flight imagery. Some comments are made on future work and how research in this area relates to the guidance of other autonomous vehicles.
Conceptual robot-vision system processes data from both microwave and visible-wavelength sensors. Concept, called "fusion of sensors," yields better information on shapes of some objects than obtained from one type of sensor alone. Proposed system fuses data from television images with polarized low-resolution radar-scattering cross sections. Using iterative procedure, generates successive approximations to shape of target by minimizing differences between observed radar returns and radar returns observed if object characterized by computed scattering transfer matrix.
A critical limitation of most of the robots utilized in industrial environments arises due to their inability to utilize sensory feedback. This forces robot operation into totally preprogrammed or teleoperation modes. In order to endow the new generation of robots with higher levels of autonomy techniques for sensing of their work environments and for accurate and efficient analysis of the sensory data must be developed. In this paper detailed development of vision system modules for inspecting various types of meters, both analog and digital, encountered in a robotic inspection and manipulation tasks are described. These modules are tested using industrial robots having multisensory input capability.
Researchers define object apprehension as the determination of the properties of an object and the relationships among these properties. They contrast this with recognition, which goes a step further to attach a label to the object as a whole. Apprehension is fundamental to manipulation. This is true whether the manipulation is being carried out by an autonomous robot or is the result of teleoperation involving sensory feedback. Researchers present an apprehension paradigm using both vision and touch. In this model, they define a representation for object apprehension in terms of a set of primitives and features, along with their relationships. This representation is the mechanism by which the data from the two modalities are combined. It is also the mechanism which drives the apprehension process.
Desirable properties of robotics vision database systems are given, and structures which possess properties appropriate for some aspects of such database systems are examined. Included in the structures discussed is a family of networks in which link membership is determined by measures of proximity between pairs of the entities stored in the database. This type of network is shown to have properties which guarantee that the search for a matching feature vector is monotonic. That is, the database can be searched with no backtracking, if there is a feature vector in the database which matches the feature vector of the external entity which is to be identified. The construction of the database is discussed, and the search procedure is presented. A section on the support provided by the database for description of the decision-making processes and the search path is also included.
Orientation-dependent techniques for the identification of a three-dimensional object by a machine vision system are represented in parts. In the first part, the data consist of intensity images of polyhedral objects obtained by a single camera, while in the second part, the data consist of range images of curved objects obtained by a laser scanner. In both cases, the attributed graphic representation of the object surface is used to drive the respective algorithm. In this representation, a graph node represents a surface patch and a link represents the adjacency between two patches. The attributes assigned to nodes are moment invariants of the corresponding face for polyhedral objects. For range images, the Gaussian curvature is used as a segmentation criterion for providing symbolic shape attributes. Identification is achieved by an efficient graph-matching algorithm used to match the graph obtained from the data to a subgraph of one of the model graphs stored in the commputer memory.