ALBERT

All Library Books, journals and Electronic Records Telegrafenberg

feed icon rss

Your email was sent successfully. Check your inbox.

An error occurred while sending the email. Please try again.

Proceed reservation?

Export
  • 1
    Publication Date: 2011-08-24
    Description: The limitations of backpropagation used as a function extrapolator were investigated. Four common functions were used to investigate the network's extrapolation capability. The purpose of the experiment was to determine whether neural networks are capable of extrapolation and, if so, to determine the range for which networks can extrapolate. The authors show that neural networks cannot extrapolate and offer an explanation to support this result.
    Keywords: CYBERNETICS
    Type: In: IJCNN - International Joint Conference on Neural Networks, Baltimore, MD, June 7-11, 1992, Proceedings. Vol. 4 (A93-37001 14-63); p. IV-25 to IV-30.
    Format: text
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
  • 2
    Publication Date: 2013-08-31
    Description: An envisioned lunar outpost shares with other NASA missions many of the same criteria that have prompted the development of intelligent automation techniques with NASA. Because of increased radiation hazards, crew surface activities will probably be even more restricted than current extravehicular activity in low Earth orbit. Crew availability for routine and repetitive tasks will be at least as limited as that envisioned for the space station, particularly in the early phases of lunar development. Certain tasks are better suited to the untiring watchfulness of computers, such as the monitoring and diagnosis of multiple complex systems, and the perception and analysis of slowly developing faults in such systems. In addition, mounting costs and constrained budgets require that human resource requirements for ground control be minimized. This paper provides a glimpse of certain lunar base tasks as seen through the lens of automation and robotic (A&R) considerations. This can allow a more efficient focusing of research and development not only in A&R, but also in those technologies that will depend on A&R in the lunar environment.
    Keywords: MECHANICAL ENGINEERING
    Type: NASA. Johnson Space Center, The Second Conference on Lunar Bases and Space Activities of the 21st Century, Volume 2; p 603-608
    Format: application/pdf
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
  • 3
    Publication Date: 2013-08-31
    Description: It is often proposed that the redundancy in choosing a force distribution for multiple arms grasping a single object should be handled by minimizing a quadratic performance index. The performance index may be formulated in terms of joint torques or in terms of the Cartesian space force/torque applied to the body by the grippers. The former seeks to minimize power consumption while the latter minimizes body stresses. Because the cost functions are related to each other by a joint angle dependent transformation on the weight matrix, it might be argued that either method tends to reduce power consumption, but clearly the joint space minimization is optimal. A comparison of these two options is presented with consideration given to computational cost and power consumption. Simulation results using a two arm robot system are presented to show the savings realized by employing the joint space optimization. These savings are offset by additional complexity, computation time and in some cases processor power consumption.
    Keywords: MAN/SYSTEM TECHNOLOGY AND LIFE SUPPORT
    Type: JPL, California Inst. of Tech., Proceedings of the NASA Conference on Space Telerobotics, Volume 4; p 431-443
    Format: application/pdf
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
  • 4
    Publication Date: 2019-06-28
    Description: An efficient implementation of Generalized Predictive Control using a multi-layer feedforward neural network as the plant's nonlinear model is presented. In using Newton-Raphson as the optimization algorithm, the number of iterations needed for convergence is significantly reduced from other techniques. The main cost of the Newton-Raphson algorithm is in the calculation of the Hessian, but even with this overhead the low iteration numbers make Newton-Raphson faster than other techniques and a viable algorithm for real-time control. This paper presents a detailed derivation of the Neural Generalized Predictive Control algorithm with Newton-Raphson as the minimization algorithm. Simulation results show convergence to a good solution within two iterations and timing data show that real-time control is possible. Comments about the algorithm's implementation are also included.
    Keywords: Cybernetics
    Type: NASA-TM-110244 , NAS 1.15:110244
    Format: application/pdf
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
  • 5
    Publication Date: 2019-06-28
    Description: A Volterra series approach was applied to the identification of nonlinear systems which are described by a neural network model. A procedure is outlined by which a mathematical model can be developed from experimental data obtained from the network structure. Applications of the results to the control of robotic systems are discussed.
    Keywords: CYBERNETICS
    Type: NASA-TM-104177 , NAS 1.15:104177
    Format: application/pdf
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
  • 6
    Publication Date: 2019-06-28
    Description: To increase quantified information about the effectiveness and subjective workload of force information relayed through manipulator input control devices, a space related task was performed by eight subjects with kinesthetic force feedback and/or local force accommodation through three different input control devices (i.e., hand controllers) operating in rate control mode. Task completion time, manipulator work, and subjective responses were measured. Results indicated a difference among the hand controllers. For the Honeywell six degree-of-freedom hand controller, the overall task completion times were shortest, the amount of work exerted was the least, and was the most preferred by test subjects. Neither force accommodation with or without reflection resulted in shorter task completion times or reduced work although those conditions were better than no force information for some aspects. Comparisons of results from previous studies are discussed.
    Keywords: MAN/SYSTEM TECHNOLOGY AND LIFE SUPPORT
    Type: AIAA PAPER 92-1451
    Format: text
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
  • 7
    Publication Date: 2019-07-12
    Description: No abstract available
    Keywords: Instrumentation and Photography; Administration and Management
    Type: ARC-E-DAA-TN38012
    Format: text
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
  • 8
    Publication Date: 2019-08-24
    Description: A method for monitoring position of and controlling a second nanosatellite (NS) relative to a position of a first NS. Each of the first and second NSs has a rectangular or cubical configuration of independently activatable, current-carrying solenoids, each solenoid having an independent magnetic dipole moment vector, .mu.1 and .mu.2. A vector force F and a vector torque are expressed as linear or bilinear combinations of the first set and second set of magnetic moments, and a distance vector extending between the first and second NSs is estimated. Control equations are applied to estimate vectors, .mu.1 and .mu.2, required to move the NSs toward a desired NS configuration. This extends to control of N nanosatellites.
    Keywords: Aircraft Communications and Navigation; Numerical Analysis
    Format: application/pdf
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
  • 9
    facet.materialart.
    Unknown
    In:  Other Sources
    Publication Date: 2019-07-13
    Description: A force-compensated control method for multiple manipulators is presented that allows coordinated manipulation of a jointly grasped object. In this scheme, each arm independently carries out the motions required to realize the desired motion of a prescribed point on the manipulated object. The approach has been implemented and demonstrated on a laboratory system consisting of two industrial, computer-controller manipulators.
    Keywords: CYBERNETICS
    Type: 1988 IEEE International Conference on Robotics and Automation; Apr 24, 1988 - Apr 29, 1988; Philadelphia, PA; United States
    Format: text
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
  • 10
    Publication Date: 2019-07-13
    Description: A model for a lattice control structure for telerobotic systems (Critter) has been developed and prototyped. The Critter hierarchical lattice structure, node potentiation, and weighted feedback are described, and the implementation of the Critter model on a VAX architecture is addressed with regard to node processes, lattice structure, node potentiation, and network activation. The implementation environment is considered and the Critter model attributes which are desirable in a telerobotic system are discussed. Future research directions on the use of this concept for telerobotic control are examined.
    Keywords: CYBERNETICS
    Type: 1987 American Control Conference; Jun 10, 1987 - Jun 12, 1987; Minneapolis, MN; United States
    Format: text
    Location Call Number Expected Availability
    BibTip Others were also interested in ...
Close ⊗
This website uses cookies and the analysis tool Matomo. More information can be found here...