Scheduled System Maintenance:
On May 6th, single article purchases and IEEE account management will be unavailable from 8:00 AM - 5:00 PM ET (12:00 - 21:00 UTC). We apologize for the inconvenience.
By Topic

Control Systems, IEEE

Issue 1 • Date Feb. 1994

Filter Results

Displaying Results 1 - 8 of 8
  • Swing and locomotion control for a two-link brachiation robot

    Publication Year: 1994 , Page(s): 5 - 12
    Cited by:  Papers (47)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (680 KB)  

    A mechanism and a control method is described for a two-link brachiation robot, a mobile robot that moves using its arms much like a gibbon moving from branch to branch. In our approach, the robot generates motions using a heuristic method, and achieves locomotion with trajectory and arm-direction feedback control. The robot can also control its swinging amplitude by a method based on parametric excitation. The robot's swing and locomotion control enable it to catch its target and continue locomotion from any initial state.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Acquiring robot skills via reinforcement learning

    Publication Year: 1994 , Page(s): 13 - 24
    Cited by:  Papers (37)  |  Patents (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1224 KB)  

    Skill acquisition is a difficult , yet important problem in robot performance. The authors focus on two skills, namely robotic assembly and balancing and on two classic tasks to develop these skills via learning: the peg-in hole insertion task, and the ball balancing task. A stochastic real-valued (SRV) reinforcement learning algorithm is described and used for learning control and the authors show how it can be used with nonlinear multilayer ANNs. In the peg-in-hole insertion task the SRV network successfully learns to insert to insert a peg into a hole with extremely low clearance, in spite of high sensor noise. In the ball balancing task the SRV network successfully learns to balance the ball with minimal feedback.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Controlling contact transition

    Publication Year: 1994 , Page(s): 25 - 30
    Cited by:  Papers (21)  |  Patents (4)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (576 KB)  

    Successful control of contact transitions is an important capability of dextrous robotic manipulators. We examine several methods for controlling the transition from free motion to constrained motion, with an emphasis on minimizing end-effector load oscillations during the transition. A new approach, based on input command shaping, is discussed and compared with several methods developed in prior research. The various techniques were evaluated on a one-axis impact testbed, and we present results from those experiments. The input shaping method was found to be comparable, and in some cases superior, to existing techniques of contact transition control.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Integral force control with robustness enhancement

    Publication Year: 1994 , Page(s): 31 - 40
    Cited by:  Papers (11)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (816 KB)  

    For robotic tasks involving contact between the robot end effector and the environment, force feedback is frequently used to maintain the required force of interaction. Among the many force control strategies proposed in the literature, integral force feedback has been found to be the most desirable algorithm due to its robustness with respect to the measurement time delay and its removal of steady state force error. However, there has not been any serious investigation of the controller performance under large force disturbances. We have experimentally observed that large force disturbances can cause bouncing instability of a nominally stable force control system. Motivated by this observation, we augment the standard integral force controller with three robustness enhancements: integral error scaling, force set-point scheduling, and integral windup saturation. Extensive experimentation on surfaces with different stiffness has shown the dramatic improvement of the modified controller.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real-time neural network control of a biped walking robot

    Publication Year: 1994 , Page(s): 41 - 48
    Cited by:  Papers (48)  |  Patents (5)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (962 KB)  

    Cerebellar model arithmetic computer (CMAC) neural networks can be applied to the problem of biped walking with dynamic balance. The project goal here is to develop biped control strategies based on a hierarchy of simple gait oscillators, PID controllers, and neural network learning, that do not require detailed kinematic or dynamic models. While results of simulation studies using two-dimensional biped simulators have appeared previously, the focus in this article is on real-time control studies using a ten axis biped robot with foot force sensing. This ongoing study has thus far produced several preliminary results toward efficient walking. The experimental biped has learned the closed chain kinematics necessary to shift body weight from side-to-side while maintaining good foot contact, has learned the quasi-static balance required to avoid falling forward or backward while shifting body weight from side-to-side at different speeds, and has learned the dynamic balance required in order to lift a foot off of the floor for a desired length of time, during which the foot can be moved to a new location relative to the body. Using these skills, the biped is able to march in place and take short steps without falling (too often).<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mousebuster: a robot for real-time catching

    Publication Year: 1994 , Page(s): 49 - 56
    Cited by:  Papers (25)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (865 KB)  

    A control methodology for catching a fast moving object with a robot manipulator, where visual information is employed to track the trajectory of the target, is described here. Sensing, planning, and control are performed in real time to cope with possible unpredictable trajectory changes of the moving target, and prediction techniques are adopted to compensate the time delays introduced by visual processing and by the robot controller. A simple but reliable model of the robot controller has been taken into account in the control architecture for improving the performance of the system. Experimental results have shown that the robot system is capable of tracking and catching an object moving on a plane at velocities of up to 700 mm/s and accelerations of up to 1500 mm/s/sup 2/.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robot juggling: implementation of memory-based learning

    Publication Year: 1994 , Page(s): 57 - 71
    Cited by:  Papers (43)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1461 KB)  

    Issues involved in implementing robot learning for a challenging dynamic task are explored in this article, using a case study from robot juggling. We use a memory-based local modeling approach (locally weighted regression) to represent a learned model of the task to be performed. Statistical tests are given to examine the uncertainty of a model, to optimize its prediction quality, and to deal with noisy and corrupted data. We develop an exploration algorithm that explicitly deals with prediction accuracy requirements during exploration. Using all these ingredients in combination with methods from optimal control, our robot achieves fast real-time learning of the task within 40 to 100 trials.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Implementating a hybrid learning force control scheme

    Publication Year: 1994 , Page(s): 72 - 79
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (778 KB)  

    The theory and implementation of a repetitive learning control algorithm for hybrid position and force control of robotic manipulators is presented here. The complete control system involves learning position control for translational motion tangent to an unknown surface, learning force control normal to the surface, and learning orientation control using torque feedback to maintain tangential motion relative to the surface. An IBM 7545 robot equipped with a wrist force/torque sensor is used to evaluate the performance of the proposed controller.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.

Aims & Scope

IEEE Control Systems Magazine is the largest circulation technical periodical worldwide devoted to all aspects of control systems.

Full Aims & Scope

Meet Our Editors

Editor-in-Chief
Jonathan P. How
jhow@mit.edu