Corpus ID: 3033550

Teaching Robots to Accomplish a Manipulation Task

  title={Teaching Robots to Accomplish a Manipulation Task},
  author={Seyed Sina Mirrazavi Salehian and Mahdi Khoramshahi},


A Dynamical System-based Approach to Modeling Stable Robot Control Policies via Imitation Learning
Keywords: Reaching Movements ; Dynamical Systems ; Imitation Learning ; Hitting Motions ; Obstacle Avoidance ; Stability ; Adaptability ; Robustness These Ecole polytechnique federale de LausanneExpand
A dynamical system approach to realtime obstacle avoidance
A novel approach to real-time obstacle avoidance based on Dynamical Systems (DS) that ensures impenetrability of multiple convex shaped objects and is verified in several robot experiments on the 7 degrees of freedom Barrett WAM arm. Expand
Learning Stable Nonlinear Dynamical Systems With Gaussian Mixture Models
A learning method is proposed, which is called Stable Estimator of Dynamical Systems (SEDS), to learn the parameters of the DS to ensure that all motions closely follow the demonstrations while ultimately reaching and stopping at the target. Expand
Bayesian measures of model complexity and fit
The posterior mean deviance is suggested as a Bayesian measure of fit or adequacy, and the contributions of individual observations to the fit and complexity can give rise to a diagnostic plot of deviance residuals against leverages. Expand
Nonlinear Dynamical Systems as Movement Primitives
This paper develops appropriate dynamic systems that can realize the above model, motivate the particular choice of the systems from a biological and engineering point of view, and presents simulation results of the performance of such movement primitives. Expand
and D
  • Sternad, “Nonlinear dynamical systems as movement primitives,” in proceedings of the IEEE-RAS International Conference on Humanoid Robots
  • 2000
DRAMA, a Connectionist Architecture for Control and Learning in Autonomous Robots
This work proposes a connectionist architecture, DRAMA, for dynamic control and learning of autonomous robots, a time-delay recurrent neural network, using Hebbian update rules, and uses a teacher-learner scenario, based on mutual following of the two agents, to enable transmission of a vocabulary from one robot to the other. Expand
Elastic Strips: A Framework for Integrated Planning and Execution
The elastic strip framework is computationally efficient and can be applied to robots with many degrees of freedom and is presented, which addresses the problem by integrating global motion planning methods with a reactive motion execution approach. Expand
Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper
Vibratory power unit for vibrating conveyers and screens comprising an asynchronous polyphase motor, at least one pair of associated unbalanced masses disposed on the shaft of said motor, with theExpand