2018 · 33 citations · 19 references
EngineeringMechanical EngineeringRobotics EngineeringMotion PlanningRobot ControlRoboticsContact DynamicsDynamic ControlImpedance ControlAdmittance ControlDynamical Movement PrimitivesIterative LearningIterative Learning ControlMovement Primitive Learning
Encoding desired motions into dynamic movement primitives (DMPs) is a common way for generating compact task representations that are able to handle sensor-based goal adaptations. At the same time, a robot should not only express adaptive motion capabilities at planning level, but use also contact wrench feedback in the adaptation and learning process of the DMP. Despite first approaches exist in this direction, no fully integrated approach has been proposed so far. In this paper, we introduce a new class of admittance-coupled DMPs that addresses environmental changes by including contact wrench feedback dynamics into the DMP formalism. Moreover, a novel iterative learning approach is devised that is based on monitoring the overall system passivity analysis in terms of reference power tracking. Simulations and experimental results with the Kuka LWR robot maintaining a non-rigid contact with the environment (wiping a surface) are shown for supporting the validity of our approach.
19
A survey of iterative learning control
Douglas A. Bristow, Marina Tharayil, Andrew G. Alleyne · IEEE Control Systems · 2006 · 2.9K citations
Impedance Control: An Approach to Manipulation
Neville Hogan · 1984 · 2.9K citations
Engineering, Mechanical Engineering, Robotics Engineering +16
Dynamical Movement Primitives: Learning Attractor Models for Motor Behaviors
Auke Jan Ijspeert, Jun Nakanishi, H. Hoffmann et al. · Neural Computation · 2012 · 1.6K citations · Full text
Reinforcement learning of motor skills with policy gradients
Jan Peters, Stefan Schaal · Neural Networks · 2008 · 864 citations