Learning control theory for robotic motion
A new concept of robot motions control, using ideas of a human movements organization is discussed. Two different recursive learning control are proposed: \(PD\)-type learning and \(PI\)-type learning. Basic theorems on the convergence of both learning control algorithms under the assumptions of complete repeatability of initialization, noise-free measurement of actual output signals and complete invariance of robot dynamics during repetition of operations, are proved. Problems of robustness of motion trajectories are discussed, and for \(PI\)-type learning algorithm it is shown that the introduction of a forgetting factor in the learning law plays a vital role in assurance of the robustness. For the proofs the author uses such properties of robot dynamics as passivity of the joint velocity, velocity vector (output) with respect to the input vector and existence of an energy-like Lyapunov function. At the end some important open problems are pointed out.
- Experiments on output tracking with internal stability by learning for a one-link flexible arm
- Modelling of direct motor program learning in fast human arm motions
- Iterative learning control for a class of nonlinear systems
- Robot motion similarity analysis using an FNN learning mechanism
- Repositioning control of a two-link flexible arm by learning
- Robust motion and force control of constrained manipulators by learning
- A simple iterative learning controller for manipulators with flexible joints
- Robustness of time-scale learning of robot motions to uncertainty in acquired knowledge
- High-order ILC with initial state learning for discrete-time delayed systems
- A novel tracker for a class of sampled-data nonlinear systems
- Repetitive control of electrically driven robot manipulators
- A barrier composite energy function approach for robot manipulators under alignment condition with position constraints
- scientific article; zbMATH DE number 4172860 (Why is no real title available?)
- scientific article; zbMATH DE number 18041 (Why is no real title available?)
- An improvement on the transient response of tracking for the sampled-data system based on an improved PD-type iterative learning control
- Robustness and convergence rate of a discrete-time learning control algorithm for a class of nonlinear systems
- Convergence and robustness of a discrete‐time learning control scheme for constrained manipulators
- Back-propagation neural-network based fuzzy controller with a self-learning teacher
- Learning control for a class of nonlinear differential-algebraic systems with application to constrained robots
- scientific article; zbMATH DE number 1087988 (Why is no real title available?)
- A P-type Iterative Learning Controller for Uncertain Robotic Systems with Exponentially Decaying Error Bounds
- Initial condition issues on iterative learning control for non-linear systems with time delay
- scientific article; zbMATH DE number 912640 (Why is no real title available?)
- CONTROLLING SYSTEMS WITH IMPACTS
- Iterative learning control for non-repetitive trajectory tracking of robot manipulators with joint position constraints and actuator faults
- Dynamics of a learning controller for surface tracking robots on unknown surfaces
- Some controllability aspects for iterative learning control
- Switchings between trajectory tracking and force minimization in human-robot collaboration
- Model-based update in task-level feedforward control using on-line approximation
- Neural network control of a rotating elastic manipulator
- Varying-order iterative learning control against perturbed initial conditions
- Iterative learning control applied to distributed-order linear time invariant MIMO systems to achieve learnability
This page was built for publication: Learning control theory for robotic motion
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3974134)
