This paper presents an integrated fuzzy approach to recover the performance in impedance control, reducing the errors in position and force, considering uncertainties in the parameters of the manipulator model and contact surface model. This integrated strategy considers a fuzzy adaptive compensator in the outer control loop that adjusts the manipulator tip position to compensate for uncertaint...

This paper is concerned with the pouring control of tilting-ladle-type automatic pouring systems in casting industries. A new approach to the modeling and control system of the pouring process is proposed. In the approach, the flow rate model is described by a nonlinear system with hydrodynamics. The flow rate control system is built by a feedfoward control using the inverse dynamics of the flo...

In Reinforcement Learning, an agent learns a policy that maximizes a given reward function. However, providing a reward function for a given learning task is often non trivial. Inverse Reinforcement Learning, which is sometimes also called Inverse Optimal Control, addresses this problem by learning the reward function from expert demonstrations. The aim of this paper is to give a brief introduc...

An unknown linear plant will track an input command signal if the plant is driven by a controller whose transfer function approximates the inverse of the plant transfer function. An adaptive inverse identification process can be used to obtain a stable controller, even if the plant is nonminimum phase. A model-reference version of this idea allows system dynamics to closely approximate desired ...

Learning in real-time applications, e.g., online approximation of the inverse dynamics model for model-based robot control, requires fast online regression techniques. Inspired by local learning, we propose a method to speed up standard Gaussian process regression (GPR) with local GP models (LGP). The training data is partitioned in local regions, for each an individual GP model is trained. The...

This paper studies dexterous manipulation in the plane by a two-fingered hand in the plane. The dynamics of each finger, which consists of two links with coupled joints, are derived based on Lagrangian mechanics. As an object is being manipulated, its orientation and the two independent joint angles of the hand constitute the state of the entire system. Contact kinematics, accounting for both s...

The “Robotics & Automatic Control Telelab” (RACT) is a remote laboratory on robotics developed at University of Siena, which extends the field of application of the “Automatic Control Telelab” (ACT). This extension consists of adding experiments on a remote robot manipulator. RACT is mainly intended for educational use, and its Matlab-based architecture allows students to easily put in practice...

W e present a motion planning/control system that deals with moving obstacles whose trajectories are not known a priori. A n artificial potential field planner i s tightly coupled with a robust inverse dynamic controller, allowing the robot t o avoid obstacles in realtime while retaining the benefits of inverse dynamic control. Our implementation of the artificial potential field planner uses d...