This paper presents an adaptive fuzzy control approach for complex tasks involving robot-environment interaction. Implementation of this approach is based on the design and optimization of fuzzy logic controller (FLC) performed in two stages. In the first stage, the FLC parameters are trained and optimized offline using a rapid prototyping algorithm combined with a method based on Solis and Wetts algorithm. The latter algorithm allows convergence of the cost function to its global minimum by using a local search algorithm which is a randomized hill-climber with an adaptive step size. For convenience of analysis, the structure of the FLC is divided into multi-input-single-output (MISO) controllers. In the second stage, an online learning of the FLC is then implemented into the proposed control structure. Robustness of the proposed approach is shown by the stability analysis based on the Lyapunov method. To show the performances of the proposed approach, simulations are carried out on a 3DOF robot performing contour following under force constraints.

This paper presents an approach for complex task control involving robot/environment interaction. An effective hybrid force/position based-approach for multi-inputs/multi-outputs (MIMO) robot control is proposed. The approach is based on fuzzy logic controller (FLC) design and optimization methodology operating in two stages: at the first stage, the FLC architecture is defined and the input variables space is partitioned; and the FLC is trained offline on the basis of data acquired during free motion of the robot, in order to map FLC outputs to real behaviour. A method based on Solis' and Wetts' algorithm is then applied for fuzzy parameter optimization so that the constraints in terms of interpretability of the predefined rules are respected. Finally, an online learning of the generated FLC is implemented into the proposed control structure. The approach has been implemented into an experimental setup, including a 2D Cartesian robot linked to a C5 parallel robot, performing contour following under force constraints. The analysis and evaluation of the obtained results show the suitability and efficiency of the proposed approach

In this paper, an adaptive fuzzy control approach for complex task involving robot/environment interaction is presented. The approach implementation is based on fuzzy logic controller (FLC) design and optimization methodology which operates in two stages. In the first stage, the FLC parameters are trained and optimized offline using a method based on Solis' and Wetts' algorithm so that the constraints in terms of interpretability and semantics are respected. For convenience of analysis, the structure of the FLC is divided into multi-input-single-output (MISO) controllers. In the second stage, an online learning of the optimized FLC is then implemented into the proposed control structure, so that the closed-loop system maintains good performances. To show the performances of the proposed approach, simulations are carried out on a three-link robot in three dimensional space, performing contour following under force constraints