Abstract
The design of robotic manipulators considering both the structure and trajectory planning problems is addressed. These problems have been solved using either classical or metaheuristics optimization techniques considering single objectives. This paper proposes a multi-objective evolutionary algorithm to generate the robot structure and required manipulator trajectories. The proposed evolutionary algorithm is organized in a hierarchical form by using three genetic algorithms to optimize the initial, final and intermediate robotic configurations which are executed for each population member of top level multi-objective structure generator. The aim is to minimize the trajectory space ripple, the initial and final binary torques, while optimizing the mechanical structure. Simulations results are presented from solving a structure synthesis problem which considers the optimization of three simultaneous objectives.

Abstract
This work addresses the fractional-order dynamics during the evolution of a Genetic Algorithm population (GA) for generating a robot manipulator trajectory. The GA objective is to minimize the trajectory space/time ripple without exceeding the torque requirements. In order to investigate the phenomena involved in the GA population evolution, the mutation is exposed to excitation perturbations and the corresponding fitness variations are evaluated. The input/output signals are studied revealing a fractional-order dynamic evolution, characteristic of a long-term system memory.

Abstract
A new optimisation algorithm is proposed that results from merging a split adaptive particle swarm optimisation algorithm with the differential evolution algorithm. The proposed technique adopts the crossover type of operator used within the differential evolution algorithm to update the swarm particle velocity vectors. The hybrid algorithm is tested in a well known benchmark continuous function and its performance compared with the particle swarm optimisation and differential evolution algorithms. Copyright (C) 2003 IFAC.

Abstract
Genetic algorithms are proposed to design two-degrees-of-freedom non-linear PID controllers for single input-single output systems. The evolutionary scheme proposed is able to design simultaneously a feedforward compensator and a nonlinear picewise PID controller. A time-domain cost function subjected to a performance constraint is deployed in order to obtain a good compromise between the set-point tracking design and the disturbance rejection design. This evolutionary approach is illustrated by a simulation example and compared with the corresponding linear configuration.

Abstract
In this paper, deterministic and Artificial Neural Networks (ANNs) based techniques are applied to generate solar radiation forecasts with the purpose of being incorporated within a greenhouse predictive control strategy. These predictions are essential to estimate heat load fluctuations in the greenhouse caused by high frequency solar radiation changes, and so to improve ventilation and heating computation requirements for the greenhouse.

Abstract
Competitive and cooperative artificial co-evolution using genetic algorithms are proposed to design PID control structures. A competitive coevolutionary based technique is proposed to design robust single-input single-output PID controllers to deal with prescribed parametric uncertainties. A cooperative coevolutionary approach and structured genetic algorithms are merged to cope with the identification of a multi-input multi-output plant within the problem of auto-tuning decentralised multivariable PI controllers. Simulated illustrative examples of both co-evolutionary techniques are presented. Copyright (C) 2000 IFAC.