Nizar Rokbani

Biped robot control using particle swarm optimization

In this paper we propose a method to generate gaits of a biped robot by a particle swarm optimization algorithm. The system generates angular positions for joints with an interpolate end segments positions to evaluate walking stability. The proposed PSO is adapted to generate angular position joints, Human walking stability criteria are used to check and validate the gaits. The experimental procedure includes a robot assembly and online test. Then an upper torso controller is introduced to correct walking stability and limits fall downs.

Toward Intelligent Biped-Humanoids Gaits Generation

In this chapter we will highlight our experimental studies on natural human walking analysis and introduce a biologically inspired design for simple bipedal locomotion system of humanoid robots. Inspiration comes directly from human walking analysis and human muscles mechanism and control. A hybrid algorithm for walking gaits generation is then proposed as an innovative alternative to classically used kinematics and dynamic equations solving, the gaits include knee, ankle and hip trajectories. The proposed algorithm is an intelligent evolutionary based on particle swarm optimization paradigm. This proposal can be used for small size humanoid robots, with a knee an ankle and a hip and at least six Degrees of Freedom (DOF).

FROM GAITS TO ROBOT, A HYBRID METHODOLOGY FOR A BIPED WALKER

This paper presents a methodology allowing simple and effective biped robot prototyping and validation using a multi-agent architecture for gait generation and a self assembled biped walker. The gait generator, GG, is based on PSO, particle swarm optimization, which is an evolutionary algorithm; the Obtained gaits are fitted to a robot in order to evaluate the real performances of the approach. To control the Center of Mass, COM, a fuzzy approach, FGG, is introduced allowing fast and effective stability control.

IK-FA, a New Heuristic Inverse Kinematics Solver Using Firefly Algorithm

In this paper, a heuristic method based on Firefly Algorithm is proposed for inverse kinematics problems in articulated robotics. The proposal is called, IK-FA. Solving inverse kinematics, IK, consists in finding a set of joint-positions allowing a specific point of the system to achieve a target position. In IK-FA, the Fireflies positions are assumed to be a possible solution for joints elementary motions. For a robotic system with a known forward kinematic model, IK-Fireflies, is used to generate iteratively a set of joint motions, then the forward kinematic model of the system is used to compute the relative Cartesian positions of a specific end-segment, and to compare it to the needed target position. This is a heuristic approach for solving inverse kinematics without computing the inverse model. IK-FA tends to minimize the distance to a target position, the fitness function could be established as the distance between the obtained forward positions and the desired one, it is subject to minimization. In this paper IK-FA is tested over a 3 links articulated planar system, the evaluation is based on statistical analysis of the convergence and the solution quality for 100 tests. The impact of key FA parameters is also investigated with a focus on the impact of the number of fireflies, the impact of the maximum iteration number and also the impact of (α, β, γ, δ) parameters. For a given set of valuable parameters, the heuristic converges to a static fitness value within a fix maximum number of iterations. IK-FA has a fair convergence time, for the tested configuration, the average was about 2.3394 × 10−3 seconds with a position error fitness around 3.116 × 10−8 for 100 tests. The algorithm showed also evidence of robustness over the target position, since for all conducted tests with a random target position IK-FA achieved a solution with a position error lower or equal to 5.4722 × 10−9.

A New Ant Supervised-PSO Variant Applied to Traveling Salesman Problem

The Traveling Salesman Problem (TSP) is one of the standard test problems often used for benchmarking of discrete optimization algorithms. Several meta-heuristic methods, including ant colony optimization (ACO), particle swarm optimization (PSO), bat algorithm, and others, were applied to the TSP in the past. Hybrid methods are generally composed of several optimization algorithms. Ant Supervised by Particle Swarm Optimization (AS-PSO) is a hybrid schema where ACO plays the role of the main optimization procedure and PSO is used to detect optimum values of ACO parameters α, β, the amount of pheromones \( {\mathcal{T}} \) and evaporation rate ρ. The parameters are applied to the ACO algorithm which is used to search for good paths between the cities. In this paper, an Extended AS-PSO variant is proposed. In addition to the previous version, it allows to optimize the parameter, \( {\mathcal{T}} \) and the parameter, ρ. The effectiveness of the proposed method is evaluated on a set of well-known TSP problems. The experimental results show that both the average solution and the percentage deviation of the average solution to the best known solution of the proposed method are better than others methods.

Impact of Ant Size on Ant Supervised by PSO, AS-PSO, Performances

AS-PSO, ANT Supervised by PSO is hybrid hierarchical metaheuristic optimization method where PSO optimizes ANT parameters to enhance its performances. In this paper, a focus is made on the impact of the ACO swarm size on AS-PSO performances for the Traveling Salesmen Problem (TSP) where AS-PSO is already known as a relevant solver. Investigations used the AS-PSO-2Opt with both inertia weight AS-PSO and Standard AS-PSO. To demonstrate the effects of ant numbers on AS-PSO-2Opt method, a selected set of test benches form TSPLIB, berlin52, st70 and eli101 was used. In this experimental study of the ant number is waved from five to the city number of each selected test benches. Therefore, experimental results showed that the best swarm size is equal to 20 and gives the best solution for all test benches.

Experimental Investigation of Ant Supervised by Simplified PSO with Local Search Mechanism (SAS-PSO-2Opt)

Self-adapting heuristics is a very challenging research issue allowing setting a class of solvers able to overcome complex optimization problems without being tuned. Ant supervised by PSO, AS-PSO, as well as its simplified version SASPSO was proposed in this scope. The main contribution of this paper consists in coupling the simplified AS-PSO with a local search mechanism and its investigations over standard test benches, of TSP instances. Results showed that the proposed method achieved fair results in all tests: find the best-known solution or even find a better one essentially for the following cases: eil51, berlin52, st70, KroA100 and KroA200. The proposed method turns better results with a faster convergence time than the classical Ant Supervised by PSO and the standard Ant Supervised by PSO as well as related solvers essentially for eil51, berlin52, st70 and kroA100 TSP test benches.

A new approach based on Global Velocity Particle Swarm Optimization to solve job-shop scheduling problems, PSO-VG-JSSP

This paper deals with the Job-shop scheduling problem. We propose to solve this problem by exploiting the Particle Swarm Optimization Global Velocity (PSOVG) algorithm. The PSOVG by its nature focus on the global optimum within a given set of solutions. In this paper a solution is PSO particle, it consists in a possible scheduling solution for the given problem. The PSO-VG-JSSP is a PSO-VGO with a constraints control policy embedded in, allowing to detect and remove non admissible solutions. In this paper the particle representing a non admissible solution is simply removed and replaced by a new random particle.

Solving the Traveling Salesman Problem Using Ant Colony Metaheuristic, A Review

This paper presents a software application allowing to solve and compare the key metaheuristic approaches for solving the Traveling Salesman Problem (TSP). The focus is based on Ant Colony Optimization (ACO) and its major hybridization schema. In this work, the hybridization ACO algorithm with local search approach and the impact of parameters while solving TSP are investigated. The paper presents results of an empirical study of the solution quality over computation time for Ant System (AS), Elitist Ant System (EAS), Best-Worst Ant System (BWAS), MAX–MIN Ant System (MMAS) and Ant Colony System (ACS), five well-known ACO algorithms. In addition, this paper describes ACO approach combined with local search approach as 2-Opt and 3-Opt algorithms to obtain the best solution compared to ACO without local search with fixed parameters setting. The simulation experiments results show that ACO hybridized with the local search algorithm is effective for solving TSP and for avoiding the premature stagnation phenomenon of standard ACO.

PSO for Job-Shop Scheduling with Multiple Operating Sequences Problem - JS

This paper focus on a complex problem of job shop scheduling where each jobs have a multiple possible operations sequences. The resolution of this type of problem has not been treated in the literature. To solve this, a new algorithm based on Particle Swarm Optimization Global Velocity (PSOVG) was proposed. The objectif is to minimize the makespan. The simulation results show the efficiency of our proposed approach.