Evolving non-trivial behaviors on real robots: A garbage collecting robot

Recently, a new approach involving a form of simulated evolution has been proposed to build autonomous robots. However, it is still not clear if this approach is adequate for real life problems. In this paper we show how control systems that perform a non-trivial sequence of behaviors can be obtained with this methodology by “canalizing” the evolutionary process in the right direction. In the experiment described in the paper, a mobile robot was successfully trained to keep clear an arena surrounded by walls by locating, recognizing, and grasping “garbage” objects and by taking collected objects outside the arena. The controller of the robot was evolved in simulation and then downloaded and tested on the real robot. We also show that while a given amount of supervision may canalize the evolutionary process in the right direction the addition of unnecessary constraints can delay the evolution of the desired behavior.     

A SVM controller for the stable walking of biped robots based on small sample sizes

Conventional machine learning methods such as neural network (NN) uses empirical risk minimization (ERM) based on infinite samples, which is disadvantageous to the gait learning control based on small sample sizes for biped robots walking in unstructured, uncertain and dynamic environments. Aiming at the stable walking control problem in the dynamic environments for biped robots, this paper puts forward a method of gait control based on support vector machines (SVM), which provides a solution for the learning control issue based on small sample sizes. The SVM is equipped with a mixed kernel function for the gait learning. Using ankle trajectory and hip trajectory as inputs, and the corresponding trunk trajectory as outputs, the SVM is trained based on small sample sizes to learn the dynamic kinematics relationships between the legs and the trunk of the biped robots. Robustness of the gait control is enhanced, which is propitious to realize the stable biped walking, and the proposed method shows superior performance when compared to SVM with radial basis function (RBF) kernels and polynomial kernels, respectively. Simulation results demonstrate the superiority of the proposed methods.     

Evolving choice structures for genetic programming

It is quite difficult but essential for Genetic Programming (GP) to evolve the choice structures. Traditional approaches usually ignore this issue. They define some “if-structures” functions according to their problems by combining “if-else” statement, conditional criterions and elemental functions together. Obviously, these if-structure functions depend on the specific problems and thus have much low reusability. Based on this limitation of GP, in this paper we propose a kind of termination criterion in the GP process named “Combination Termination Criterion” (CTC). By testing CTC, the choice structures composed of some basic functions independent to the problems can be evolved successfully. Theoretical analysis and experiment results show that our method can evolve the programs with choice structures effectively within an acceptable additional time.     

Robust recursive linear quadratic regulator for wheeled mobile robots based on optical motion capture cameras

In this paper, we deal with nonholonomic wheeled mobile robots (WMR) modeled as uncertain nonlinear systems. Sources of uncertainties can be due to erroneous estimation of mass, inertia, and center of gravity and due to payload time‐varying. They also can be considered as external disturbances generated from unstructured environments. We are proposing the use of a robust linear quadratic regulator (RLQR) to deal with tracking problems of WMR. In order to guarantee the effectiveness of this control approach, the robot posture is measured through a high‐precision motion capture system. This RLQR encompasses in a unified framework all state and output uncertain parameters of the system and does not depend on any auxiliary parameter to be tuned. It is useful to be used in online applications. Experimental results are presented with a comparative study among the R‐LQR, the nonlinear control via game theory, and the standard proportional‐derivative controller plus computed torque (PD+CT).     

Model reference adaptive control algorithms for industrial robots

In this paper some problems concerning the control of multifunctional manipulators (industrial robots) with high speed continuous movements are investigated. Although deterministic approaches to the control of robots, whose model are highly interconnected and non-linear, are known alternative approaches based on the Model Reference Adaptive System (MRAS) method of control are possible and useful. In the paper it is proved that a generalized MRAS control assures the convergence to a suitable reference model for a class of processes: the manipulator is shown to belong to such a class. The paper is completed by some applications evaluated by simulation.     

A new hybrid method using evolutionary algorithms to train Fuzzy Cognitive Maps

A novel hybrid method based on evolutionary computation techniques is presented in this paper for training Fuzzy Cognitive Maps. Fuzzy Cognitive Maps is a soft computing technique for modeling complex systems, which combines the synergistic theories of neural networks and fuzzy logic. The methodology of developing Fuzzy Cognitive Maps relies on human expert experience and knowledge, but still exhibits weaknesses in utilization of learning methods and algorithmic background. For this purpose, we investigate a coupling of differential evolution algorithm and unsupervised Hebbian learning algorithm, using both the global search capabilities of Evolutionary strategies and the effectiveness of the nonlinear Hebbian learning rule. The use of differential evolution algorithm is related to the concept of evolution of a number of individuals from generation to generation and that of nonlinear Hebbian rule to the concept of adaptation to the environment by learning. The hybrid algorithm is introduced, presented and applied successfully in real-world problems, from chemical industry and medicine. Experimental results suggest that the hybrid strategy is capable to train FCM effectively leading the system to desired states and determining an appropriate weight matrix for each specific problem.     

Models of computation for reactive control of autonomous mobile robots

The paper studies computation models for tasks performed by autonomous mobile robots. Such tasks can be accomplished by reactive control algorithms. Reactive control systems can be described using different models of computation which have as distinguishing feature the abstraction level of time. Thus, three computation models are defined: the untimed model, the synchronous model and the timed model. It is shown that the clocked-synchronous model of computation is more appropriate for describing the controller for a parallel parking task.     

Concurrent design of controller and passive elements for robots with impulsive actuation systems

There are some biological evidences showing that the actuation system in legged animals is impulsive; it is not continuous. As opposed to continuous control/actuation, the control actions occur in specific intervals, and from the instant of one actuation until the start of the next one, passive elements guarantee the stability of the robotic system and govern its natural dynamics. In this paper, we present an analytical method for concurrent design of impulsive controller and passive elements (compliance and damper) for robotic systems; e.g., manipulators and legged-robots. To optimize the force profiles of passive elements, three different cost functions are presented which optimize the natural dynamics and energy consumption of the robot. The presented method can be applied to both cyclic and non-cyclic (explosive) tasks so as to attain energy efficient and bio-inspired motions. The method is applied to three biological models: a simulated human arm for throwing an object, a swing leg for drawing an oval, and a 3D quadruped robot for performing walking gait. Our findings in the simulation studies are in line with the hypothesis of impulsive actuation in nature and show the applicability of our method in robotics.     

Revisiting parallel cyclic reduction and parallel prefix-based algorithms for block tridiagonal systems of equations

Direct solvers based on prefix computation and cyclic reduction algorithms exploit the special structure of tridiagonal systems of equations to deliver better parallel performance compared to those designed for more general systems of equations. This performance advantage is even more pronounced for block tridiagonal systems. In this paper, we re-examine the performances of these two algorithms taking the effects of block size into account. Depending on the block size, the parameter space spanned by the number of block rows, size of the blocks and the processor count is shown to favor one or the other of the two algorithms. A critical block size that separates these two regions is shown to emerge and its dependence both on problem dependent parameters and on machine-specific constants is established. Empirical verification of these analytical findings is carried out on up to 2048 cores of a Cray XT4 system.     

Behavioral task processing for cognitive robots using artificial emotions

This paper presents an artificial emotional-cognitive system-based autonomous robot control architecture for a four-wheel driven and four-wheel steered mobile robot. Discrete stochastic state-space mathematical model is considered for behavioral and emotional transition processes of the autonomous mobile robot in the dynamic realistic environment. The term of cognitive mechanism system which is composed from rule base and reinforcement self-learning algorithm explain all of the deliberative events such as learning, reasoning and memory (rule spaces) of the autonomous mobile robot. The artificial cognitive model of autonomous robot control architecture has a dynamic associative memory including behavioral transition rules which are able to be learned for achieving multi-objective robot tasks. Motivation module of architecture has been considered as behavioral gain effect generator for achieving multi-objective robot tasks. According to emotional and behavioral state transition probabilities, artificial emotions determine sequences of behaviors for long-term action planning. Also reinforcement self-learning and reasoning ability of artificial cognitive model and motivational gain effects of proposed architecture can be observed on the executing behavioral sequences during simulation. The posture and speed of the robot and the configurations, speeds and torques of the wheels and all deliberative and cognitive events can be observed from the simulation plant and virtual reality viewer. This study constitutes basis for the multi-goal robot tasks and artificial emotions and cognitive mechanism-based behavior generation experiments on a real mobile robot.     

Optimum motion planning in joint space for robots using genetic algorithms

The optimum motion planning in joint space (OMPJS) for robots, which generally consists of two subproblems, optimum path planning and optimum trajectory planning, was considered as a whole in the paper. A new method for optimum motion planning problem based on an improved genetic algorithm is proposed, which is more general, flexible and effective. This approach incorporates kinematics constraints, dynamics constraints, and control constraints of robotic manipulator. The simulation results for a two and a three degrees of freedom robots are presented and discussed. The simulations are based on genetic algorithm class library WGAClass 1.0 developed by us with Borland C++ 3.1.     

Combining series elastic actuation and magneto-rheological damping for the control of agile locomotion

All-terrain robot locomotion is an active topic of research. Search and rescue maneuvers and exploratory missions could benefit from robots with the abilities of real animals. However, technological barriers exist to ultimately achieving the actuation system, which is able to meet the exigent requirements of these robots. This paper describes the locomotion control of a leg prototype, designed and developed to make a quadruped walk dynamically while exhibiting compliant interaction with the environment. The actuation system of the leg is based on the hybrid use of series elasticity and magneto-rheological dampers, which provide variable compliance for natural-looking motion and improved interaction with the ground. The locomotion control architecture has been proposed to exploit natural leg dynamics in order to improve energy efficiency. Results show that the controller achieves a significant reduction in energy consumption during the leg swing phase thanks to the exploitation of inherent leg dynamics. Added to this, experiments with the real leg prototype show that the combined use of series elasticity and magneto-rheological damping at the knee provide a 20 % reduction in the energy wasted in braking the knee during its extension in the leg stance phase.     

Symmetry position/force hybrid control for cooperative object transportation using multiple humanoid robots

A symmetry position/force hybrid control framework for cooperative object transportation tasks with multiple humanoid robots is proposed in this paper. In a leader-follower type cooperation, follower robots plan their biped gaits based on the forces generated at their hands after a leader robot moves. Therefore, if the leader robot moves fast (rapidly pulls or pushes the carried object), some of the follower humanoid robots may lose their balance and fall down. The symmetry type cooperation discussed in this paper solves this problem because it enables all humanoid robots to move synchronously. The proposed framework is verified by dynamic simulations.     

Optimization of interval type-2 fuzzy logic controllers for a perturbed autonomous wheeled mobile robot using genetic algorithms

We describe a tracking controller for the dynamic model of a unicycle mobile robot by integrating a kinematic and a torque controller based on type-2 fuzzy logic theory and genetic algorithms. Computer simulations are presented confirming the performance of the tracking controller and its application to different navigation problems.     

On the design and simulation-based validation of an active compliance law for multi-arm robots

A special active compliance law is presented as the feedback element in a non-master/slave (i.e. symmetric) coordination strategy with explicit force distribution for robots with multiple cooperating arms. The method used to design the compliance controller comprise a structural design phase and dynamics design phase. The proposed controller structure simplifies the design problem as it maps the multivariate system onto two decoupled SISO loops with PI controllers describing internal and external compliance behavior. The conditions for the validity of this conceptual system model are discussed and the significance of task parameters such as grasp configuration, force distribution law and mechanical compliance values for the controller structure is explored. The dynamic behavior of internal and external compliance is determined in the second design phase by the choice of gain and integral action time of the respective controllers. An example shows the applicability of classical SISO control system design tools such as the root locus technique. The validity of the design method has been verified by means of the multi-arm robot simulation program MAROSIM, which is also presented in the paper.     

An indirect elicitation method for the parameters of the ELECTRE TRI-nB model using genetic algorithms

Indirect approaches for eliciting preference model parameters for multiple criteria decision aiding are of growing interest because they imply relatively less cognitive effort from the decision-maker (DM). Direct approaches are particularly hard in the case of the new ELECTRE TRI-nB method, because the task involves eliciting a number of limiting profiles for each category boundary. However, in ELECTRE methods, the simultaneous inference of the whole set of parameters needs the construction and resolution of a non-linear non-convex programming problem, which is typically very hard to solve. Therefore, an evolutionary-based method to infer the parameters of the ELECTRE TRI-nB model is proposed in this paper. The quality of the solutions is tested by measuring the capacity to restore the assignment examples and the capacity to make consistent assignments of new actions. In extensive computer experiments, using the pseudo-conjunctive assignment procedure, some main conclusions arise: (i) the capacity of the method to restore the training examples reaches high values, mainly with three and five limiting profiles per category; and (ii) the capacity to make appropriate assignments of new actions (not belonging to the training information) can be greatly improved by increasing the number of limiting profiles.     

An iterative learning scheme for motion control of robots using neural networks: A case study

In this paper, an iterative learning controller using neural networks has been studied for the motion control of robotic manipulators. Simulations of a two-link robot have demonstrated that the proposed control scheme for robotic manipulators can greatly reduce tracking errors after a few trials. Our modification of the original back-propagation algorithm is employed in the neural network, resulting in a much faster learning rate. The results of simulation have also shown that the proposed iterative learning controller has a faster rate of convergence and better robustness.     

Islanding detection of distributed generation by using multi-gene genetic programming based classifier

This paper proposed a new method for detecting islanding of distributed generation (DG), using Multi-gene Genetic Programming (MGP). Islanding has been a serious concern among power distribution utilities and distributed generation owners, because it poses risks to the safety of utilities’ workers and consumers, and can cause damage to power distribution systems’ equipment. Therefore, a DG must be disconnected as soon as an islanding is detected. In addition, an islanding detection method must have high degree of dependability to correctly discriminate islanding from other events, such as load switching, in order to avoid unnecessary disconnection of the distributed generator. In this context, the novelty of the proposed method is that the MGP is capable of obtaining a set of mathematical and logic functions employed to detect and classify islanding correctly. This is a new approach among the computational intelligent methods proposed for DG islanding detection. The main idea was to use local voltage measurements as input of the method, eliminating the need of complex and expensive communication infrastructure. The method has been trained with several islanding and non-islanding cases, by using a power distribution system comprising five concentrated loads, a synchronous distributed generator and a wind power plant. The results showed that the proposed method was successful in differentiating the islanding events from other disturbances, revealing its great potential to be applied in anti-islanding protection schemes for distributed generation.     

Minimum-phase criterion on sampling time for sampled-data interval systems using genetic algorithms

In this paper, a genetic algorithm-based approach is proposed to determine a desired sampling-time range which guarantees minimum phase behaviour for the sampled-data system of an interval plant preceded by a zero-order hold (ZOH). Based on a worst-case analysis, the identification problem of the sampling-time range is first formulated as an optimization problem, which is subsequently solved under a GA-based framework incorporating two genetic algorithms. The first genetic algorithm searches both the uncertain plant parameters and sampling time to dynamically reduce the search range for locating the desired sampling-time boundaries based on verification results from the second genetic algorithm. As a result, the desired sampling-time range ensuring minimum phase behaviour of the sampled-data interval system can be evolutionarily obtained. Because of the time-consuming process that genetic algorithms generally exhibit, particularly the problem nature which requires undertaking a large number of evolution cycles, parallel computation for the proposed genetic algorithm is therefore proposed to accelerate the derivation process. Illustrated examples in this paper have demonstrated that the proposed GA-based approach is capable of accurately locating the boundaries of the desired sampling-time range.     

Providing decision support for replenishment operations using a genetic algorithms based fuzzy system

Owing to the shockwaves brought by the recent financial tsunami, most enterprises are facing tremendous challenges in maintaining the good liquidity of their own companies. In order to sustain a desirable level of cash flow for expanding business, inventory needs to be well organized because unnecessary inventory that ties up the capital in the business would prevent the enterprises from making investments. Because the existing approaches to replenishment are inflexible and unsophisticated, a new customer‐based responsive replenishment system embracing online analytical processing, fuzzy logic and genetic algorithm is proposed in this paper. This system could determine accurate and realistic order quantities based on all possible and relevant variables that affect the order quantity for each item that needs to be replenished. Once the quantity has been accurately identified, the company can increase the level of customer satisfaction while minimizing stocks. Furthermore, rather than static rule repositioning, the proposed dynamic rule refining ability makes the replenishment system self‐ameliorating by using genetic algorithm to investigate the possible fuzzy rule candidates for a more accurate inventory management model. A study has been conducted in a case company for the validation of the feasibility of the proposed system. After performing a spatial analysis, the results obtained indicate that the proposed responsive replenishment system is capable of ensuring improved inventory control performance in the case company.