Integration of a stereo vision system and a laser range finder for 3-D construction

In this article, we investigate the problem of integrating a binocular stereo vision system and a laser range finder to construct a 3-D map of the environment. The proposed scheme is realized by using the alignment parameters obtained in the 2-D map construction of the laser range finder for the 3-D data generated by the stereo vision system. The 2-D map alignment task is formulated as an optimization problem of minimizing the alignment errors between local maps and selected parts of the developing global map. The problem is then solved using the Simplex method. To increase the robustness of the searching process, multiple initial guesses are provided in the Simplex method. The performance of the proposed architecture is verified by experimental results from a mobile vehicle for obstacle avoidance.     

3D registration of human face using evolutionary computation and Kriging interpolation

This paper proposes a fast and robust 3D human face geometric data registration strategy dedicated for image-guided medical applications. The registration scheme is composed of a coarse transformation stage and a fine-tuning stage. In the first stage, fuzzy c-mean is used to reduce the data amount of template 3D image, and evolutionary computation is implemented to find optimal initial pose for the Iterative Closest Point plus k-dimensional (KD) tree scheme. In the second stage, the huge reference image data are replaced by a Kriging model. The time-consuming search for corresponding points in evaluating the degree of misalignment is substituted by projecting the points in the template image onto the model. To illustrate the validity and applicability of the proposed approach, a problem composed of 174 635 points reference image and an 11 280 points template image is demonstrated. Computational results show that our approach accelerates the registration process from 1361.28 seconds to 432.85 seconds when compared with the conventional ICP plus K-D tree scheme, while the average misalignment reduces from 11.35 mm to 2.33 mm. This work was presented in part at the 13th International Symposium on Artificial Life and Robotics, Oita, Japan, January 31–February 2, 2008     

A Hybrid Search Algorithm for Porous Air Bearings Optimization

The study deals with the development of a hybrid search algorithm for efficient optimization of porous air bearings. Both the compressible Reynolds equation and Darcy's law are linearized and solved iteratively by a successive-over-relaxation method for modeling parallel-surface porous bearings. Three factors affecting the computational efficiency of the numerical model are highlighted and discussed. The hybrid optimization is performed by adopting genetic algorithm (GA) for initial search and accelerated by simplex method (SM) for refined solution. A simple and useful variable transformation is presented and used to convert the unconstrained SM to a constrained method. In this study, the hybrid search algorithm for a multi-variable design exhibits better efficiency compared with the search efficiency by using the SM. The proposed hybrid method also eliminates the need of several trials with random initial guesses to ensure high probability of global optimization. This study presents a new approach for optimizing the performance of porous air bearings and other tribological components.     

Practical and flexible path planning for car-like mobile robot using maximal-curvature cubic spiral

This paper presents a nonholonomic path planning method, aiming at taking into considerations of curvature constraint, length minimization, and computational demand, for car-like mobile robot based on cubic spirals. The generated path is made up of at most five segments: at most two maximal-curvature cubic spiral segments with zero curvature at both ends in connection with up to three straight line segments. A numerically efficient process is presented to generate a Cartesian shortest path among the family of paths considered for a given pair of start and destination configurations. Our approach is resorted to minimization via linear programming over the sum of length of each path segment of paths synthesized based on minimal locomotion cubic spirals linking start and destination orientations through a selected intermediate orientation. The potential intermediate configurations are not necessarily selected from the symmetric mean circle for non-parallel start and destination orientations. The novelty of the presented path generation method based on cubic spirals is: (i) Practical: the implementation is straightforward so that the generation of feasible paths in an environment free of obstacles is efficient in a few milliseconds; (ii) Flexible: it lends itself to various generalizations: readily applicable to mobile robots capable of forward and backward motion and Dubins’ car (i.e. car with only forward driving capability); well adapted to the incorporation of other constraints like wall-collision avoidance encountered in robot soccer games; straightforward extension to planning a path connecting an ordered sequence of target configurations in simple obstructed environment.     

Application of the Genetic Algorithm to the Multi-Objective Optimization of Air Bearings

A feasible solution must be obtained in a reasonable time with high probability of global optimum for a complex tribological design problem. To meet this decisive requirement in a multi-objective optimization problem, the popular and powerful genetic algorithms (GAs) are adopted in an illustrated air bearing design. In this study, the goal of multi-objective optimization is achieved by incorporating the criterion of Pareto optimality in the selection of mating groups in the GAs. In the illustrated example the diversity of group members in the evolution process is much better maintained by using Pareto ranking method than that with the roulette wheel selection scheme. The final selection of the optimal point of the points satisfied the Pareto optimality is based on the minimum–maximum objective deviation criterion. It is shown that the application of the GA with the Pareto ranking is especially useful in dealing with multi-objective optimizations. A hybrid selection scheme combining the Pareto ranking and roulette wheel selections is also presented to deal with a problem with a combined single objective. With the early generations running the Pareto ranking criterion, the resultant divergence preserved in the population benefits the overall GA's performance. The presented procedure is readily adoptable for parallel computing, which deserves further study in tribological designs to improve the computational efficiency.     

Model-Based Adaptive Predictive Control with Visual Servo of a Rotary Crane System

This paper investigated the implementation of an adaptive predictive controller using nonlinear dynamic echo state neural (ESN) model for a rotary crane system by the visual servo method. The control sequences within the control horizon were described using cubic spline interpolation to enlarge the predictive horizon. Verification of the proposed scheme in the face of exogenous disturbances and modeling error with inaccurate string length was demonstrated by both simulations and experiments.     

The electrochemical behavior of austenitic stainless steel with different degrees of sensitization in the transpassive potential region in 1 M H2SO4 containing chloride

This paper investigates electrochemical methods to estimate the degree of sensitization (DOS) for as-rolled and solution-treated austenitic stainless steels (AISI 304). The change in DOS was introduced by heat treatment of various time periods at 700 °C, and the electrochemical experiments were conducted at 27 °C in 1 M H₂SO₄ + 0.2 wt.% NaCl. The results show that there is no obvious difference in the anodic polarization curves of the specimens with the differences in DOS. However, the DOS of specimens can be clearly differentiated with AC impedance response in a particular transpassive potential region. In the transpassive potential region of the anodic polarization curve, as overpotential is increased beyond the breakdown potential, three types of anodic dissolution, passive dissolution, grain-boundary attack, and pitting can be characterized. The DOS can only be correctly evaluated with AC impedance response in the middle of the transpassive potential region, where anodic dissolution is of grain-boundary attack type, from 1.05 to 1.1 V. The chromium-depleted zone was preferentially attacked and an intergranular corrosion was found for the serious sensitized specimen after AC impedance test. The healing effect was observed in as-rolled specimens as the specimens were heated more than 72 h, but the effect was not found in the solution-treated specimens sensitized for up to 480 h at 700 °C.     

Robust fuzzy control and evolutionary fuzzy identification of singularly perturbed nonlinear systems with parameter uncertainty

This paper presents an H _∞ robust fuzzy control strategy which stabilizes singularly perturbed (SP) nonlinear systems with bounded uncertainties and guarantees disturbance attenuation bounds for all admissible uncertainties. The modified Takagi–Sugeno (T–S) fuzzy linear models are used to describe the SP nonlinear systems. By the proposed fuzzy control strategy, the number and type of membership functions in the fuzzy control rules are not necessarily the same as those in the fuzzy models. A sufficient condition for the existence of the H _∞ robust fuzzy controllers is then presented in terms of a novel linear matrix inequalities (LMIs) form which takes full consideration of modeling error and uncertainties in system parameters. This condition provides extra design parameters with more flexibility in control gain selection. Furthermore, we propose a compound search strategy composed of island genetic algorithms concatenated with the simplex method to identify the uncertain SP nonlinear systems for the fuzzy control design, and to solve the LMI problem. Finally, design example of the proposed H _∞ robust fuzzy controller for an uncertain SP nonlinear system is presented.     

Enhancing Design of Visual-Servo Delayed System

A robust adaptive predictor is proposed to solve the time-varying and delay control problem of an overhead crane system with a stereo-vision servo. The predictor is based on the use of a recurrent neural network (RNN) with tapped delays, and is used to supply the real-time signal of the swing angle. There are two types of discrete-time controllers under investigation, i.e., the proportional-integral-derivative (PID) controller and the sliding controller. Firstly, a design principle of the neural predictor is developed to guarantee the convergence of its swing angle estimation. Then, an improved version of the particle swarm optimization algorithm, the parallel particle swarm optimization (PPSO) method is used to optimize the control parameters of these two types of controllers. Finally, a homemade overhead crane system equipped with the Kinect sensor for the visual servo is used to verify the proposed scheme. Experimental results demonstrate the effectiveness of the approach, which also show the parameter convergence in the predictor.     

Human face detection with neural networks and the DIRECT algorithm

Based on Rowley’s approach, this article proposes a new architecture that uses a specific optimization technique, the DIRECT (DIviding RECTangle) algorithm, to improve the efficiency of face detection in images. The system consists of two main parts: a neural network-based face detection arbitrator, and a search strategy based on an integer-handling DIRECT algorithm. By the architecture, the number of arbitrations is dramatically reduced, and human faces, if they are present in an image, are not restricted to predetermined resolutions and aspect ratios. Experimental results show that the proposed architecture is efficient in terms of both speed and robustness. This work was presented in part at the 12th International Symposium on Artificial Life and Robotics, Oita, Japan, January 25–27, 2007