Youlun Xiong

Intelligent robotics and applications

This volume constitutes the refereed proceedings of the Second International Conference on Intelligent Robotics and Applications, ICIRA 2009, held in Singapore, in December 2009. The 128 revised full papers presented were thoroughly reviewed and selected from 173 submissions. They are organized in topical sections on ubiquitous and cooperative robots in smart space; advanced control on autonomous vehicles; intelligent vehicles: perception for safe navigation; novel techniques for collaborative driver support; robot and automation in tunneling; robot mechanism and design; robot motion analysis; robot motion control; visual perception by robots; computational intelligence by robots; robot and application; and robot and investigation.

Impulse Noise Removal Using Directional Difference Based Noise Detector and Adaptive Weighted Mean Filter

A two-stage algorithm, called switching-based adaptive weighted mean filter, is proposed to remove salt-and-pepper noise from the corrupted images. First, the directional difference based noise detector is used to identify the noisy pixels by comparing the minimum absolute value of four mean differences between the current pixel and its neighbors in four directional windows with a predefined threshold. Then, the adaptive weighted mean filter is adopted to remove the detected impulses by replacing each noisy pixel with the weighted mean of its noise-free neighbors in the filtering window. Numerous simulations demonstrate that the proposed filter outperforms many other existing algorithms in terms of effectiveness in noise detection, image restoration and computational efficiency.

A connector-based hierarchical approach to assembly sequence planning for mechanical assemblies

This paper presents an approach to find feasible and practical plans for mechanical assemblies based on a connector-based structure (CBS) hierarchy. The basic idea of the approach is to construct plans for an assembly (i.e. the root node of the CBS hierarchy) by systematically merging plans for primitive structures in the CBS hierarchy, while the plans for primitive structures are built using one of three methods: by reusing the existing plans, by retrieving the stored plans, and by geometric reasoning. The input to the approach consists of the assembly solid model, the connector-based relational model (CBRM) graph, the spatial constraint graphs, and the selected base part for the assembly, all of which are assumed to be generated previously in an interactive and/or automated way. Then, a CBS hierarchy for the assembly is automatically derived from the input CBRM by firstly establishing its functional model, which is constructed from the CBRM by decomposing the assembly or resulted part sets with respect to their connectors. Based on the CBS hierarchy, a set of assembly precedence diagrams representing good plans for the assembly are generated by merging plans for primitive structures systematically in a bottom-up manner. It can be proved that the proposed approach is both correct and complete. To verify the validness and efficiency of the approach, a variety of assemblies including some complicated products from industry are tested in the experimental CBHAP planner.

The Fast Multilevel Fuzzy Edge Detection of Blurry Images

To realize the fast and accurate detection of the edges from the blurry images, the fast multilevel fuzzy edge detection (FMFED) algorithm is proposed. The FMFED algorithm first enhances the image contrast by means of the fast multilevel fuzzy enhancement (FMFE) algorithm using the simple transformation function based on two image thresholds. Second, the edges are extracted from the enhanced image by the two-stage edge detection operator that identifies the edge candidates based on the local characteristics of the image and then determines the true edge pixels using the edge detection operator based on the extremum of the gradient values. Experimental results demonstrate that the FMFED algorithm can extract the thin edges and remove the false edges from the image, which leads to its better performance than the Sobel operator, Canny operator, traditional fuzzy edge detection algorithm, and other multilevel fuzzy edge detection algorithms

Virtual prototyping of mold design: geometric mouldability analysis for near-net-shape manufactured parts by feature recognition and geometric reasoning

This paper presents a virtual prototyping (VP) approach for geometric mouldability analysis of near-net-shape manufactured parts. The geometric mouldability of a part depends on the geometry of the part and is affected by the number and types of undercut features. A virtual prototype (VP) of a mold, which is a realistic digital product model, is generated by combining automated and interactive approaches to evaluate the mouldability of a part in the early stages of the product development cycle. The automated approaches for generating a VP are proposed to construct the parting surface, cores and cavity of the mold based on the recognized undercut features. Interaction with the VP in the virtual reality environment allows the designers to evaluate the mouldability of a part in an intuitive way. A new volume-based feature recognition method and data structure using non-directional blocking graph (NDBG) have been developed to recognize both isolated and interacting undercut features in a uniform way. Firstly, a set of potential undercuts are generated by performing the regularized difference between the part and its convex hull. The optimal parting direction is then determined by minimizing the number of undercuts. Finally, undercut features are identified from a set of potential features with respect to the optimal parting direction. The potential features of an interacting feature are generated by two stages: volume decomposition, in which the volume to be recognized is decomposed into convex cells by intersecting it with half spaces of its faces having concave edges; and reconstruction of features, in which potential features are reconstructed through systematically connecting the small cells using NDBG of the cells and the part. Moreover, multiple interpretations of an interacting feature can be easily generated by simply subtracting potential external undercut features from each other in different orders. A system configuration for the proposed VP has been developed and implemented using available virtual reality technologies.

Automatic segmentation of unorganized noisy point clouds based on the Gaussian map

A nonparametric clustering algorithm, called cell mean shift (CMS), is developed to extract clusters of a set of points on the Gaussian sphere S^2. It is computationally more efficient than the traditional mean shift (MS). Based on the singular value decomposition, the dimensional analysis is introduced to classify these clusters into point-, curve-, and area-form clusters. Each cluster is the Gaussian image of a set of points which will be examined by a connected search in R^3. An orientation analysis of the Gaussian map to area-form clusters is applied to identify hyperbolic and elliptical regions. A signed point-to-plane distance function is used to identify points of convex and concave regions. Segmentation results of several real as well as synthetic point clouds, together with complexity analyses, are presented.

Identification of the optimal product configuration and parameters based on individual customer requirements on performance and costs in one-of-a-kind production

One-of-a-kind production (OKP) aims at manufacturing products based on the requirements from individual customers while maintaining the high quality and efficiency of mass production. This research addresses the issues in identifying the optimal product configuration and its parameters based on individual customer requirements on performance and costs of products. In this work, variations of product configurations and parameters in an OKP product family are modeled by an AND-OR tree and parameters of the nodes in this tree. Different product configurations with different parameters are evaluated by performance and cost measures. These evaluation measures are converted into comparable customer satisfaction indices using the non-linear relations between the evaluation measures and the customer satisfaction indices. The optimal product configuration and its parameters with the maximum overall customer satisfaction index are identified by genetic programming and constrained optimization. A case study to identify the optimal configuration and its parameters of window products in an industrial company is used to demonstrate the effectiveness of the introduced approach.

A Distance Function Based Approach for Localization and Profile Error Evaluation of Complex Surface

This paper presents a unified framework for best-fitting of complex rigid surface to measured 3-D coordinate data by adjusting its location (position/orientation). For a point expressed in the machine reference frame and a nominal surface represented in its own model frame, a signed point-to-surface distance function is defined, and its properties are investigated, especially, its increment with respect to the differential motion of the surface, up to the second order, is derived. On this basis, localization and profile error evaluation of complex surface are formulated as a nonlinear least-squares problem and nonlinear constrained optimization problem respectively, and sequential approximation algorithms are developed to solve them. The two algorithms have the advantages of implementational simplicity, computational efficiency and robustness. Also strategies for estimating initial solution and compensating probe radius are presented. Examples confirm the validity of the proposed approach.

Global optimization of tool path for five-axis flank milling with a conical cutter

In this paper, optimum positioning of the conical cutter for five-axis flank milling of slender surfaces is addressed from the perspective of approximating the tool envelope surface to the data points on the design surface following the minimum zone criterion recommended by ANSI and ISO standards for tolerance evaluation. Based on the observation that a conical surface can be treated as a canal surface, i.e. envelope surface of one-parameter family of spheres, the swept envelope of a conical cutter is represented as a sphere-swept surface. Then, an approach is presented to efficiently compute the signed distance between a point in space and the swept surface without constructing the swept surface itself. The first order differential increment of the signed point-to-surface distance with respect to the differential deformation of the tool axis trajectory surface is derived. By using the distance function, tool path optimizations for semi-finish and finish millings are formulated as two constrained optimization problems in a unified framework, and a sequential approximation algorithm along with a hierarchical algorithmic structure is developed for the optimization. Numerical examples are given to confirm the validity and efficiency of the proposed approach. Comparing with the existing approaches, the present one improves the machining accuracy greatly. The rationale developed applies to general rotary cutters.

An alternative time-domain index for condition monitoring of rolling element bearings—A comparison study

Abstract Statistical moments have been widely used for detection and diagnosis of rolling element bearing damage. Among them, Kurtosis and Honarvar third moment S r are the major parameters. In this paper a new statistical moment, from the viewpoint of Renyi entropy, is derived, which is shown to be as effective as kurtosis and S r . Comprehensive comparisons of kurtosis, S r and this moment are performed, and the results from simulations and experiments show the new moment has a better overall performance than kurtosis and S r . On the one hand, this moment behaves much like kurtosis but is less susceptible to spurious vibrations, which is considered to be one of the main shortcomings of higher statistical moments including kurtosis. On the other hand, from the viewpoint of sensitivity to incipient faults, which is the major drawback of lower statistical moments including S r , the new moment is superior to S r . Moreover, the sensitivity of this new moment to changes of bearing speed and load is also less than kurtosis and is close to that of S r .