R. Osorio-Comparan

Using Object’s Contour, Form and Depth to Embed Recognition Capability into Industrial Robots

Robot vision systems can differentiate parts by pattern matching irrespective of part orientation and location. Somemanufacturers offer 3D guidance systems using robust vision and laser systems so that a 3D programmed point canbe repeated even if the part is moved varying its location, rotation and orientation within the working space. Despitethese developments, current industrial robots are still unable to recognize objects in a robust manner; that is, todistinguish an object among equally shaped objects taking into account not only the object’s contour but also its formand depth information, which is precisely the major contribution of this research. Our hypothesis establishes that it ispossible to integrate a robust invariant object recognition capability into industrial robots by using image features fromthe object’s contour (boundary object information), its form (i.e., type of curvature or topographical surfaceinformation) and depth information (from stereo disparity maps). These features can be concatenated in order to forman invariant vector descriptor which is the input to an artificial neural network (ANN) for learning and recognitionpurposes. In this paper we present the recognition results under different working conditions using a KUKA KR16industrial robot, which validated our approach.

A fuzzy approach for on-line error compensation during robotic welding

During robot welding operations in the manufacturing industry there is a need to modify on-line the welding path due to a mismatch in the position of the components to be welded. These positioning errors are due to multiple factors such as ageing of the components in the part conveyor system, clamp fixtures, disturbances, etc. Therefore, robot reprogramming is needed which requires a stop in the production line and consequently an increment in production costs. In this article, we present an alternative solution to this problem that involves the use of structured lighting using a low-cost laser beam, a CMOS camera and a Fuzzy Controller. To validate the proposed control system, a robotic cell was designed using an industrial KUKA KR16 robot for welding metallic plates. The method was evaluated experimentally under lateral and vertical positioning errors. The control interface includes apart from the misalignment correction, the on/off control of the welding power supply, arc voltage and current adjustment, welding torch speed and the control of the distance between the torchs tip and the welding plate. Obtained results using the experimental design method showed a maximum error of 1.6mm, which is considered appropriate for the welding of industrial beads in metallic plates and which demonstrates the methods effectiveness in practical situations.

Learning and fast object recognition in robot skill acquisition: a new method

Invariant object recognition aims at recognising an object independently of its position, scale and orientation. This is important in robot skill acquisition during grasping operations especially when working in unstructured environments. In this paper we present an approach to aid the learning of manipulative skills on-line. We introduce and approach based on an ANN for object learning and recognition using a descriptive vector built on recurrent patterns. Experimental learning results using a fast camera are presented. Some simple parts (i.e. circular, squared and radiused-square) were used for comparing different connectionist models (Backpropagation, Perceptron and FuzzyARTMAP) and to select the appropriate model. Later during experiments, complex figures were learned using the chosen FuzzyARTMAP algorithm showing a 93.8% overall efficiency and 100% recognition rate with not so complex parts. Recognition times were lower than 1 ms, which clearly indicates the suitability of the approach to be implemented in robotic real-world operations.

A new colour image segmentation

In this paper an unsupervised colour image segmentation algorithm is presented. This method combines the advantages of the approaches based on split&merge and region growing, and the use of the RGB and HSV colour representation models. The effectiveness of the proposed method has been verified by the implementation of the algorithm using three different testing images with homogeneous regions, spatially compact and continuous. It was observed that the proposed algorithm outperforms the other analysed techniques requiring shorter processing time when compared with the other analysed methods.

Fuzzy Logic for Omni directional Mobile Platform Control Displacement using FPGA and Bluetooth

The article shows an omnidirectional mobile platform control using the artificial intelligence technique of Fuzzy Logic; the control allows a practical and reliable driving control of 4 omnidirectional wheels. The control module is implemented in FPGA allowing having an independent and autonomous single chip system out of a central computer dependence to be used in different applications like service robots platforms. An additional feature is performed by using Bluetooth communication with a cellular phone as the handset control device. Driving movements for the mobile platform is limited for eight directions, a Fuzzy Logic module controls the travelling of the platform with independent movements for each wheel, physical feedback is implemented by using electronic decoders, and experimental results were achieved with an additional feature of a handset device control based on a smartphone OS Android with Bluetooth communication. Not using external software and having a system using an artificial intelligence technique implemented in fast hardware, gives the system robust and reliable control capabilities.

Towards 3D pipe reconstruction employing affine transformations from video information

The development of a virtual scenario is desirable in a number of hostile environments such as in mining, or sewer pipelines to inspect its current condition and to identify possible failures. Obtaining a virtual image through the reconstruction of the mineshaft or inner pipe is a valuable tool for assessment and fault detection. In this paper, we present results for our 3D reconstruction approach, which proposes to employ regions with affine transformations that are used as dense correspondences. These features are calculated through local correspondences, such as the SIFT (Scale-invariant feature transform) and SURF (Speeded Up Robust Features). The correspondences are required to obtain the orientation and position of the camera and to get the structure of the scene leading to the creation of the 3D environment. The algorithm is presented as well as its results, which highlights the potential of the method.

Mobile robot navigation using potential fields and LMA

A common objective in mobile robotics is to find an optimal trajectory to reach a final destination from a starting point location. Obstacles are likely to be encountered in the robots trajectory that need to be avoided. In this article, a path planning approach for mobile robots that uses the algorithms of potential field in conjunction with Local Minimal Avoidance (LMA) is presented in order to avoid local minima and to achieve an optimal robots navigation.