Three-dimensional point clouds produced by 3D scanners are often noisy and contain outliers. Such data inaccuracies can significantly affect current deep learning-based methods and reduce their ability to classify objects. Most deep neural networks-based object classification methods were targeted to achieve high classification accuracy without considering classification robustness. Thus, despite their great success, they still fail to achieve good classification accuracy with low levels of noise and outliers. This work is carried out to develop a robust network structure that can solidly identify objects. The proposed method uses patches of planar segments, which can robustly capture object appearance. The planar segments information are then fed into a deep neural network for classification. We base our approach on the PointNet deep learning architecture. Our method was tested against several kinds of data inaccuracies such as scattered outliers, clustered outliers, noise and missing points. The proposed method shows excellent performance in the presence of these inaccuracies compared to state-of-the-art techniques. By decomposing objects into planes, the suggested method is simple, fast, provides good classification accuracy and can handle different kinds of point cloud data inaccuracies. The code can be found at https://github.com/AymanMukh/Pl-Net3D INDEX TERMS Object recognition, point cloud classification, primitive fitting, robust classification.

The potential of multi-degrees-of-freedom (DOFs) local magnetic actuation (LMA) has been established in recent years for dexterous minimally invasive surgical manipulations. Nonetheless, having multiple magnetic based units, one for each DOF, within a close vicinity to each other leads to magnetic field interaction among the magnetic sources, hence resulting in a disturbance to a given LMA unit. It is further realised that the disturbance is a result of actuation effort by the neighbouring magnetic sources forming the LMA units, and that the actuation command to all LMA units is a known information to the controller. Therefore, partial information of the disturbance is known and can be exploited in a disturbance rejection strategy. In this paper, this disturbance is modelled and used to augment a simplified model of the systems dynamics of the LMA-based surgical manipulators. The internal model principle (IMP) strategy is selected in which an observer is designed to estimate the disturbance to be rejected. Numerical simulation as well as experimental validation were performed to validate the efficacy of the IMP. The results serve to remove a significant technical hurdle in bringing the new emerging technique of Local Magnetic Actuation into practical reality for abdominal surgeries.

No abstract

As manufacturing processes become increasingly automated, so should tool condition monitoring (TCM) as it is impractical to have human workers monitor the state of the tools continuously. Tool condition is crucial to ensure the good quality of products -Worn tools affect not only the surface quality but also the dimensional accuracy, which means higher reject rate of the products. Therefore, there is an urgent need to identify tool failures before it occurs on the fly. While various versions of intelligent tool condition monitoring have been proposed, most of them suffer from a cognitive nature of traditional machine learning algorithms. They focus on the how-to-learn process without paying attention to other two crucial issueswhat-to-learn, and when-to-learn. The what-to-learn and the when-to-learn provide self-regulating mechanisms to select the training samples and to determine time instants to train a model. A novel tool condition monitoring approach based on a psychologically plausible concept, namely the metacognitive scaffolding theory, is proposed and built upon a recently published algorithm recurrent classifier (rClass). The learning process consists of three phases: what-to-learn, how-to-learn, whento-learn and makes use of a generalized recurrent network structure as a cognitive component. Experimental studies with real-world manufacturing data streams were conducted where rClass demonstrated the highest accuracy while retaining the lowest complexity over its counterparts.

No abstract

No abstract

Classification of 3D shapes into physically meaningful categories is one of the most important tasks in understanding the immediate environment. Methods that leverage the recent advancements in deep learning have shown to outperform the traditional approaches. However, performances of those methods have only been analyzed with relatively clean data. Three-dimensional measurement sets (point clouds) produced by 3D scanners are rarely that accurate and often contain noise, outliers or missing points. This paper presents an extensive analysis of the robustness of the state-of-the-art neural network algorithms to realistic data inaccuracies. Our experiments show that the existence of these inaccuracies can significantly affect the performance of the deep learning-based algorithms.

Gap width is an important factor that affects material removal rate, surface finish, and machining stability in electrical discharge machining processes. This research is to develop a novel control method for a new hybrid positioning system which consists of a linear motor and a piezoelectric actuator for high-efficiency electrical discharge machining processes. In the new system, the linear motor provides the macro feeding while the piezoelectric actuator feeds the workpiece in micro scale at high frequency. To reduce the delay caused by separate movements of the linear motor and piezoelectric actuator, a new control algorithm was developed to synchronize the movements of the motor and piezoelectric actuator. A fuzzy control system was used to control the feeding process. Piezoelectric actuator position and its speed were selected as the fuzzy inputs, while the fuzzy output was the linear motor speed. Cutting experiments were conducted, and results show that the fuzzy system is more powerful than the conventional algorithm and the new algorithm with constant motor speed. An increase in material removal rate of 1.6 times was achieved using the proposed fuzzy control algorithm.