Abstract Inverse kinematics is one of the most complicated problems in robotics. The inverse kinematics calculation is the basis for any industrial robot’s ability to plan and follow a trajectory. This paper proposes a hybrid algorithm, e3GSA, based on the gravitational search algorithm (GSA) for solving the inverse kinematics problem of an n-link redundant robot manipulator. The algorithm’s efficiency was evaluated using a fitness function comprising of position error, orientation error, and collision error, and it was found to perform better than the conventional GSA in simulations. A generalized framework was proposed and tested by simulating a 6-, 8-, and 12-link robot manipulators. Experimental validation is carried out using a 6-link robot manipulator, which shows that the simulation data are on par with the experimental data. The proposed algorithm was also found to perform adaptively with faster convergence rates and lesser computation time, making it a better choice for other engineering problems that can be transformed into optimization problems.

Abstract Fibrous networks are abundant in nature and commonly used in industry. However, their geometrical modelling is challenging due to their complex microstructure. In this study, a novel method, called fibre placement method (FPM), is developed. In contrast to the existing methods, the FPM has various advantages, such as a fully parametric definition of structure. Also, this method is superior in mimicking the stochastic microstructure of fibrous networks compared with other schemes. Various fibrous networks can be generated easily by employing a user-friendly graphical user interface. Also, the generated fibrous networks are compatible with analysis software such as computer-aided engineering tools. Finally, this algorithm characterizes various features of networks including uniformity, void area fraction, and average curliness.

Abstract Fault diagnosis of rolling element bearings (REBs), one type of essential mechanical element, has been actively researched; recent research has focused on the use of deep-learning-based approaches. However, conventional deep-learning-based fault-diagnosis approaches are vulnerable to various operating speeds, which greatly affect the vibration characteristics of the system studied. To solve this problem, previous deep-learning-based studies have usually been carried out by increasing the complexity of the model or diversifying the task of the model. Still, limitations remain because the reason of increasing complexity is unclear and the roles of multiple tasks are not well-defined. Therefore, this study proposes a multi-head de-noising autoencoder-based multi-task model for robust diagnosis of REBs under various speed conditions. The proposed model employs a multi-head de-noising autoencoder and multi-task learning strategy to robustly extract features under various speed conditions, while effectively disentangling the speed- and fault-related information. In this research, we evaluate the proposed method using the signals measured from bearing experiments under various speed conditions. The results of the evaluation study show that the proposed method outperformed conventional methods, especially when the training and test datasets have large discrepancies in their operating conditions.

Abstract Data-driven intelligent computational design (DICD) is a research hotspot that emerged under fast-developing artificial intelligence. It emphasizes utilizing deep learning algorithms to extract and represent the design features hidden in historical or fabricated design process data and then learn the combination and mapping patterns of these design features for design solution retrieval, generation, optimization, evaluation, etc. Due to its capability of automatically and efficiently generating design solutions and thus supporting human-in-the-loop intelligent and innovative design activities, DICD has drawn the attention of both academic and industrial fields. However, as an emerging research subject, many unexplored issues still limit the development and application of DICD, such as specific dataset building, engineering design-related feature engineering, systematic methods and techniques for DICD implementation in the entire product design process, etc. In this regard, a systematic and operable road map for DICD implementation from a full-process perspective is established, including a general workflow for DICD project planning, an overall framework for DICD project implementation, the common mechanisms and calculation principles during DICD, key enabling technologies for detailed DICD implementation, and three case scenarios of DICD application. The road map can help academic researchers to locate their specific research directions for the further development of DICD and provide operable guidance for the engineers in their specific DICD applications.

Abstract In a car accident, negligence is evaluated through a process known as split liability assessment. This assessment involves reconstructing the accident scenario based on information gathered from sources such as dashcam footage. The final determination of negligence is made by simulating the information contained in the video. Therefore, accident cases for split liability assessment should be classified based on information affecting the negligence degree. While deep learning has recently been in the spotlight for video recognition using short video clips, no research has been conducted to extract meaningful information from long videos, which are necessary for split liability assessment. To address this issue, we propose a new task for analysing long videos by stacking the important information predicted through the 3D CNNs model. We demonstrate the feasibility of our approach by proposing a split liability assessment method using dashcam footage.

Abstract In recent years, exploration tasks in disaster environments, victim localization and primary assistance have been the main focuses of Search and Rescue (SAR) Robotics. Developing new technologies in Mixed Reality (M-R) and legged robotics has taken a big step in developing robust field applications in the Robotics field. This article presents MR-RAS (Mixed-Reality for Robotic Assistance), which aims to assist rescuers and protect their integrity when exploring post-disaster areas (against collapse, electrical, and toxic risks) by facilitating the robot’s gesture guidance and allowing them to manage interest visual information of the environment. Thus, ARTU-R (A1 Rescue Tasks UPM Robot) quadruped robot has been equipped with a sensory system (lidar, thermal, and RGB-D cameras) to validate this proof of concept. On the other hand, Human-Robot interaction is executed by using the Hololens glasses. This work’s main contribution is the implementation and evaluation of a Mixed-Reality system based on a ROS-Unity solution, capable of managing at a high level the guidance of a complex legged robot through different interest zones (defined by a Neural Network and a vision system) of a post-disaster environment (PDE). The robot’s main tasks at each point visited involve detecting victims through thermal, RGB imaging, and neural networks and assisting victims with medical equipment. Tests have been carried out in scenarios that recreate the conditions of PDE (debris, simulation of victims, etc.). An average efficiency improvement of 48% has been obtained when using the immersive interface and a time optimization of 21.4% compared to conventional interfaces. The proposed method has proven to improve rescuers’ immersive experience of controlling a complex robotic system.

Abstract The current design of aerodynamic shapes, like airfoils, involves computationally intensive simulations to explore the possible design space. Usually, such design relies on the prior definition of design parameters and places restrictions on synthesizing novel shapes. In this work, we propose a data-driven shape encoding and generating method, which automatically learns representations from existing airfoils and uses the learned representations to generate new airfoils. The representations are then used in the optimization of synthesized airfoil shapes based on their aerodynamic performance. Our model is built upon VAEGAN, a neural network that combines Variational Autoencoder with Generative Adversarial Network and is trained by the gradient-based technique. Our model can (1) encode the existing airfoil into a latent vector and reconstruct the airfoil from that, (2) generate novel airfoils by randomly sampling the latent vectors and mapping the vectors to the airfoil coordinate domain, and (3) synthesize airfoils with desired aerodynamic properties by optimizing learned features via a genetic algorithm. Our experiments show that the learned features encode shape information thoroughly and comprehensively without predefined design parameters. By interpolating/extrapolating feature vectors or sampling from Gaussian noises, the model can automatically synthesize novel airfoil shapes, some of which possess competitive or even better aerodynamic properties as compared to airfoils used for model training purposes. By optimizing shapes on the learned latent domain via a genetic algorithm, synthesized airfoils can evolve to target aerodynamic properties. This demonstrates an efficient learning-based airfoil design framework that encodes and optimizes the airfoil on the latent domain and synthesizes promising airfoil candidates for required aerodynamic performance.

Abstract A metaheuristic algorithm that simulates the foraging behavior of remora has been proposed in recent years, called ROA. ROA mainly simulates host parasitism and host switching in the foraging behavior of remora. However, in the experiment, it was found that there is still room for improvement in the performance of ROA. When dealing with complex optimization problems, ROA often falls into local optimal solutions, and there is also the problem of too-slow convergence. Inspired by the natural rule of “Survival of the fittest”, this paper proposes a random restart strategy to improve the ability of ROA to jump out of the local optimal solution. Secondly, inspired by the foraging behavior of remora, this paper adds an information entropy evaluation strategy and visual perception strategy based on ROA. With the blessing of three strategies, a multi-strategy Remora Optimization Algorithm (MSROA) is proposed. Through 23 benchmark functions and IEEE CEC2017 test functions, MSROA is comprehensively tested, and the experimental results show that MSROA has strong optimization capabilities. In order to further verify the application of MSROA in practice, this paper tests MSROA through five practical engineering problems, which proves that MSROA has strong competitiveness in solving practical optimization problems.

Abstract Technical analysis indicators are popular tools in financial markets. These tools help investors to identify buy and sell signals with relatively large errors. The main goal of this study is to develop new practical methods to identify fake signals obtained from technical analysis indicators in the precious metals market. In this paper, we analyze these indicators in different ways based on the recorded signals for 10 months. The main novelty of this research is to propose hybrid neural network-based metaheuristic algorithms for analyzing them accurately while increasing the performance of the signals obtained from technical analysis indicators. We combine a convolutional neural network and a bidirectional gated recurrent unit whose hyperparameters are optimized using the firefly metaheuristic algorithm. To determine and select the most influential variables on the target variable, we use another successful recently developed metaheuristic, namely, the moth-flame optimization algorithm. Finally, we compare the performance of the proposed models with other state-of-the-art single and hybrid deep learning and machine learning methods from the literature. Finally, the main finding is that the proposed neural network-based metaheuristics can be useful as a decision support tool for investors to address and control the enormous uncertainties in the financial and precious metals markets.