Search

Neuroevolution is a promising approach for designing artificial neural networks using an evolutionary algorithm. Unlike recent trending methods that rely on gradient-based algorithms, neuroevolution can simultaneously evolve the topology and weights of neural networks. In neuroevolution with topological evolution, handling crossover is challenging because of the competing conventions problem. Mutation-based evolving artificial neural network is an alternative topology and weights neuroevolution approach that omits crossover and uses only mutations for genetic variation. This study enhances the performance of mutation-based evolving artificial neural network in two ways. First, the mutation step size controlling the magnitude of the parameter perturbation is automatically adjusted by a self-adaptive mutation mechanism, enabling a balance between exploration and exploitation during the evolution process. Second, the structural mutation probabilities are automatically adjusted depending on the network size, preventing excessive expansion of the topology. The proposed methods are compared with conventional neuroevolution algorithms using locomotion tasks provided in the OpenAI Gym benchmarks. The results demonstrate that the proposed methods with the self-adaptive mutation mechanism can achieve better performance. In addition, the adjustment of structural mutation probabilities can mitigate topological bloat while maintaining performance.

This study tackles the task of swarm robotics, where robots explore the environment to detect targets. When a robot detects a target, the robot must be connected with a base station via intermediate relay robots for wireless communication. Our previous results confirmed that Lévy flight outperformed the usual random walk for exploration strategy in an indoor environment. This paper investigated the search performance of swarm crawler robots with Lévy flight on target detection problems in large environments through a series of real robots’ experiments. The results suggest that the swarm crawler robots with Lévy flight succeeded in the target’s discovery in the indoor environment with a 100% success rate, and were able to find several targets in a given time in the outdoor environment. Thus, we confirmed that target exploration in a large environment would be possible by crawler robots with Lévy flight and significant variances in the detection rate among the positions to detect the outdoor environment’s target.

An artificial neural network (ANN) approach is proposed to the problem of estimating the propeller torques of a frigate using combined diesel, electric and gas (CODLAG) propulsion system. The authors use a multilayer perceptron (MLP) feed-forward ANN trained with data from a dataset which describes the decay state coefficients as outputs and system parameters as inputs – with a goal of determining the propeller torques, removing the decay state coefficients and using the torque values of the starboard and port propellers as outputs. A total of 53760 ANNs are trained – 26880 for each of the propellers, with a total 8960 parameter combinations. The results are evaluated using mean absolute error (MAE) and coefficient of determination (R2). Best results for the starboard propeller are MAE of 2.68 [Nm], and MAE of 2.58 [Nm] for the port propeller with following ANN configurations respectively: 2 hidden layers with 32 neurons and identity activation and 3 hidden layers with 16, 32 and 16 neurons and identity activation function. Both configurations achieve R2 value higher than 0.99. [ABSTRACT FROM AUTHOR]

In this study, the use of a popular deep reinforcement learning algorithm -- deep Q-learning -- in developing end-to-end control policies for robotic swarms is explored. Robots only have limited local sensory capabilities; however, in a swarm, they can accomplish collective tasks beyond the capability of a single robot. Compared with most automatic design approaches proposed so far, which belong to the field of evolutionary robotics, deep reinforcement learning techniques provide two advantages: (i) they enable researchers to develop control policies in an end-to-end fashion; and (ii) they require fewer computation resources, especially when the control policy to be developed has a large parameter space. The proposed approach is evaluated in a round-trip task, where the robots are required to travel between two destinations as much as possible. Simulation results show that the proposed approach can learn control policies directly from high-dimensional raw camera pixel inputs for robotic swarms. [ABSTRACT FROM AUTHOR]

Swarm robotic systems (SRSs) are a type of multirobot system in which robots operate without any form of centralized control. The typical design methodology for SRSs comprises a behavior-based approach, where the desired collective behavior is obtained manually by designing the behavior of individual robots in advance. In contrast, in an automatic design approach, a certain general methodology is adopted. This paper presents a deep reinforcement learning approach for collective behavior acquisition of SRSs. The swarm robots are expected to collect information in parallel and share their experience for accelerating their learning. We conducted real swarm robot experiments and evaluated the learning performance of the swarm in a scenario where the robots consecutively traveled between two landmarks. [ABSTRACT FROM AUTHOR]

This paper focuses on the effect of congestion on swarm performance by considering the number of robots and their size. Swarm robotics is the study of a large group of autonomous robots from which collective behavior emerges without reliance on any centralized control. Due to the fact that robotic swarms are composed of a large number of robots, it is important to consider the congestion among them. However, only a few studies have focused on the relationship between the congestion and the performance of robotic swarms;moreover, these studies only discuss the effect of the number of robots. In this study, experiments were conducted by computer simulation and carried out by varying both the number of robots and the size of the robots in a path formation task. The robot controller was designed with an evolutionary robotics approach. The results show that not only the number of robots but also their size are essential features in the relationship between congestion and swarm performance. In addition, autonomous specialization within the robotic swarm emerged in situations with moderate congestion. [ABSTRACT FROM AUTHOR]

This study deals with the estimation of the changes that occur in the Business-to-Business (B2B) networks in the Japanese textile and apparel industry by applying datasets of about 2000 companies from 2011/2012 to 2015/2016. Network analysis was used to examine the properties of the B2B networks. A factor of innovation in information and communications technology (ICT) and logistics technology was introduced into an agent-based model to demonstrate changes occurring in the related structures of B2B networks. The agent-based model was designed and tested based on qualitative information on Japanese textile and apparel industries. Consequently, network analysis revealed power-law properties and the structures of centralized hub companies. Moreover, in the simulation experiments, the centralizations of the networks generated by the agent-based model due to innovation in ICT and logistics technology were illustrated. Therefore, one of the predicted cases regarding changes that occur in the B2B networks was explained as centralizations to hub companies. [ABSTRACT FROM AUTHOR]

OBJECTIVES: Specificity of transcranial motor-evoked potentials (MEPs) is low because amplitude fluctuation is common, which seems due to several technical and fundamental reasons including difficulty in electrodes positioning and fixation for transcranial stimulation and susceptibility to anaesthesia. This study aimed to investigate the feasibility, safety and stability of our novel technique of transoesophageal spinal cord stimulation to improve the stability of MEPs. METHODS: Ten anaesthetized adult beagle dogs were used. Transoesophageal stimulation was performed between the oesophageal luminal surface electrode (cathode) and a subcutaneous needle electrode (anode) at the fourth to fifth thoracic vertebra level. Stimulation was achieved with a train of five pulses delivered at 2.0-ms intervals. Compound muscle action potentials were recorded from four limbs and external anal sphincter muscles. Stability to anaesthetic agents was tested at varying speeds of propofol and remifentanil, and effects of varying concentration of sevoflurane inhalation were also evaluated. RESULTS: Transoesophageal MEPs could be recorded without difficulty in all dogs. Fluoroscopic evaluation showed that electrodes misalignment up to 5 cm cranially or caudally could be tolerated. Stimulus intensity to achieve maximum amplitude of hindlimb muscle potentials on both sides was significantly lower by transoesophageal stimulation than by transcranial stimulation (383 ± 41 vs 533 ± 121 V, P = 0.02) and had less interindividual variability. Latency of transoesophageal MEPs was shorter than that of transcranial MEPs at every recording point. No arrhythmia was provoked during stimulation. Animals that were allowed to recover showed no neurological abnormality. In the two sacrificed animals, the explanted oesophagus showed no mucosal injury. Stability to varying dose of anaesthetic agents was similar between transoesophageal and transcranial stimulation, except for the potentials of forelimbs by transoesophageal stimulation that were resistant to anaesthetic depression. CONCLUSIONS: Transoesophageal stimulation for MEPs monitoring was feasible without difficulty and safe. Although its stability to anaesthetic agents was similar to that of transcranial stimulation, its technical ease and small interindividual variability warrants further studies on the response to spinal cord ischaemia. [ABSTRACT FROM AUTHOR]

Purpose. We examined the postoperative clinical results and hemodynamic performance of full root replacement using a freestyle stentless bioprosthesis performed in patients with severe aortic stenosis or aortic root disease. Methods. We performed 17 full root replacements with a stentless bioprosthesis. The mean age of the patients was 73.9 ± 4.1 years, ranging from 63 to 81, and 35% were male. The operative indications were aortic stenosis (AS) in 9 patients, aortic stenosis with regurgitation (ASR) in 4, and aortic regurgitation due to aortic root dissection or annuloaortic ectasia in 4. Results. The valve size of the freestyle bioprosthesis was 25.1 ± 2.6?mm, ranging from 21 to 29?mm. There were no early or late mortalities. No postoperative aortic regurgitation was found. In the 13 patients undergoing an operation for AS or ASR, peak pressure gradients were 8.5 ± 4.2 and 8.4 ± 5.2?mmHg, and LV mass indices were 159.4 ± 19.0 and 106.9 ± 22.6?g/m 2, as determined by echocardiography at 1 and 10 months after operation, respectively. Conclusion. Full root replacement with stentless bioprosthesis is a suitable procedure for patients of advanced age with severe AS, aortic root dissection, or annuloaortic ectasia, because of its superior hemodynamics. [ABSTRACT FROM AUTHOR]

Analyzes the synthesis of stable grasp by multifingered robotic hands through evolutionary programming (EP). Mathematical description of the problem; Stability conditions considered; Contact points, contact forces and joint stiffnesses as problem variables; Derivation of the EP method used.