A robotic system based on neural network controllers

In this paper, a control algorithm based on neural networks is presented. This control algorithm has been applied to a robot arm which has a highly nonlinear structure. The model based approaches for robot control (such as the computed torque technique) require high computational time and can result in a poor control performance, if the specific model-structure selected does not properly reflect all the dynamics. The control technique proposed here has provided satisfactory results. A decentralised model has been assumed here where a controller is associated with each joint and a separate neural network is used to adjust the parameters of each controller. Neural networks have been used to adjust the parameters of the controllers, being the outputs of the neural networks, the control parameters.     

Inferring causal networks using fuzzy cognitive maps and evolutionary algorithms with application to gene regulatory network reconstruction

Fuzzy cognitive maps have been widely used as abstract models for complex networks. Traditional ways to construct fuzzy cognitive maps rely on domain knowledge. In this paper, we propose to use fuzzy cognitive map learning algorithms to discover domain knowledge in the form of causal networks from data. More specifically, we propose to infer gene regulatory networks from gene expression data. Furthermore, a new efficient fuzzy cognitive map learning algorithm based on a decomposed genetic algorithm is developed to learn large scale networks. In the proposed algorithm, the simulation error is used as the objective function, while the model error is expected to be minimized. Experiments are performed to explore the feasibility of this approach. The high accuracy of the generated models and the approximate correlation between simulation errors and model errors suggest that it is possible to discover causal networks using fuzzy cognitive map learning. We also compared the proposed algorithm with ant colony optimization, differential evolution, and particle swarm optimization in a decomposed framework. Comparison results reveal the advantage of the decomposed genetic algorithm on datasets with small data volumes, large network scales, or the presence of noise.     

AOM: adaptive mobile data traffic offloading for M2M networks

With the increasing application of machine-to machine (M2M) communication through cellular networks, such as telematics, smart metering, point-of-sale terminals, and home security, more data traffice has been produced in the cellular network. Although many schemes have been proposed to reduce data traffic, they are inefficient in practical application due to poor adaption. In this paper, we focus on how to adaptively offload data traffic for cellular M2M networks. To this end, we propose an adaptive mobile data traffic offloading model (AOM). This model can decide whether to adopt opportunistic communications or communicate via cellular networks adaptively. In the AOM, we introduce traffic offloading rate (called TOR) and local resource consumption rate (called LRCR) and analyze them based on continue time Markov chain. Theory proof and extensive simulations demonstrate that our model is accurate and effective, and can adaptively offload data traffic of cellular M2M networks.     

Cooperative control of multiple neural networks for an indoor blimp robot

We report on the cooperative control of multiple neural networks for an indoor blimp robot. In our research group, the indoor blimp robot has been studied to achieve various flying robot applications. The objective of this article is to propose a robust controller that can adapt to mechanical accidents such as the breakdown of propellers. In our proposed method, each propeller thrust is independently calculated by a small neural network. We confirm the advantage of the proposed method against the control by a single large neural network. This work was presented in part at the 13th International Symposium on Artificial Life and Robotics, Oita, Japan, January 31–February 2, 2008     

Hierarchical behavior categorization using correlation based adaptive resonance theory

This paper introduces a new model for robot behavior categorization. Correlation based adaptive resonance theory (CobART) networks are integrated hierarchically in order to develop an adequate categorization, and to elicit various behaviors performed by the robot. The proposed model is developed by adding a second layer CobART network which receives first layer CobART network categories as an input, and back-propagates the matching information to the first layer networks. The first layer CobART networks categorize self-behavior data of a robot or an object in the environment while the second layer CobART network categorizes the robot's behavior with respect to its effect on the object. Experiments show that the proposed model generates reasonable categorization of behaviors being tested. Moreover, it can learn different forms of the behaviors, and it can detect the relations between them. In essence, the model has an expandable architecture and it contains reusable parts. The first layer CobART networks can be integrated with other CobART networks for another categorization task. Hence, the model presents a way to reveal all behaviors performed by the robot at the same time.     

An integer programming approach to optimal control problems in context-sensitive probabilistic Boolean networks

A Boolean network is one of the models of biological networks such as gene regulatory networks, and has been extensively studied. In particular, a probabilistic Boolean network (PBN) is well known as an extension of Boolean networks, but in the existing methods to solve the optimal control problem of PBNs, it is necessary to compute the state transition diagram with 2ⁿ nodes for a given PBN with n states. To avoid this computation, an integer programming-based approach is proposed for a context-sensitive PBN (CS-PBN), which is a general form of PBNs. In the proposed method, a CS-PBN is transformed into a linear system with binary variables, and the optimal control problem is reduced to an integer linear programming problem. By a numerical example, the effectiveness of the proposed method is shown.     

A hierarchical gene regulatory network for adaptive multirobot pattern formation

Most existing multirobot systems for pattern formation rely on a predefined pattern, which is impractical for dynamic environments where the pattern to be formed should be able to change as the environment changes. In addition, adaptation to environmental changes should be realized based only on local perception of the robots. In this paper, we propose a hierarchical gene regulatory network (H-GRN) for adaptive multirobot pattern generation and formation in changing environments. The proposed model is a two-layer gene regulatory network (GRN), where the first layer is responsible for adaptive pattern generation for the given environment, while the second layer is a decentralized control mechanism that drives the robots onto the pattern generated by the first layer. An evolutionary algorithm is adopted to evolve the parameters of the GRN subnetwork in layer 1 for optimizing the generated pattern. The parameters of the GRN in layer 2 are also optimized to improve the convergence performance. Simulation results demonstrate that the H-GRN is effective in forming the desired pattern in a changing environment. Robustness of the H-GRN to robot failure is also examined. A proof-of-concept experiment using e-puck robots confirms the feasibility and effectiveness of the proposed model.     

Exploring gene causal interactions using an enhanced constraint-based method

DNA microarray provides a powerful basis for analysis of gene expression. Bayesian networks, which are based on directed acyclic graphs (DAGs) and can provide models of causal influence, have been investigated for gene regulatory networks. The difficulty with this technique is that learning the Bayesian network structure is an NP-hard problem, as the number of DAGs is superexponential in the number of genes, and an exhaustive search is intractable. In this paper, we propose an enhanced constraint-based approach for causal structure learning. We integrate with graphical Gaussian modeling and use its independence graph as an input of our constraint-based causal learning method. We also present graphical decomposition techniques to further improve the performance. Our enhanced method makes it feasible to explore causal interactions among genes interactively. We have tested our methodology using two microarray data sets. The results show that the technique is both effective and efficient in exploring causal structures from microarray data.     

Aprojected gradient based game theoretic approach for multi-user power control in cognitive radio network

The fifth generation (5G) networks have been envisioned to support the explosive growth of data demand caused by the increasing traditional high-rate mobile users and the expected rise of interconnections between human and things. To accommodate the ever-growing data traffic with scarce spectrum resources, cognitive radio (CR) is considered a promising technology to improve spectrum utilization. We study the power control problem for secondary users in an underlay CR network. Unlike most existing studies which simplify the problem by considering only a single primary user or channel, we investigate a more realistic scenario where multiple primary users share multiple channels with secondary users. We formulate the power control problem as a non-cooperative game with coupled constraints, where the Pareto optimality and achievable total throughput can be obtained by a Nash equilibrium (NE) solution. To achieve NE of the game, we first propose a projected gradient based dynamic model whose equilibrium points are equivalent to the NE of the original game, and then derive a centralized algorithm to solve the problem. Simulation results show that the convergence and effectiveness of our proposed solution, emphasizing the proposed algorithm, are competitive. Moreover, we demonstrate the robustness of our proposed solution as the network size increases.     

Designing genetic regulatory networks using fuzzy Petri nets approach

In this paper, we have successfully presented a fuzzy Petri net (FPN) model to design the genetic regulatory network. Based on the FPN model, an efficient algorithm is proposed to automatically reason about imprecise and fuzzy information. By using the reasoning algorithm for the FPN, we present an alternative approach that is more promising than the fuzzy logic. The proposed FPN approach offers more flexible reasoning capability because it is able to obtain results with fuzzy intervals rather than point values. In this paper, a novel model with a new concept of hidden fuzzy transition (HFT) to design the genetic regulatory network is developed. We have built the FPN model and classified the input data in terms of time point and obtained the output data, so the system can be viewed as the two-input and one output system. This method eliminates possible false predictions from the classical fuzzy model thereby allowing a wider search space for inferring regulatory relationship. The experimental results show the proposed approach is feasible and acceptable to design the genetic regulatory network and investigate the dynamical behaviors of gene network.     

Application of a JXTA-overlay P2P system for end-device control and e-learning

This work is motivated by the need to develop decentralized P2P approaches for controlling end-devices in a wide-area network without changing the network security policy. Much of current research work on P2P systems is devoted to P2P networks of standard peers such as PCs. Due to improvements of connections capabilities of mobile devices and end-devices, there is an increasing interest to design, implement and deploy full featured P2P networks that integrate standard peers, mobile devices and end-devices. In this paper, we use the JXTA-Overlay for the control of end-devices and e-learning in a P2P network. We considered as end-devices the smart box (which is used for stimulating the learners in our implemented P2P e-learning system), robot, and room lightening. We also considered the control of a mobile car in order to prove the applicability of our approach in wireless environment. The proposed approach, due to the capabilities of JXTA protocols to overcome firewalls and NATs, is able to control devices without changing network security policies. We evaluate the proposed system by many experiments and have shown that the proposed system has a good performance and can be used successfully for the control of end-devices and in e-learning.     

改进的YOLO特征提取算法及其在服务机器人隐私情境检测中的应用

为了提高YOLO识别较小目标的能力,解决其在特征提取过程中的信息丢失问题,提出改进的YOLO特征提取算法.将目标检测方法DPM与R-FCN融入到YOLO中,设计一种改进的神经网络结构,包含一个全连接层以及先池化再卷积的特征提取模式以减少特征信息的丢失.然后,设计基于RPN的滑动窗口合并算法,进而形成基于改进YOLO的特征提取算法.搭建服务机器人情境检测平台,给出服务机器人情境检测的总体工作流程.设计家居环境下的六类情境,建立训练数据集、验证数据集和4类测试数据集.测试分析训练步骤与预测概率估计值、学习率与识别准确性之间的关系,找出了适合所提出算法的训练步骤与学习率的经验值.测试结果表明:所提出的算法隐私情境检测准确率为94.48%,有较强的识别鲁棒性.最后,与YOLO算法的比较结果表明,本文算法在识别准确率方面优于YOLO算法.     

Generating probabilistic Boolean networks from a prescribed stationary distribution

Modeling gene regulation is an important problem in genomic research. Boolean networks (BN) and its generalization probabilistic Boolean networks (PBNs) have been proposed to model genetic regulatory interactions. BN is a deterministic model while PBN is a stochastic model. In a PBN, on one hand, its stationary distribution gives important information about the long-run behavior of the network. On the other hand, one may be interested in system synthesis which requires the construction of networks from the observed stationary distribution. This results in an inverse problem which is ill-posed and challenging. Because there may be many networks or no network having the given properties and the size of the inverse problem is huge. In this paper, we consider the problem of constructing PBNs from a given stationary distribution and a set of given Boolean Networks (BNs). We first formulate the inverse problem as a constrained least squares problem. We then propose a heuristic method based on Conjugate Gradient (CG) algorithm, an iterative method, to solve the resulting least squares problem. We also introduce an estimation method for the parameters of the PBNs. Numerical examples are then given to demonstrate the effectiveness of the proposed methods.     

Neural network-based self-learning control for power transmission line deicing robot

Recently, the application of the maintenance transmission line robot has been very popular in the power industry. However, difficulties in the control of maintenance transmission line robot exist due to multiple nonlinearities, plant parameter variations and external disturbances. This paper investigates the possibility of using neural network as a promising self-learning control alternative for the control problem of inspection and deicing transmission line robot. We first discuss the mechanical structure, as well as dynamic model of a deicing robot. And then, a neural network-based self-learning control strategy consists of a fuzzy neural network controller and an ELM-based single-layer-feedback neural networks identifier are proposed for this deicing transmission line robot. Both the structure and the learning algorithm of the control system are presented. The proposed controller is verified by computer simulations and experiments.     

A Proposed Hybrid Recurrent Neural Control System for Two Co-operating Robots

This paper discusses a model refernce adaptive (MRAC) position/force controller using proposed neural networks for two co-operating planar robots. The proposed neural network is a recurrent hybrid network. The recurrent networks have feedback connections and thus an inherent memory for dynamics, which makes them suitable for representing dynamic systems. A feature of the networks adopted is their hybrid hidden layer, which includes both linear and nonlinear neurons. On the other hand, the results of the case of a single robot under position control alone are presented for comparison. The results presented show the superior ability of the proposed neural network based model reference adaptive control scheme at adapting to changes in the dynamics parameters of robots.     

An adaptive-learning algorithm to solve the inverse kinematics problem of a 6 D.O.F serial robot manipulator

An adoptive learning strategy using an artificial neural network ANN has been proposed here to control the motion of a 6 D.O.F manipulator robot and to overcome the inverse kinematics problem, which are mainly singularities and uncertainties in arm configurations. In this approach a network have been trained to learn a desired set of joint angles positions from a given set of end effector positions, experimental results has shown an excellent mapping over the working area of the robot, to validate the ability of the designed network to make prediction and well generalization for any set of data, a new training using different data set has been performed using the same network, experimental results has shown a good generalization for the new data sets.The proposed control technique does not require any prior knowledge of the kinematics model of the system being controlled, the basic idea of this concept is the use of the ANN to learn the characteristics of the robot system rather than to specify explicit robot system model. Any modification in the physical set-up of the robot such as the addition of a new tool would only require training for a new path without the need for any major system software modification, which is a significant advantage of using neural network technology.     

Improved recurrent neural networks for online solution of Moore‐Penrose inverse applied to redundant manipulator kinematic control

In this paper, two novel neural networks (NNNs), namely NNN‐L and NNN‐R neural models, are proposed to online left and right Moore‐Penrose inversion. As compared to GNN (gradient neural network) and the recently proposed ZNN (Zhang neural network) for the left or right Moore‐Penrose inverse solving, our models are theoretically proven to possess superior global convergence performance. More importantly, the proposed NNN‐R model is successfully applied to path‐tracking control of a three‐link planar robot manipulator. Illustrative examples well validate the theoretical analyses as well as demonstrate the feasibility of the proposed models, which are adopted and verified their effectiveness in kinematic control of a redundant manipulator, for real‐time Moore‐Penrose inverse solving.     

F-Ant: an effective routing protocol for ant colony optimization based on fuzzy logic in vehicular ad hoc networks

Vehicular ad hoc networks (VANETs) are a subset of mobile ad hoc networks that provide communication services between nearby vehicles and also between vehicles and roadside infrastructure. These networks improve road safety and accident prevention and provide entertainment for passengers of vehicles. Due to the characteristics of VANET such as self-organization, dynamic nature and fast-moving vehicles, routing in this network is a considerable challenge. Swarm intelligence algorithms (nature-inspired) such as ant colony optimization (ACO) have been proposed for developing routing protocols in VANETs. In this paper, we propose an enhanced framework for ACO protocol based on fuzzy logic for VANETs. To indicate the effectiveness and performance of our proposed protocol, the network simulator NS-2 is used for simulation. The simulation results demonstrate that our proposed protocol achieves high data packet delivery ratio and low end-to-end delay compared to traditional routing algorithms such as ACO and ad hoc on-demand distance vector (AODV).

     

使用模型检测解决概率布尔网络优化控制

系统生物学期望对复杂生物系统建立一个真实的、可计算的模型,以便于以系统的角度去理解生物系统的演变过程。在系统生物学中,一个重要的主题是通过外部的干预控制发展关于基因调控网络的控制理论,以作为未来基因治疗技术。目前,布尔网络及其扩展的概率布尔网络已经被广泛用于对基因调控网络进行建模。在控制问题的研究中,概率布尔控制网络的状态迁移本质上构成一条有限状态空间的离散时间马尔科夫决策过程。依据马尔科夫决策过程的理论,通过概率模型检测方法解决网络中有限范围优化控制问题和无限范围优化控制问题。针对带有随机干扰且上下文相关的概率布尔控制网络,使用概率模型检测器PRISM对其进行形式化建模,然后将两类优化控制问题描述为相应的时序逻辑公式,最后通过模型检测寻找出最优解。实验结果表明,提出的方法可以有效地用于生物网络的分析和优化控制。