Bio-inspired Neural Network Research Articles

Improved Glasius bio-inspired neural network for target search by multi-agents

This paper focuses on solving the multi-agent cooperative target search problem with the demand for obtaining the maximal cumulative detection reward, given the prior target probability map and the sensor detection ability under various constraints. First, a topologically organized model of Glasius bio-inspired neural network (GBNN) is constructed individually for each agent in order to represent the searching environment. The neural activities are determined not only by the activity propagation among neurons, but also by the external input containing the single detection reward and various constraints synthetically. Then, the agent’s searching motion can be selected greedily based on the dynamic activity landscape of GBNN. With the disadvantages of propagation time delay and activity attenuation, however, the relatively global mechanism in GBNN may lead to unsatisfactory performance or even fail to avoid the local optimal problem. Hence the Gaussian mixture model (GMM) is utilized to extract the high-value subregions and compute the future detection reward quantitatively, which can be introduced into the neuron’s external excitatory input of GBNN directly. The simulation results verify the high efficiency and strong robustness of GBNN-GMM in the searching scenarios.

A neural network-based prediction model in water monitoring networks

Abstract To improve the prediction accuracy of ammonia nitrogen in water monitoring networks, the combination of a bio-inspired algorithm and back propagation neural network (BPNN) has often been deployed. However, due to the limitations of the bio-inspired algorithm, it would also fall into the local optimal. In this paper, the seagull optimization algorithm (SOA) was used to optimize the structure of BPNN to obtain a better prediction model. Then, an improved SOA (ISOA) was proposed, and the common functional validation method was used to verify its optimization performance. Finally, the ISOA was applied to improve BPNN, which is known as the improved seagull optimization algorithm–back propagation (ISOA–BP) model. The simulation results showed that the prediction accuracy of ammonia nitrogen was greatly improved and the proposed model can be better applied to the prediction of complex water quality parameters in water monitoring networks.

On-chip trainable hardware-based deep Q-networks approximating a backpropagation algorithm

Reinforcement learning (RL) using deep Q-networks (DQNs) has shown performance beyond the human level in a number of complex problems. In addition, many studies have focused on bio-inspired hardware-based spiking neural networks (SNNs) given the capabilities of these technologies to realize both parallel operation and low power consumption. Here, we propose an on-chip training method for DQNs applicable to hardware-based SNNs. Because the conventional backpropagation (BP) algorithm is approximated, a performance evaluation based on two simple games shows that the proposed system achieves performance similar to that of a software-based system. The proposed training method can minimize memory usage and reduce power consumption and area occupation levels. In particular, for simple problems, the memory dependency can be significantly reduced given that high performance is achieved without using replay memory. Furthermore, we investigate the effect of the nonlinearity characteristics and two types of variation of non-ideal synaptic devices on the performance outcomes. In this work, thin-film transistor (TFT)-type flash memory cells are used as synaptic devices. A simulation is also conducted using fully connected neural network with non-leaky integrated-and-fire (I&F) neurons. The proposed system shows strong immunity to device variations because an on-chip training scheme is adopted.

Adaptive Orthogonal Characteristics of Bio-Inspired Neural Networks

Abstract In recent years, neural networks have attracted much attention in the machine learning and the deep learning technologies. Bio-inspired functions and intelligence are also expected to process efficiently and improve existing technologies. In the visual pathway, the prominent features consist of nonlinear characteristics of squaring and rectification functions observed in the retinal and visual cortex networks, respectively. Further, adaptation is an important feature to activate the biological systems, efficiently. Recently, to overcome short-comings of the deep learning techniques, orthogonality for the weights in the networks has been developed for the signal propagation and the efficient optimization of the learning. In this paper, bio-inspired asymmetric networks with nonlinear characteristics are proposed, which are derived from the retinal networks in the biological visual pathway. The asymmetric network proposed here was verified to detect the movement of the object, efficiently in our previous studies. This paper shows a new characteristic of the adaptive orthogonality in the asymmetric networks. First, it is shown that the asymmetric network with nonlinear characteristics is effective for generating orthogonality. Second, the proposed asymmetric network with Gabor filters is compared with the conventional energy model from the point of the orthogonality characteristics. Finally, the asymmetric networks with nonlinear characteristics can generate the extended orthogonal bases in independent subspaces, which are useful for classification and efficient learning.

A Bioinspired Neural Network-Based Approach for Cooperative Coverage Planning of UAVs

This paper describes a bioinspired neural-network-based approach to solve a coverage planning problem for a fleet of unmanned aerial vehicles exploring critical areas. The main goal is to fully cover the map, maintaining a uniform distribution of the fleet on the map, and avoiding collisions between vehicles and other obstacles. This specific task is suitable for surveillance applications, where the uniform distribution of the fleet in the map permits them to reach any position on the map as fast as possible in emergency scenarios. To solve this problem, a bioinspired neural network structure is adopted. Specifically, the neural network consists of a grid of neurons, where each neuron has a local cost and has a local connection only with neighbor neurons. The cost of each neuron influences the cost of its neighbors, generating an attractive contribution to unvisited neurons. We introduce several controls and precautions to minimize the risk of collisions and optimize coverage planning. Then, preliminary simulations are performed in different scenarios by testing the algorithm in four maps and with fleets consisting of 3 to 10 vehicles. Results confirm the ability of the proposed approach to manage and coordinate the fleet providing the full coverage of the map in every tested scenario, avoiding collisions between vehicles, and uniformly distributing the fleet on the map.

Multi-UAV Path Planning Based on Fusion of Sparrow Search Algorithm and Improved Bioinspired Neural Network

Aiming at the problems of low stability of path planning, inability to avoid dynamic obstacles, and long path planning for multi unmanned aerial vehicles (UAV) in mountainous environment, a path planning method for UAV was proposed based on the fusion of Sparrow Search Algorithm (SSA) and Bioinspired Neural Network (BINN). The method first scans the flight environment and smoothes the surface, then raises it to obtain the safe surface, and uses SSA to find a series of nodes with the lowest comprehensive cost on the safe surface. Then, B-spline curves are used to fit these nodes, so that the planned path is smooth to meet the flight requirements of the UAV. When the dynamic obstacle is detected in the predetermined trajectory, the improved BINN method is used to carry out local path replanning to achieve the purpose of dynamic obstacle avoidance. Computer simulation results demonstrate that the fusion algorithm can plan a collision-free path in a mountainous environment, and the planned path is smooth and short. Compared with the Artificial Bee Colony Algorithm (ABC) and Dragonfly Algorithm (DA), the fusion algorithm has obvious advantages in the stability of path planning and planned path length, and has the ability of dynamic obstacle avoidance.

Bio-inspired intelligence with applications to robotics: a survey

In the past decades, considerable attention has been paid to bio-inspired intelligence and its applications to robotics. This paper provides a comprehensive survey of bio-inspired intelligence, with a focus on neurodynamics approaches, to various robotic applications, particularly to path planning and control of autonomous robotic systems. Firstly, the bio-inspired shunting model and its variants (additive model and gated dipole model) are introduced, and their main characteristics are given in detail. Then, two main neurodynamics applications to real-time path planning and control of various robotic systems are reviewed. A bio-inspired neural network framework, in which neurons are characterized by the neurodynamics models, is discussed for mobile robots, cleaning robots, and underwater robots. The bio-inspired neural network has been widely used in real-time collision-free navigation and cooperation without any learning procedures, global cost functions, and prior knowledge of the dynamic environment. In addition, bio-inspired backstepping controllers for various robotic systems, which are able to eliminate the speed jump when a large initial tracking error occurs, are further discussed. Finally, the current challenges and future research directions are discussed in this paper.

AUV Global Security Path Planning Based on a Potential Field Bio-Inspired Neural Network in Underwater Environment

AUV Global Security Path Planning Based on a Potential Field Bio-Inspired Neural Network in Underwater Environment

A Fuzzy-Based Bio-Inspired Neural Network Approach for Target Search by Multiple Autonomous Underwater Vehicles in Underwater Environments

An essential issue in a target search is safe navigation while quickly finding targets. In order to improve the efficiency of a target search and the smoothness of AUV’s (Autonomous Underwater Vehicle) trajectory, a fuzzy-b... | Find, read and cite all the research you need on Tech Science Press

Path planning and task assignment of the multi-AUVs system based on the hybrid bio-inspired SOM algorithm with neural wave structure

A hybrid bio-inspired self-organizing map neural network algorithm is proposed for path planning and task assignment for a multi-autonomous underwater vehicle (AUV) system within a mixed (dynamic and static) three-dimensional (3D) environment. A 3D hybrid bio-inspired neural network model is established to represent the underwater environment and the distribution of the neuron pheromone content gradually diffusing, centered on the source point of the neural wave. Through self-regulation of the neural wave diffusion, the targets can achieve self-adaptive capabilities. “Multiple Newton interpolation” is used to identify the real target among interference targets, and the multi-AUV system transitions from tracking the false target to tracking the real target. Based on the principle of AUV individual kinematics, a velocity vector synthesis algorithm is proposed to overcome the interference of ocean currents. Simulation studies performed in five different environments demonstrate that the proposed algorithm has high adaptability, and the potential for wide application because its neural waves can be updated in real time.

Recognition of deaf gestures based on a bio-inspired neural network

In this paper discusses the current situation in Russia and the world in the field of development of sign languages translation system. The main problems are formulated, and ways to solve them are given. One of the most important unresolved tasks is the task of recognizing the gestures of the deaf. To effectively solve it, an approach based on the development of bio-inspired neural networks is proposed. The architecture of a bio-inspired neural network, including four types of neurons, is described. New simpler MT neuron model proposed.

Optimal Time-Consuming Path Planning for Autonomous Underwater Vehicles Based on a Dynamic Neural Network Model in Ocean Current Environments

Path planning is a prerequisite for autonomous underwater vehicles to perform tasks autonomously. Many shortest distance algorithms are applied, and ocean currents are ignored to plan a short path in distance, which is usually time and energy consuming. In fact, the favourable currents can be exploited while avoiding the opposite ocean flows. Based on the bioinspired neural network architecture, this paper proposes a novel dynamic neural network model to plan the time-saving path in ocean current environments. After that, the path is smoothed by the B-spline algorithm. Analysis of the model shows that it can find out the minimum time path. Many simulations have also been introduced to test the effectiveness of the proposed model, showing good results. The dynamic neural network model has no learning procedure and can run in parallel. It has the advantages of loose parameter restrictions and wide spreading of neural activities. In addition, it has also been proven to be suitable for strong ocean currents.

Control framework for cooperative robots in smart home using bio-inspired neural network

In this paper, we present a model-free tracking controller for a cooperative mobile-manipulators, which are the cornerstone for future smart homes. The mobile-manipulators are common in industries as they are flexible and mobile, and there are several control frameworks for their industrial applications. However, these control algorithms do not consider the unique complex environment of a smart home, which requires a specialized and customized control. For example, elderly care robots in smart homes are not monitored by skilled users in that particular field, as the goals are different in the home environment, so the controller should also be different. The paper is centered around the tracking control problem of the mobile-manipulators to perform tasks individually and cooperatively. We used an optimization-driven approach to formulate an optimization problem that includes our set goals. We then used a zeroing neural network with beetle antennae search (ZNNBAS) algorithm to solve it. ZNNBAS is a nature-inspired metaheuristic algorithm inspired by the food searching nature of the beetles. It also incorporates the parallel-processing capability of ZNN, which further enhances the computational power and efficiency of the system. The paper also deals with the theoretical analysis of ZNNBAS and proves that it is stable and convergent. To test our algorithm, we used a simulated model of IIWA14 (KUKA LBR), mounted on the P3-DX mobile platform. We used two mobile-manipulators and tested them in the following scenarios: (1) Robots working independently, (2) Robots working cooperatively. The simulation results show that ZNNBAS was able to accurately and robustly complete the assigned tasks.

R-STDP Based Spiking Neural Network for Human Action Recognition

ABSTRACT Video surveillance systems are omnipresent and automatic monitoring of human activities is gaining importance in highly secured environments. The proposed work explores the use of the bio-inspired third generation neural network called spiking neural network (SNN) in order to recognize the action sequences present in a video. The SNN used in this work carries the neural information in terms of timing of spikes rather than the shape of the spikes. The learning technique used herein is reward-modulated spike time-dependent plasticity (R-STDP). It is based on reinforcement learning that modulates or demodulates the synaptic weights depending on the reward or the punishment signal that it receives from the decision layer. The absence of gradient descent techniques and external classifiers makes the system computationally efficient and simple. Finally, the performance of the network is evaluated on the two benchmark datasets, viz., Weizmann and KTH datasets.

Self-powered high-sensitivity sensory memory actuated by triboelectric sensory receptor for real-time neuromorphic computing

Artificial sensory memory, which is expected to collect, integrate, and refine massive sensory data timely for dynamically training the bioinspired neural network, is a promising candidate to achieve novel architectures of hardware artificial intelligence to mimic neural network. Unfortunately, the reports about artificial sensory memory are very limited and more importantly, there are still many unsolved problems in previously reported artificial sensory memory devices, such as the low sensitivity of perception receptors, high power consumption, and realization of instantaneous neuromorphic computing. Here, we propose a rapid-response, high-sensitivity, and self-powered artificial sensory memory, which is integrated with a triboelectric nanogenerator (TENG) and a field effect synaptic transistor, and is able to achieve real-time neuromorphic computing with a TENG matrix for the first time. Typical properties of sensory memory are successfully demonstrated, such as, excitatory post-synaptic current and paired pulse facilitation, followed with hierarchical memorial processes from sensory memory to short-term memory and to long-term memory. Finally, 28 × 28 matrix triboelectric sensory receptors are fabricated to connect the real-time handwritten image with large-scale data processing. This work proposed a remarkable self-powered artificial afferent nerve to realize rapid and high-sensitivity response, which would show a widespread potential in low consumption artificial neuromorphic interface such as human-robot interaction, edge computing and neurorobotics. • A triboelectric sensory receptor actuated high-sensitivity and self-powered artificial sensory memory is introduced. • The basic synaptic functions can be well mimicked and a hierarchical memorial process is achieved with this device. • A real-time neuromorphic computing system is achieved for the first time, which could well mimic biological sensory memory.

Automata complete computation with Hodgkin–Huxley neural networks composed of synfire rings

Synfire rings are neural circuits capable of conveying synchronous, temporally precise and self-sustained activities in a robust manner. We propose a cell assembly based paradigm for abstract neural computation centered on the concept of synfire rings. More precisely, we empirically show that Hodgkin–Huxley neural networks modularly composed of synfire rings are automata complete. We provide an algorithmic construction which, starting from any given finite state automaton, builds a corresponding Hodgkin–Huxley neural network modularly composed of synfire rings and capable of simulating it. We illustrate the correctness of the construction on two specific examples. We further analyze the stability and robustness of the construction as a function of changes in the ring topologies as well as with respect to cell death and synaptic failure mechanisms, respectively. These results establish the possibility of achieving abstract computation with bio-inspired neural networks. They might constitute a theoretical ground for the realization of biological neural computers.

An Improved Real-Time Path Planning Method Based on Dragonfly Algorithm for Heterogeneous Multi-Robot System

Heterogeneous multi-robot system is one of the most important research directions in the robotic field. Real-time path planning for heterogeneous multi-robot system under unknown 3D environment is a new challenging research and a hot spot in this field. In this paper, an improved real-time path planning method is proposed for a heterogeneous multi-robot system, which is composed of many unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs). In the proposed method, the 3D environment is modelled as a neuron topology map, based on the grid method combined with the bio-inspired neural network. Then a new 3D dynamic movement model for multi-robots is established based on an improved Dragonfly Algorithm (DA). Thus, the movements of the robots are optimized according to the activities of the neurons in the bio-inspired neural network to realize the real-time path planning. Furthermore, some simulations have been carried out. The results show that the proposed method can effectively guide the heterogeneous UAV/UGV system to the target, and has better performance than traditional methods in the real-time path planning tasks.

A leader–follower formation control approach for target hunting by multiple autonomous underwater vehicle in three-dimensional underwater environments

As one of the challenging tasks of multiple autonomous underwater vehicles systems, the realization of target hunting is the great significance. The multiple autonomous underwater vehicle target hunting is studied in this article. In some research, because the hunting members cannot reach the hunting point at the same time, the hunting time is long or the target escapes. To improve the efficiency of the target hunting, the leader–follower formation algorithm is introduced. Firstly, the task is assigned based on the distance between the autonomous underwater vehicle and the target. Then, the autonomous underwater vehicles with the same task are formed based on leader–follower mode, and the formation is kept to track the target. In the final capture phase, multiple autonomous underwater vehicle system use angle matching algorithm to round up target. The simulation results show that the proposed algorithm can effectively accomplish the target hunting task, save the hunting time, and avoid the target escape. Compared with the bioinspired neural network algorithm, the proposed algorithm shows better performance.

Toward Brain-Inspired Learning With the Neuromorphic Snake-Like Robot and the Neurorobotic Platform

Neurorobotic mimics the structural and functional principles of living creature systems. Modeling a single system by robotic hardware and software has existed for decades. However, an integrated toolset studying the interaction of all systems has not been demonstrated yet. We present a hybrid neuromorphic computing paradigm to bridge this gap by combining the neurorobotics platform (NRP) with the neuromorphic snake-like robot (NeuroSnake). This paradigm encompasses the virtual models, neuromorphic sensing and computing capabilities, and physical bio-inspired bodies, with which an experimenter can design and execute both in-silico and in-vivo robotic experimentation easily. The NRP is a public Web-based platform for easily testing brain models with virtual bodies and environments. The NeuroSnake is a bio-inspired robot equipped with a silico-retina sensor and neuromorphic computer for power-efficiency applications. We illustrate the efficiencies of our paradigm with an easy designing of a visual pursuit experiment in the NRP. We study two automatic behavior learning tasks which are further integrated into a complex task of semi-autonomous pole climbing. The result shows that robots could build new learning rules in a less explicit manner inspired by living creatures. Our method gives an alternative way to efficiently develop complex behavior control of the ro As spiking neural network is a bio-inspired neural network and the NeuroSnake robot is equipped with a spike-based silicon retina camera, the control system can be easily implemented via spiking neurons simulated on neuromorphic hardware, such as SpiNNaker.bot.

Complete Coverage Autonomous Underwater Vehicles Path Planning Based on Glasius Bio-Inspired Neural Network Algorithm for Discrete and Centralized Programming

For the complete coverage path planning of autonomous underwater vehicles (AUVs), a new strategy with Glasius bio-inspired neural network (GBNN) algorithm with discrete and centralized programming is proposed. The basic modeling for multi-AUVs complete coverage problem based on grid map and neural network is discussed first. Then, the design for single AUV complete coverage is introduced based on GBNN algorithm which is a new developed tool with small amount of calculation and high efficiency. In order to solve the difficulty of single AUV full coverage task of large water range, the multi-AUV full coverage discrete and centralized programming is proposed based on GBNN algorithm. The simulation experiment is conducted to confirm that through the proposed algorithm, multi-AUVs can plan reasonable and collision-free coverage path and reach full coverage on the same task area with division of labor and cooperation.