Robust k-WTA Network Generation, Analysis, and Applications to Multiagent Coordination

Modified RNN for Solving Comprehensive Sylvester Equation With TDOA Application

The augmented Sylvester equation, as a comprehensive equation, is of great significance and its special cases (e.g., Lyapunov equation, Sylvester equation, Stein equation) are frequently encountered in various fields. It is worth pointing out that the current research on simultaneously eliminating the lagging error and handling noises in the nonstationary complex-valued field is rather rare. Therefore, this article focuses on solving a nonstationary complex-valued augmented Sylvester equation (NCASE) in real time and proposes two modified recurrent neural network (RNN) models. The first proposed modified RNN model possesses gradient search and velocity compensation, termed as RNN-GV model. The superiority of the proposed RNN-GV model to traditional algorithms including the complex-valued gradient-based RNN (GRNN) model lies in completely eliminating the lagging error when employed in the nonstationary problem. The second model named complex-valued integration enhanced RNN-GV with the nonlinear acceleration (IERNN-GVN) model is proposed to adapt to a noisy environment and accelerate the convergence process. Besides, the convergence and robustness of these two proposed models are proved via theoretical analysis. Simulative results on an illustrative example and an application to the moving source localization coincide with the theoretical analysis and illustrate the excellent performance of the proposed models.

Robust neural dynamics with adaptive coefficient applied to solve the dynamic matrix square root

Zeroing neural networks (ZNN) have shown their state-of-the-art performance on dynamic problems. However, ZNNs are vulnerable to perturbations, which causes reliability concerns in these models owing to the potentially severe consequences. Although it has been reported that some models possess enhanced robustness but cost worse convergence speed. In order to address these problems, a robust neural dynamic with an adaptive coefficient (RNDAC) model is proposed, aided by the novel adaptive activation function and robust evolution formula to boost convergence speed and preserve robustness accuracy. In order to validate and analyze the performance of the RNDAC model, it is applied to solve the dynamic matrix square root (DMSR) problem. Related experiment results show that the RNDAC model reliably solves the DMSR question perturbed by various noises. Using the RNDAC model, we are able to reduce the residual error from 10$$^1$$ 1 to 10$$^{-4}$$ - 4 with noise perturbed and reached a satisfying and competitive convergence speed, which converges within 3 s.

The Curved Openspace Algorithm and a Spike-Latency Model for Sonar-Based Obstacle Avoidance

The rapid control of a sonar-guided vehicle to pursue a goal while avoiding obstacles has been a persistent research topic for decades. Taking into account the limited field-of-view of practical sonar systems and vehicle kinematics, we propose a neural model for obstacle avoidance that maps the 2-D sensory space into a 1-D motor space and evaluates motor actions while combining obstacles and goal information. A two-stage winner-take-all (WTA) mechanism is used to select the final steering action. To avoid excessive scanning of the environment, an attentional system is proposed to control the directions of sonar pings for efficient, task-driven, sensory data collection. A mobile robot was used to test the proposed model navigating through a cluttered environment using a narrow field-of-view sonar system. We further propose a spiking neural model using spike-timing representations, a spike-latency memory, and a “race-to-first-spike” WTA circuit.

Distributed adaptive fixed-time neural networks control for nonaffine nonlinear multiagent systems

This paper, with the adaptive backstepping technique, presents a novel fixed-time neural networks leader–follower consensus tracking control scheme for a class of nonaffine nonlinear multiagent systems. The expression of the error system is derived, based on homeomorphism mapping theory, to formulate a set of distributed adaptive backstepping neural networks controllers. The weights of the neural networks controllers are trained, by an adaptive law based on fixed-time theory, to determine the adaptive control input. The control algorithm can guarantee that the output of the follower agents of the system effectively follow the output of the leader of the system in a fixed time, while the upper bound of the settling time can be calculated without initial parameters. Finally, a simulation example is presented to demonstrate the effectiveness of the proposed consensus tracking control approach. A step-by-step procedure for engineers and researchers interested in applications is proposed.