Bioinspired control design using cerebellar model articulation controller network for omnidirectional mobile robots

Abstract

As a learning mechanism that emulates the structure of the cerebellum, cerebellar model articulation controllers have been widely adopted in the control of robotic systems because of the fast learning ability and simple computational structure. In this article, a cerebellar model articulation controller–based neural network controller is developed for an omnidirectional mobile robot. With the powerful learning ability of cerebellar model articulation controller, a cerebellar model articulation controller neural network is constructed to learn the complex dynamics of the omnidirectional mobile robot such that the robot is controlled without a priori knowledge of the robot dynamics. In addition, to overcome the limitation of the neural network controller, a global control technique with a group of smooth switching functions is designed such that the global ultimately uniformly boundedness of cerebellar model articulation controller is achieved instead of conventional semi-global ultimately uniformly boundedness. Moreover, smooth decreasing boundary functions are synthesized into the controller to guarantee the transient control performance. Based on an omnidirectional mobile robot, numerical experiments have been conducted to demonstrate the effectiveness of the proposed cerebellar model articulation controller controller.

Unicycle Mobile Robot Formation Control in Hardware in the Loop Environments

“…Among the different mobile robots, there are the following types of robots: unicycle, car-like and omnidirectional. The unicycle type mobile robots are the most used due to its good mobility and simple configuration, these robots are specialized in sectors such as: floor cleaning, surveillance and industrial charge transport using autonomous guided vehicles [6,7], These robots consist of a structure with 3 or 4 wheels, which in turn consist of a series of rollers that allow the wheel to move flexibly in two directions (together with the wheel and together with the roller) in the coordinate frame [8] The Car-like mobile robot is composed of an electric system, i.e., a motor with drive on the rear wheel and steering on the front wheel [9].…”

“…One of the existing alternatives is the control in formation based on different methods that are classified within three conventional ones: leader follower or master/slave [10,11], based on behavior, [12], and virtual structures. Many of the multi-vehicle coordination algorithms, such as [8], it considers only robots of punctual mass with dynamics of simple or double integrator, where the robot can be moved instantaneously in any direction on the plane. The robots uniciclo with different characteristics, require the synchronization of their movements to achieve to maintain the formation and this way to follow a predefined path [13].…”

A Biomimetic Control Method Increases the Adaptability of a Humanoid Robot Acting in a Dynamic Environment

“…Although the advantages, such as the rapid algorithmic computation based on least-mean-square training and the fast incremental learning, this approach lack of generalization and is sensitive to noise and large error (Miller et al, 1990). Over the years, researchers have been focusing on solving these drawbacks and the CMAC module has been mostly used as non-linear function approximator to boost the tracking accuracy of the adaptive controller and mitigate the effects of the approximation errors (Lin and Chen, 2007; Chen, 2009; Guan et al, 2018; Jiang et al, 2018). Although the promising results obtained by these applications of the CMAC network, this industrial research line did not completely exploit the overall capabilities and components of the cerebellum.…”

Dynamic surface control–based adaptive neural tracking for full-state constrained omnidirectional mobile robots

“…22 An adaptive NN-based control approach for wheeled mobile robots with full-state constraints was proposed. 23 Jiang et al 24 proposed a cerebellar model articulation controller (CMAC)-based NN control strategy with the BLF method to achieve the state-constrained tracking performance. But the above proposed methods are all dependent on the conventional backstepping technique.…”

“…2. Compared with the backstepping-based control schemes of full-state constrained nonlinear systems, [21][22][23][24] the NN-based adaptive DSC control approach is proposed. Because the second-order filter is used at each step of the backstepping procedure, the explosion of complexity problem can be eliminated.…”