Attractor switching by neural control of chaotic neurodynamics

Pasemann, Frank; Stollenwerk, Nico

doi:10.1088/0954-898x/9/4/009

Cited by 13 publications

(6 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SO(2)-based CPG is a versatile recurrent neural network consisting of two fully-connected standard additive discretetime neurons N 0 and N 1 , both using a sigmoid transfer function. The SO(2) oscillator can exhibit various dynamical behaviors (e.g., periodic patterns with different frequencies, chaotic patterns, and hysteresis effects [24], [25], [26]) by changing its synaptic weights through manual control or sensory feedback. These dynamical network behaviors can subsequently be exploited for complex locomotion (e.g., chaotic leg movement for self-untrapping of a leg from a hole in the ground [27], walking at different frequencies [28]).…”

Section: A Central Pattern Generator (Cpg)mentioning

confidence: 99%

Generic Neural Locomotion Control Framework for Legged Robots

Thor

Kulvičius

Manoonpong

2021

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

In this paper, we present a generic locomotion control framework for legged robots and a strategy for control policy optimization. The framework is based on neural control and black-box optimization. The neural control combines a central pattern generator (CPG) and a radial basis function (RBF) network to create a CPG-RBF network. The control network acts as a neural basis to produce arbitrary rhythmic trajectories for the joints of robots. The main features of the CPG-RBF network are: 1) it is generic, since it can be applied to legged robots with different morphologies; 2) it has few control parameters, resulting in fast learning; 3) it is scalable, both in terms of policy/trajectory complexity and the number of legs that can be controlled using similar trajectories; 4) it does not rely heavily on sensory feedback to generate locomotion and is thus less prone to sensory faults; and 5) once trained, it is simple, minimal, and intuitive to use and analyze. These features will lead to an easy-to-use framework with fast convergence and the ability to encode complex locomotion control policies. In this work, we show that the framework can successfully be applied to three different simulated legged robots with varying morphologies, and even broken joints, to learn locomotion control policies. We also show that after learning, the control policies can also be successfully transferred to a real-world robot without any modifications. We, furthermore, show the scalability of the framework by implementing it as a central controller for all legs of a robot and as a decentralized controller for individual legs and leg pairs. By investigating the correlation between robot morphology and encoding type, we are able to present a strategy for control policy optimization. Finally, we show how sensory feedback can be integrated into the CPG-RBF network to enable online adaptation.

show abstract

Section: A Central Pattern Generator (Cpg)mentioning

confidence: 99%

Generic Neural Locomotion Control Framework for Legged Robots

Thor

Kulvičius

Manoonpong

2021

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

show abstract

“…The SO(2)-oscillator is a neural network consisting of only two fully-connected standard additive discrete-time neurons (N 0−1 ), both using a sigmoid transfer function. The SO(2)-oscillator can produce rhythmic output signals with a phase shift of π/2 and display various dynamic behaviors (e.g., periodic patterns with varying frequencies, chaotic patterns, and hysteresis effects (38)(39)(40)) by adjusting its synaptic weights through sensory feedback or manual control. These dynamical network behaviors can subsequently be exploited for complex locomotion modes (e.g., walking at different frequencies (41), chaotic leg movement for self-untrapping of legs that are stuck (42)).…”

Section: To Generate the Basic Rhythmic Signals For Locomotion We Use...mentioning

confidence: 99%

Versatile modular neural locomotion control with fast learning

Thor¹,

Manoonpong²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Plugging chaos into Artificial Neural Networks (ANN) may enrich its state space with a large number of dynamic behaviors when compared to hopfield networks. These behaviors can be utilized through chaos control methods [18,19,21]. Results of applying such control methods to chaotic attractors showed stabilization into one of its UPOs [7,8,11,20,24].…”

Section: Introductionmentioning

confidence: 99%

Investigation of a Chaotic Spiking Neuron Model

Alhawarat¹,

Scheper²,

Crook³

2014

IJCA

View full text Add to dashboard Cite

Chaos provides many interesting properties that can be used to achieve computational tasks. Such properties are sensitivity to initial conditions, space filling, control and synchronization. Chaotic neural models have been devised to exploit such properties. In this paper, a chaotic spiking neuron model is investigated experimentally. This investigation is performed to understand the dynamic behaviours of the model. The aim of this research is to investigate the dynamics of the nonlinear dynamic state neuron (NDS) experimentally. The experimental approach has revealed some quantitative and qualitative properties of the NDS model such as the control mechanism, the reset mechanism, and the way the model may exhibit dynamic behaviours in phase space. It is shown experimentally in this paper that both the reset mechanism and the self-feed back control mechanism are important for the NDS model to work and to stabilise to one of the large number of available unstable periodic orbits (UPOs) that are embedded in its attractor. The experimental investigation suggests that the internal dynamics of the NDS neuron provide a rich set of dynamic behaviours that can be controlled and stabilised. These wide range of dynamic behaviours may be exploited to carry out information processing tasks. General Terms:Chaotic Neural Model, Chaos

show abstract

Attractor switching by neural control of chaotic neurodynamics

Cited by 13 publications

References 24 publications

Generic Neural Locomotion Control Framework for Legged Robots

Generic Neural Locomotion Control Framework for Legged Robots

Versatile modular neural locomotion control with fast learning

Investigation of a Chaotic Spiking Neuron Model

Contact Info

Product

Resources

About