1,167 Hits in 3.4 sec

Facilitating Controller Evolution in Morpho-functional Machines — A Bipedal Case Study [chapter]

Torsten Reil, Colm Massey
2003 Morpho-functional Machines: The New Species  
use of passive dynamics such as free-swinging lower legs, knee caps and springy ankles, b) proportional derivative controllers (or their variants) as actuators, and c) a modular, specifically coupled neural  ...  Simulations of bipedal walking showed that the evolution of stable gaits can be greatly facilitated by harnessing design solutions inspired by those of biological organisms.  ...  Acknowledgements The authors would like to thank David Raubenheimer and Julian Worby for helpful suggestions, as well as MathEngine PLC for early access to their Dynamics Toolkit.  ... 
doi:10.1007/978-4-431-67869-4_5 fatcat:xfs5ykfqnjg3tj3bvxuotm4vqm

Sensor-driven neural control for omnidirectional locomotion and versatile reactive behaviors of walking machines

P. Manoonpong, F. Pasemann, F. Wörgötter
2008 Robotics and Autonomous Systems  
This article describes modular neural control structures for different walking machines utilizing discrete-time neurodynamics.  ...  A simple neural oscillator network serves as a central pattern generator producing the basic rhythmic leg movements.  ...  Thus, the basic rhythmic leg movement is generated by the neural oscillator ) - . Modular neural control for omnidirectional locomotion and the reflex behavior of walking machines.  ... 
doi:10.1016/j.robot.2007.07.004 fatcat:ltjg3iptbrclpben7jcpwhsjby

Dynamical Systems in the Sensorimotor Loop: On the Interrelation Between Internal and External Mechanisms of Evolved Robot Behavior [chapter]

Martin Hülse, Steffen Wischmann, Poramate Manoonpong, Arndt von Twickel, Frank Pasemann
2007 Lecture Notes in Computer Science  
By using structural evolution, minimal recurrent neural networks of general type were evolved for behavior control.  ...  The small size of the neural structures facilitates thorough investigations of behavior relevant neural dynamics and how they relate to interactions of robots within the sensorimotor loop.  ...  Neural hysteresis in reflex-walking-control. In this section the role of a hysteresis element in a simple neural reflex-oscillator for single-leg (3DOF) control of walking machines is demonstrated.  ... 
doi:10.1007/978-3-540-77296-5_18 fatcat:pr5v6v67rffmhllquc4hdlbcse


M. Anthony Lewis, Andrew H. Fagg, George A. Bekey
1994 Recent Trends in Mobile Robots  
First, an oscillator for the individual leg movements is evolved. Then, a network of these oscillators is evolved to coordinate the movements of the different legs.  ...  This paper describes the staged evolution of a complex motor pattern generator (CPG) for the control of the leg movements of a six-legged walking robot. The CPG is composed of a network of neurons.  ...  Phase 2 : Evolving to Walk The genetic string for the second phase not only specifies the circuitry for the oscillator, but also the set of connections between the oscillators.  ... 
doi:10.1142/9789814354301_0011 fatcat:7yhwb6uzmrdyfavadfiu2j4f54

Behavior control in the sensorimotor loop with short-term synaptic dynamics induced by self-regulating neurons

Hazem Toutounji, Frank Pasemann
2014 Frontiers in Neurorobotics  
Neural systems endowed with the derived synaptic dynamics can be utilized for the neural behavior control of autonomous mobile agents.  ...  They can also operate as oscillators, which allow them to surpass the level of activity imposed by their homeostatic operation conditions.  ...  AUTHOR CONTRIBUTIONS ACKNOWLEDGMENTS The authors thank Josef Behr, Andrea Suckro, and Florian Ziegler for testing and refining the simulation models and for their contributions to the NERD Toolkit.  ... 
doi:10.3389/fnbot.2014.00019 pmid:24904403 pmcid:PMC4033235 fatcat:nlqmhpnkf5ej7lmpoftz4febiy

Neural Reflex Networks for Automating Quadcopter Drone Obstacle Avoidance

Marius Alexandru PANAIT
2022 INCAS Bulletin  
Using a physical representation of biologic neurons, both motor (NU) and cortical (NV) these structures mimic simple reflex arcs present in a large number of evolved organisms.  ...  These powerful neuromimetic machines allow for a robust implementation of automated responses in autonomous or semi-autonomous robots.  ...  CONCLUSIONS Modern approaches to neural network control for mobile platforms (mainly smart cars and industrial robots, line followers etc.) rely heavily on machine vision and a large class of neural networks  ... 
doi:10.13111/2066-8201.2022.14.2.6 fatcat:w2dd3ufs3nhl7ofqwrmscxsjfq

Insect-Inspired Robots: Bridging Biological and Artificial Systems

Poramate Manoonpong, Luca Patanè, Xiaofeng Xiong, Ilya Brodoline, Julien Dupeyroux, Stéphane Viollet, Paolo Arena, Julien R. Serres
2021 Sensors  
Are insects good models for building such intelligent hexapod robots because they are the only animals with six legs?  ...  Acknowledgments: We thank Vincent Fourcassié and Pierre Moretto from CRCA UMR5163 (CNRS/ University of Toulouse 3), France, for their fruitful discussions concerning biological inputs in ants.  ...  Thor and Manoonpong: Neural oscillator and fast dynamic state recovery dynamical state forcing for online adaptation Chuthong et al.: Neural oscillator with Figure 7.  ... 
doi:10.3390/s21227609 pmid:34833685 pmcid:PMC8623770 fatcat:7gne3leewjhwhaqs4bcd5hmxjm

A simple neural network solar tracker for optimizing conversion efficiency in off-grid solar generators

M.A. Panait, T. Tudorache
2008 The Renewable Energies and Power Quality Journal (RE&PQJ)  
The project aims to develop a small pilot tracker -based solar plant for testing purposes and to develop a useable technology for the ever-growing demand for green power.  ...  A new model of neural network and a new type of neural controller are proposed, aiming to reduce cost and complexity without sacrificing efficiency of traditional, more complex neural net-based solar trackers  ...  We take this occasion to thank Romanian projects management institutions CNCSIS and CNMP for their support and also to the Laboratory of Electrical Engineering in Medicine from Univ.  ... 
doi:10.24084/repqj06.278 fatcat:62qowvmd65hm3g24eu34mozxk4

A Distributed Neural Network Architecture for Hexapod Robot Locomotion

Randall D. Beer, Hillel J. Chiel, Roger D. Quinn, Kenneth S. Espenschied, Patrik Larsson
1992 Neural Computation  
We present a fully distributed neural network architecture for controlling the locomotion of a hexapod robot.  ...  In previous work , we described a neural network architecture for hexapod locomotion.  ...  For example, whenever a leg is lifted for some reason, it reflexively swings forward and whenever one leg swings forward, all other legs move backward slightly.  ... 
doi:10.1162/neco.1992.4.3.356 fatcat:sdjwyg6kuvcjlmz76yieovswda

Locomotion. Perception Driven Robot Locomotion

M. Anthony Lewis
2002 Journal of the Robotics Society of Japan  
Introduction Walking machine research spans about 40 years.  ...  However, the control system of a walking machine requires more than sensory information. Walking machines require perception.  ... 
doi:10.7210/jrsj.20.273 fatcat:2fgwczpcbjddpat3xywtrimkca

Dynamic Walking: A Step Forward? [chapter]

R. E. Reeve
1999 Advances in Intelligent Autonomous Systems  
_________________________ Beer and Gallagher evolved the parameters of a dynamic neural network to control a (statically stable) insect walking in simulation [7] .  ...  As many different forms of evolution have been tried as there are researchers, but generally they tend to evolve parameters for some kind of neural controller for the robot: normally the strengths of connections  ... 
doi:10.1007/978-94-011-4790-3_15 fatcat:li3jxoyzrbbihetiyp7b62ftza

Neuroethological Concepts and their Transfer to Walking Machines

Volker Dürr, André F. Krause, Josef Schmitz, Holk Cruse
2003 The international journal of robotics research  
A systems approach to animal motor behavior reveals concepts that can be useful for the pragmatic design of walking machines.  ...  KEY WORDS-artificial neural network, postural reflex,  ...  To date, a number of walking robots give evidence for this, because the rules that make insects walk (Cruse 1990 ; see Figure 4 (a)) make machines walk too.  ... 
doi:10.1177/0278364903022003002 fatcat:o36gh5tikzerfb64bdeifgpezu

Central pattern generators for locomotion control in animals and robots: A review

Auke Jan Ijspeert
2008 Neural Networks  
It will then cover how CPG models implemented as neural networks or systems of coupled oscillators can be used in robotics for controlling the locomotion of articulated robots.  ...  Finally, various methods for designing CPGs to control specific modes of locomotion will be briefly reviewed.  ...  For instance, when specific feet placements are required during walking (e.g. when a cat walks over a branch or when we cross a river walking on stones), rhythmic signals from the CPGs need to be modulated  ... 
doi:10.1016/j.neunet.2008.03.014 pmid:18555958 fatcat:fcfgpdv6vbeqroaygif3stowuq

An Interactively Constrained Neuro-Evolution Approach for Behavior Control of Complex Robots [chapter]

Christian Rempis, Frank Pasemann
2012 Variants of Evolutionary Algorithms for Real-World Applications  
The application of the ICONE method is demonstrated by evolving a walking behavior for a physical humanoid robot, for which a whole library of behaviors has been developed.  ...  This becomes even harder when functional recurrent network structures cannot be given in advance and have to be evolved together with other parameters like synaptic weights and bias terms.  ...  Thanks go to Verena Thomas, Ferry Bachmann, Robert Muil and Chris Reinke for contributions to the simulation environment, and to Tanya Beck for proofreading the chapter.  ... 
doi:10.1007/978-3-642-23424-8_10 fatcat:p2666rukavfpnf3kp6xgdltri4

Stance Control Inspired by Cerebellum Stabilizes Reflex-Based Locomotion on HyQ Robot [article]

Gabriel Urbain, Victor Barasuol, Claudio Semini, Joni Dambre and Francis wyffels
2020 arXiv   pre-print
At the same time, biological evidence has attested the functional role of the cerebellum for predictive control of balance and stance within mammals.  ...  An analysis of experimental results demonstrates that the most biologically plausible alternative also leads to better results for robust locomotion.  ...  The authors would also like to thank Shamel Fahmi for his help during the experiments and to process data.  ... 
arXiv:2003.09327v1 fatcat:afq63mjwwvbxrj73j27op2ro4a
« Previous Showing results 1 — 15 out of 1,167 results