Feathered Flyer: Integrating Morphological Computation and Sensory Reflexes into a Physically Simulated Flapping-Wing Robot for Robust Flight Manoeuvre

Shim, Yoonsik; Husbands, Phil

doi:10.1007/978-3-540-74913-4_76

Cited by 16 publications

(13 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This could represent a biological implementation of the filter bank of our proposed theoretical model. Remarkably, the resulting morphological computation has already been considered in Shim and Husbands (2007). They used nonlinear angular springs to simulate the distortions of the feathers and combined it with 9 As opposed to the recurrent networks as sketched in Fig.…”

Section: If There Is a Rich Enough Pool B Of Basis Filters (Timeinvarmentioning

confidence: 99%

See 1 more Smart Citation

Towards a theoretical foundation for morphological computation with compliant bodies

et al. 2011

View full text Add to dashboard Cite

The control of compliant robots is, due to their often nonlinear and complex dynamics, inherently difficult. The vision of morphological computation proposes to view these aspects not only as problems, but rather also as parts of the solution. Non-rigid body parts are not seen anymore as imperfect realizations of rigid body parts, but rather as potential computational resources. The applicability of this vision has already been demonstrated for a variety of complex robot control problems. Nevertheless, a theoretical basis for understanding the capabilities and limitations of morphological computation has been missing so far. We present a model for morphological computation with compliant bodies, where a precise mathematical characterization of the potential computational contribution of a complex physical body is feasible. The theory suggests that complexity and nonlinearity, typically unwanted properties of robots, are desired features in order to provide computational power. We demonstrate that simple generic models of physical bodies, based on mass-spring systems, can be used to implement complex nonlinear operators. By adding a simple readout (which is static and linear) to the morphology such devices are able to emulate complex mappings of input to output streams in continuous time. Hence, by outsourcing parts of the computation to the physical body, the difficult problem of learning to control a complex body, could be reduced to a simple and perspicuous learning task, which can not get stuck in local minima of an error function. Abstract The control of compliant robots is, due to their often nonlinear and complex dynamics, inherently difficult. The vision of morphological computation proposes to view these aspects not only as problems, but rather also as parts of the solution. Non-rigid body parts are not seen anymore as imperfect realizations of rigid body parts, but rather as potential computational resources. The applicability of this vision has already been demonstrated for a variety of complex robot control problems. Nevertheless, a theoretical basis for understanding the capabilities and limitations of morphological computation has been missing so far. We present a model for morphological computation with compliant bodies, where a precise mathematical characterization of the potential computational contribution of a complex physical body is feasible. The theory suggests that complexity and nonlinearity, typically unwanted properties of robots, are desired features in order to provide computational power. We demonstrate that simple generic models of physical bodies, based on mass-spring systems, can be used to implement complex nonlinear operators. By adding a simple readout (which is static and linear) to the morphology, such devices are able to emulate complex mappings of input to output streams in continuous time. Hence, by outsourcing parts of the computation to the physical body, the difficult problem of learning to control a complex body, could be reduced to a simple and perspicuous le...

show abstract

Section: If There Is a Rich Enough Pool B Of Basis Filters (Timeinvarmentioning

confidence: 99%

“…It exploits the dynamics between its physical body and its environment. In the physically more complex field of flying has also been demonstrated that morphological computation can play an important role, for example, to stabilize flight, e.g., Wood (2007) and Shim and Husbands (2007).…”

Section: Introductionmentioning

confidence: 99%

Towards a theoretical foundation for morphological computation with compliant bodies

et al. 2011

View full text Add to dashboard Cite

show abstract

“…For example, the simple quadruped robot Puppy by Iida and Pfeifer (2006) with a mixture of active and passive joints, the artificial fish "Wanda" by Ziegler et al (2006), or, in the context of the physically more complex field of flying, winged robots by Wood (2007) and Shim and Husbands (2007).…”

Section: Introductionmentioning

confidence: 99%

The role of feedback in morphological computation with compliant bodies

et al. 2012

View full text Add to dashboard Cite

The generation of robust periodic movements of complex nonlinear robotic systems is inherently difficult, especially, if parts of the robots are compliant. It has previously been proposed that complex nonlinear features of a robot, similarly as in biological organisms, might possibly facilitate its control. This bold hypothesis, commonly referred to as morphological computation, has recently received some theoretical support by Hauser et al. (Biol Cybern 105:355-370, doi:10.1007/s00422-012-0471-0, 2012. We show in this article that this theoretical support can be extended to cover not only the case of fading memory responses to external signals, but also the essential case of autonomous generation of adaptive periodic patterns, as, e.g., needed for locomotion. The theory predicts that feedback into the morphological computing system is necessary and sufficient for such tasks, for which a fading memory is insufficient. We demonstrate the viability of this theoretical analysis through computer simulations of complex nonlin- ear mass-spring systems that are trained to generate a large diversity of periodic movements by adapting the weights of a simple linear feedback device. Hence, the results of this article substantially enlarge the theoretically tractable application domain of morphological computation in robotics, and also provide new paradigms for understanding control principles of biological organisms.

show abstract

“…Since its publication, several researchers have implemented Sims' work in evolving both the creatures' morphology and its controller adopting different approaches [2][3][4][5][6][7]. However, reasonable amount of research focused on the evolution of controllers for physically modelled creatures with fixed morphologies that doesn' t change over the simulation [8][9][10] due to best exemplifY the natural evolution occurs in real creatures such as human, animals and insects which have bodies and are situated in physical environment where their skills and behavior are developed autonomously through direct interaction with their environment.…”

Section: Introductionmentioning

confidence: 99%

NEAT neural networks to control and simulate virtual creature's locomotion

Tibermacine

Djedi

2014

2014 International Conference on Multimedia Computing and Systems (ICMCS)

View full text Add to dashboard Cite

This paper presents the application of evolutionary computation techniques for evolving behaviorisms in virtual creatures existing within a realistic virtual environment that are subj ect of the constraints as defined by the Newtonian model of physics. Evolutionary computation technique uses NEAT's network that is based on three fundamental principles (Genetic Encoding with Historical Markings, Speciation and Minimizing Dimensionality). The creatures' morphology is completely predetermined and is designed to elicit a variety of locomotive behaviors and test the generalization abilities of our framework. Three different morphologies are introduced into the simulation; each morphology represents an entirely different species of virtual creatures. The experiments show that NEAT's network is able to generate efficient locomotive behaviors.

show abstract

Feathered Flyer: Integrating Morphological Computation and Sensory Reflexes into a Physically Simulated Flapping-Wing Robot for Robust Flight Manoeuvre

Cited by 16 publications

References 14 publications

Towards a theoretical foundation for morphological computation with compliant bodies

Towards a theoretical foundation for morphological computation with compliant bodies

The role of feedback in morphological computation with compliant bodies

NEAT neural networks to control and simulate virtual creature's locomotion

Contact Info

Product

Resources

About