Deriving neural network controllers from neuro-biological data: implementation of a single-leg stick insect controller

Abstract

This article presents modular recurrent neural network controllers for single legs of a biomimetic six-legged robot equipped with standard DC motors. Following arguments of Ekeberg et al. (Arthropod Struct Dev 33:287-300, 2004), completely decentralized and sensori-driven neuro-controllers were derived from neuro-biological data of stick-insects. Parameters of the controllers were either hand-tuned or optimized by an evolutionary algorithm. Employing identical controller structures, qualitatively similar behaviors were achieved for robot and for stick insect simulations. For a wide range of perturbing conditions, as for instance changing ground height or up- and downhill walking, swing as well as stance control were shown to be robust. Behavioral adaptations, like varying locomotion speeds, could be achieved by changes in neural parameters as well as by a mechanical coupling to the environment. To a large extent the simulated walking behavior matched biological data. For example, this was the case for body support force profiles and swing trajectories under varying ground heights. The results suggest that the single-leg controllers are suitable as modules for hexapod controllers, and they might therefore bridge morphological- and behavioral-based approaches to stick insect locomotion control.

Dominance of local sensory signals over inter-segmental effects in a motor system: experiments

“…Thus, we could convincingly reconfirm the existence of independent CPGs that are associated with the different joints, under conditions more closely related to actual walking. The strong impact of the CS signal on the CTr-joint CPG, moreover, supports the idea that coupling between CPGs of different leg joints in the stick insect can be mediated by sensory signals as suggested by recent experimental and modeling studies (Büsch-ges 2005; Daun-Gruhn 2011; Daun-Gruhn and Toth 2011; Ekeberg et al 2004;von Twickel et al 2011). Our findings imply that the different leg CPGs may be under varying degrees of inter-segmental and local influence.…”

“…These results give rise to the notion that sensory feedback signals play a pivotal role in coordinating the activity of CPGs of the leg joints to generate a functional stepping motor output in the single leg (for review see e.g., Büschges and Gruhn 2008;. This is supported by simulation studies showing that sensory feedback from the leg can serve inter-joint coordination within the single leg to produce functional stepping (Ekeberg et al 2004;von Twickel et al 2011). …”

A neuromechanical model explaining forward and backward stepping in the stick insect

“…Besides theoretical models on the coordination of multiple legs, which are based on behavioral data (Cruse 1990;Graham 1977;Wendler 1968), there exists a large number of models that are also based on neuronal networks controlling the mechanical movement of the extremities (e.g., Cruse et al 1998Cruse et al , 2000Dürr et al 2004;Schilling et al 2007;von Twickel et al 2011). The network models these studies employ consist of artificial neurons related only vaguely to their biological counterparts in the nervous system of insects (e.g., Cruse et al 1998Cruse et al , 2000Schilling et al 2007;von Twickel et al 2011).…”

“…In addition to these physical observations, a growing amount of theoretical work has been published over the years (e.g., based on behavioral studies and/or artificial neural networks Cruse 1990;Cruse and Bartling 1995;Cruse et al 1998Cruse et al , 2000Schilling et al 2007;Schumm and Cruse 2006). The knowledge gained in this field has been applied to robots that use biological principles of locomotion, which were deduced from the experimental and theoretical investigations (Dürr et al 2004;Ijspeert et al 2007;von Twickel et al 2011).…”

Bioartificial Brains and Mobile Robots

“…This has been shown by pioneer publications Shahaf and Marom, 2001;Martinoia et al, 2004), in which experiments have been performed with populations of neurons, micro-electrode arrays (MEAs) and then further extended to an actual neuro-robotic platform (Bakkum et al, 2007;Novellino et al, 2007) up to a neural inspired control in a biomimetic robot (von Twickel et al, 2011) and to a "ratcar" in which a vehicle is moved following electrophysiological signals extracted by the cortical motor area of a rat (Fukayama et al, 2010). Among the possible approaches related to the choice of the robotic platform and of the control system (artificial, bioartificial or biological), there are common issues that can be explored by means of this experimental paradigm, namely: (i) how to convey information to the brain and (ii) how to extract information from the brain.…”