A connectionist central pattern generator for the aquatic and terrestrial gaits of a simulated salamander

By Auke Jan Ijspeert. Biological cybernetics, 2001

384 citations recorded by the source corpus.

Subfields: Cell Biology, Cognitive Neuroscience, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/feb4ff376edcac2a9cadb933d7c6856e446809d8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cell Biology

In Cognitive Neuroscience

In Electrical and Electronic Engineering

Citations in the corpus

Adaptive Dynamic Walking of a Quadruped Robot on Irregular Terrain Based on Biological Concepts (2003, methodology): “…walking using a neural system model, including studies on dynamic walking in simulation (Taga, Yamaguchi, and Shimizu 1991; Taga 1995; Miyakoshi et al. 1998; Ijspeert 2001), and real robots (Kimura, Akiyama, and Sakurama 1999; Ilg et al. 1999; Tsujita, Tsuchiya, and Onat 2001; Lewis et al. 2003).”
From human to humanoid locomotion—an inverse optimal control approach (2010, background): “Ijspeert 2001 ) study natural motions on joint level.”
Contact-invariant optimization for hand manipulation (2012, background): “…is speciﬁc to trajectory optimization – as opposed to optimization of feed-back controllers which have dealt with contacts automatically [Sim94, Ijs01] but have other limitations including computationally-intensive optimization, poor local minima, and the need to guess a suitable controller…”
The Dynamics of Legged Locomotion: Models, Analyses, and Challenges (2006, background): “In the former papers, bodies composed of rigid links actuated by simplified spring/damper muscle models are used and the fluid environment is represented by empirical drag and lift forces applied along the body; a recent paper on salamander locomotion considers both aquatic and terrestrial gaits [18”
Adaptive Dynamic Walking of a Quadruped Robot on Natural Ground Based on Biological Concepts (2007, methodology): “…research in this area attempted to generate walking using a neural system model, including simulation studies of dynamic walking (Taga et al. 1991 Taga 1995 Ijspeert 2001 Tomita and Yano 2003) and real robots (Kimura et al. 1999, 2001 Berns et al. 1999 Tsujita et al. 2001 Lewis et al. 2003).”
AmphiBot I: an amphibious snake-like robot (2005, methodology): “• The current snake-like robot is a good base to build a salamander robot like those investigated in simulation in Ijspeert (2001).”
How the body shapes the way we think - a new view on intelligence (2006, background): “robots (Ayers 2004) at Northeastern University in Boston;Auke Ijspeert’s work on the simulated robot salamander at the Swiss Federal Institute of Technology in Lausanne, Switzerland (Ijspeert, 2001); the “artificial mouse” developed at the University of Zurich to investigate the role of whiskers in ”
Learning from demonstration and adaptation of biped locomotion (2004, background): “This kind of coupling is motivated from a biological point of view where it has been hypothesized that coupling among neural oscillators plays an important role in coordinating the desired phase relationship of limb movements in locomotion and gait transition [31].”
Learning to Control a 6-Degree-of-Freedom Walking Robot (2007, background): “Examples of these are studies on locomotion of dog-like robot [13], [14], [15], hexapod [16], salamander-like robot [17], or human-like biped [18], [11].”
Central pattern generators for locomotion control in animals and robots: A review (2008, methodology): “Ijspeert / Neural Networks 21 (2008) 642–653 643”
The evolvability of artificial neural net-works for robot control (2002, background): “Since then, a number of researchers have used CTRNNs for robot control, both in simulated and real environments (Ijspeert, 2001; Jakobi, 1998c; Beer and Gallagher, 1992; Beer et al., 1999; Chiel et al., 1999).”
Dynamical Movement Primitives: Learning Attractor Models for Motor Behaviors (2013, background): “Due to this lack of analytical tractability, some people have suggested recurrent neural network (Paine & Tani, 2004; Jaeger & Haas, 2004) or evolutionary methods (Ijspeert, Hallam, & Willshaw, 1999; Ijspeert, 2001) as a design strategy for nonlinear dynamical systems controllers.”