Embodied Symbol Emergence Based on Mimesis Theory

By Tetsunari Inamura, I. Toshima, H. Tanie, Yoshihiko Nakamura. Int. J. Robotics Res., 2004

366 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Social Psychology

View Paper: https://www.semanticscholar.org/paper/7b06d089fd0bc1c4cf10363de51bd416108f9336

How researchers see this paper

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

In Cognitive Neuroscience

In Social Psychology

Citations in the corpus

Task-Specific Generalization of Discrete and Periodic Dynamic Movement Primitives (2010, methodology): “It has been shown that HMMs can be used effectively for motion and action recognition [23] and”
Movement segmentation using a primitive library (2011, background): “A significant amount of previous work in the literature tries to segment human movement into such movement primitives, e.g., with statistical methods [3], [4].”
A tutorial on task-parameterized movement learning and retrieval (2015, background): “An alternative way of handling task-parameterized movements is to fit a model to each demonstration and associate it with a task-specific feature, goal, style variable or perceptual feedback, see, for example, [21,29,44,48,51,60,97].”
Incremental Learning, Clustering and Hierarchy Formation of Whole Body Motion Patterns using Adaptive Hidden Markov Chains (2008, methodology): “Several different techniques have been applied to the modeling the motion primitives, including dynamical models (Nakanishi et al. 2004), neural networks (Ogata et al. 2005), and stochastic models (Inamura et al. 2004 Billard et al. 2006 Taylor et al. 2006).”
On improving the extrapolation capability of task-parameterized movement models (2013, background): “, Gaussian process with trajectory models database) [4], [6]–[11];”
Humanoid Robot's Autonomous Acquisition of Proto-Symbols through Motion Segmentation (2006, methodology): “A set of parameters for an HMM is defined as a proto symbol and a scheme to configure a proto symbol space based on degree of dissimilarities among HMMs has been proposed in [10][11], where the sample motions were manually segmented into individual behaviors before optimizing the parameters of the H”
Incremental learning of full body motion primitives and their sequencing through human motion observation (2012, methodology): “…networks (Ogata et al. 2005; Erlhagen et al. 2006; Ito and Tani 2004; Andry et al. 2004), stochastic models such as hidden Markov models (HMMs) (Inamura et al. 2004; Takano et al. 2006, 2005; Billard et al. 2006, 2004; Asfour et al. 2006), phase oscillators for rhythmic motions (Nakanishi et…”
An Algorithmic Perspective on Imitation Learning (2018, methodology): “(3.21) In the framework in [Inamura et al., 2004], HMMs are used to represent primitive motions.”
Dynamical System Modulation for Robot Learning via Kinesthetic Demonstrations (2008, methodology): “2006703 process latent variable model (GPLVM) [11], spatiotemporal isomap (ST-Isomap) [12]) or some probabilistic model like hidden Markov models (HMMs) [13] or Bayesian networks [14].”