A Kendama Learning Robot Based on Bi-directional Theory

By Hiroyuki Miyamoto, Stefan Schaal, F. Gandolfo, Hiroaki Gomi, Y. Koike, Rieko Osu, E. Nakano, Y. Wada, Mitsuo Kawato. 1996

How researchers see this paper

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

Citations in the corpus

Reinforcement learning in robotics: A survey (2013, background): “Miyamoto et al. (1996) optimized the position and timing of such via-points in order to learn a kendama task (a traditional Japanese toy similar to a ball in a cup).”
An Algorithmic Perspective on Imitation Learning (2018, methodology): “Inverse reinforcement learning has been used for tasks such as parsing sentences Neu and Szepesvári [2009], car driving Abbeel and Ng [2004], path planning Ratliff et al.”
Task-Relevant Adversarial Imitation Learning (2019, methodology): “The use of demonstrations to help agent training has been studied extensively in robotics [Bakker and Kuniyoshi, 1996, Kawato et al., 1994, Miyamoto et al., 1996] with approaches ranging from Q-learning [Schaal, 1997] to behavioral cloning (BC) [Pomerleau, 1989].”
Keyframe-based Learning from Demonstration (2012, methodology): “In the LfD setting, an earlier work [21] utilizes via-points, which are similar to keyframes.”
Learning tasks from a single demonstration (1997, methodology): “Using the same robot as the one used in this work, learning from demonstration was investigated by Kawato et al. (1994) and Miyamoto et al. (1996) .”
Learning to select and generalize striking movements in robot table tennis (2012, methodology): “To represent movement primitives such that they can adapt trajectories obtained by imitation learning, several methods have been suggested (Miyamoto et al. 1996; Ijspeert, Nakanishi, and Schaal 2002; Calinon, Guenter, and Billard 2007; Williams, Toussaint, and Storkey 2008).”
Learning from demonstration and adaptation of biped locomotion (2004, methodology): “Motivated by human’s capability of learning and imitating demonstrated movements of a teacher, imitation learning has been explored as an efficient method for motor learning in robots to accomplish desired movements [19–21].”
Task-Specific Generalization of Discrete and Periodic Dynamic Movement Primitives (2010, background): “the one utilized in [16] have been employed in robotics in many contexts [19], but their explicit dependency on time can be cumbersome [20].”
Trajectories and keyframes for kinesthetic teaching: A human-robot interaction perspective (2012, background): “In this paper, we explore the alternative of providing a sparse set of consecutive keyframes that achieve the skill when connected together.”
A unifying computational framework for motor control and social interaction. (2003, background): “It has been proposed that the CNS uses a modular approach in which multiple controllers coexist and are selected based on the movement context or state ( Jacobs et al. 1991; Narendra et al. 1995; Narendra & Balakrishnan 1997; Ghahramani & Wolpert 1997).”
Learning Attractor Landscapes for Learning Motor Primitives (2002, unknown): “Spline-based approaches [6] have a similar problem.”
Learning from Demonstration (1996, unknown): “In the context of human skill learning, teaching by showing was investigated by Kawato, Gandolfo , Gomi, & Wada (1994) and Miyamoto et al. (1996) for a complex manipulation task to be learned by an anthropomorphic robot arm.”
Policy Gradient Methods for Robotics (2006, background): “Spline-based trajectory planning is well-known in the robotics literature, see e.g., [43], [ 44 ].”
Imitation and Reinforcement Learning (2010, methodology): “[25], who used a 7 DoF anthropomorphic arm and recorded human”