Learning inverse kinematics

By Aaron D'Souza, Sethu Vijayakumar, Stefan Schaal. Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180), 2001

342 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Control and Systems Engineering, Pulmonary and Respiratory Medicine

View Paper: https://www.semanticscholar.org/paper/18b76ef9b4a3abcca14efcf0da16dc8ff3b1e12d

How researchers see this paper

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

In Biomedical Engineering

In Control and Systems Engineering

In Pulmonary and Respiratory Medicine

Citations in the corpus

Body schema acquisition through active learning (2010, methodology): “Many approaches address this problem with non-parametric methods [1], [2], [3] without relying on the actual geometry.”
Curiosity driven reinforcement learning for motion planning on humanoids (2014, methodology): “Some methods learn internal models, such as hand-eye motor maps (Nori et al., 2007), inverse kinematic mappings (D’Souza et al., 2001), and operational space control laws (Peters and Schaal, 2008), but these are not curiosity-driven.”
Discriminative and adaptive imitation in uni-manual and bi-manual tasks (2006, methodology): “Moreover, in order to deal with the non-linearity of the transformation, various methods based on multiple locally linear models have also been explored, using either neural networks [19] or regression techniques [11].”
Task-Specific Generalization of Discrete and Periodic Dynamic Movement Primitives (2010, background): “2These problems can be addressed by biasing [50] or re-weighting [51] the data.”
On-line regression algorithms for learning mechanical models of robots: A survey (2011, positive): “[32], an inverse kinematics model is learned with lwpr.”
Abstraction Levels for Robotic Imitation: Overview and Computational Approaches (2010, methodology): “Many different techniques can be used by the robot to learn about its own body [41, 84, 108, 129, 144].”
Model learning for robot control: a survey (2011, background): “These approaches additionally requires explorations in the data space, where the explorations can be performed in the input space (D’Souza et al. 2001) or the target space (Rolf et al.”
Computational approaches to motor learning by imitation. (2003, positive): “Task-level imitation requires prior knowledge of how a task-level command can be converted into a command in internal coordinates, a classic problem in control theory treated under the name of inverse kinematics (Baillieul & Martin 1990), but which has found several elegant solutions in neural compu”
Online Goal Babbling for rapid bootstrapping of inverse models in high dimensions (2011, background): “Goal-directed exploration has been part of many learning schemes for inverse models, but only been possible with prior knowledge [15], [16] or non goal-directed pre-training [17], [18].”
Visual learning by imitation with motor representations (2005, background): “In the work described in [4], the imitator can replicate both the demonstrator’s gestures and dynamics.”
Goal Babbling Permits Direct Learning of Inverse Kinematics (2010, background): “Despite being seemingly simple in terms of control, the earlierproposedmethodsforthelearningofadirectinversefunc-tion areeitherunplausiblefromadevelopmentalpointof vieworfailinthecaseofredundancy.”