Results 1  10
of
15
Goal Babbling Permits Direct Learning of Inverse Kinematics
 IEEE TRANSACTIONS ON AUTONOMOUS MENTAL DEVELOPMENT
, 2010
"... We present an approach to learn inverse kinematics of redundant systems without prior or expertknowledge. The method allows for an iterative bootstrapping and refinement of the inverse kinematics estimate. The essential novelty lies in a path based sampling approach: we generate trainig data along ..."
Abstract

Cited by 25 (6 self)
 Add to MetaCart
(Show Context)
We present an approach to learn inverse kinematics of redundant systems without prior or expertknowledge. The method allows for an iterative bootstrapping and refinement of the inverse kinematics estimate. The essential novelty lies in a path based sampling approach: we generate trainig data along pathes, which result from execution of the currently learned estimate along a desired path towards a goal. The information structure thereby induced enables an efficient detection and resolution of inconsistent samples solely from directly observable data. We derive and illustrate the exploration and learning process with a lowdimensional kinematic example that provides direct insight into the bootstrapping process. We further show that the method scales for high dimensional problems, such as the Honda humanoid robot or hyperredundant planar arms with up to 50 degrees of freedom.
Model Learning for Robot Control: A Survey
 COGNITIVE SCIENCE
"... Models are among the most essential tools in robotics, such as kinematics and dynamics models of the robot’s own body and controllable external objects. It is widely believed that intelligent mammals also rely on internal models in order to generate their actions. However, while classical robotics ..."
Abstract

Cited by 13 (1 self)
 Add to MetaCart
Models are among the most essential tools in robotics, such as kinematics and dynamics models of the robot’s own body and controllable external objects. It is widely believed that intelligent mammals also rely on internal models in order to generate their actions. However, while classical robotics relies on manually generated models that are based on human insights into physics, future autonomous, cognitive robots need to be able to automatically generate models that are based on information which is extracted from the data streams accessible to the robot. In this paper, we survey the progress in model learning with a strong focus on robot control on a kinematic as well as dynamical level. Here, a model describes essential information about the behavior of the environment and the influence of an agent on this environment. In the context of model based learning control, we view the model from three different perspectives. First, we need to study the different possible model learning architectures for robotics. Second, we discuss what kind of problems these architecture and the domain of robotics imply for the applicable learning methods. From this discussion, we deduce future directions of realtime learning algorithms. Third, we show where these scenarios have been used successfully in several case studies.
Reaching movement generation with a recurrent neural network based on learning inverse kinematics for the humanoid robot iCub
 IEEE CONF. HUMANOID ROBOTICS
, 2009
"... We introduce a novel control framework based on a recurrent neural network for reaching movement generation. The network first learns forward and inverse kinematics, i.e. to associate end effector coordinates with joint angles, by means of attractor states. Modulating the attractor states with the d ..."
Abstract

Cited by 8 (2 self)
 Add to MetaCart
We introduce a novel control framework based on a recurrent neural network for reaching movement generation. The network first learns forward and inverse kinematics, i.e. to associate end effector coordinates with joint angles, by means of attractor states. Modulating the attractor states with the desired target input allows generalization of the learned kinematics to a wide range of untrained target positions. Representing the static kinematic mapping within a dynamical system enables smooth trajectory generation by exploiting the transient network dynamics when approaching an attractor state. Efficient online learning and execution of the network makes the proposed approach realtime capable. We evaluate the network’s generalization abilities and controller properties systematically in a humanoid robot setting.
Learning Inverse Kinematics for PoseConstraint BiManual Movements
 INT. CONF. ON SIMULATION OF ADAPTIVE BEHAVIOR
, 2010
"... Abstract. We present a neural network approach to learn inverse kinematics of the humanoid robot ASIMO, where we focus on bimanual tool use. The learning copes with both the highly redundant inverse kinematics of ASIMO and the additional arbitrary constraint imposed by the tool that couples both ha ..."
Abstract

Cited by 2 (1 self)
 Add to MetaCart
(Show Context)
Abstract. We present a neural network approach to learn inverse kinematics of the humanoid robot ASIMO, where we focus on bimanual tool use. The learning copes with both the highly redundant inverse kinematics of ASIMO and the additional arbitrary constraint imposed by the tool that couples both hands. We show that this complex kinematics can be learned from few groundtruth examples using an efficient recurrent reservoir framework, which has been introduced previously for kinematics learning and movement generation. We analyze and quantify the network’s generalization for a given tool by means of reproducing the constraint in untrained target motions. 1
Learning Flexible Full Body Kinematics for Humanoid Tool Use
 LABRS
, 2010
"... We show that inverse kinematics of different tools can be efficiently learned with a single recurrent neural network. Our model exploits all upper body degrees of freedom of the Honda humanoid robot research platform. Both hands are controlled at the same time with parametrized tool geometry. We sho ..."
Abstract

Cited by 2 (2 self)
 Add to MetaCart
We show that inverse kinematics of different tools can be efficiently learned with a single recurrent neural network. Our model exploits all upper body degrees of freedom of the Honda humanoid robot research platform. Both hands are controlled at the same time with parametrized tool geometry. We show that generalization both in space as well as across tools is possible from very few training data. The network even permits extrapolation beyond the training data. For training we use an efficient online scheme for recurrent reservoir networks utilizing supervised backpropagationdecorrelation (BPDC) output adaptation and an unsupervised intrinsic plasticity (IP) reservoir optimization.
1 Kinematic Bézier Maps
"... Abstract — The kinematics of a robot with many degrees of freedom is a very complex function. Learning this function for a large workspace with a good precision requires a huge number of training samples, i.e., robot movements. In this work, we introduce the Kinematic Bézier Map (KBMap), a parametr ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
(Show Context)
Abstract — The kinematics of a robot with many degrees of freedom is a very complex function. Learning this function for a large workspace with a good precision requires a huge number of training samples, i.e., robot movements. In this work, we introduce the Kinematic Bézier Map (KBMap), a parametrizable model without the generality of other systems, but whose structure readily incorporates some of the geometric constraints of a kinematic function. In this way, the number of training samples required is drastically reduced. Moreover, the simplicity of the model reduces learning to solving a linear least squares problem. Systematic experiments have been carried out showing the excellent interpolation and extrapolation capabilities of KBMaps and their relatively low sensitivity to noise. Index Terms — Learning, robot kinematics, humanoid robots. I.
Mastering Growth while Bootstrapping Sensorimotor Coordination
 INT. CONF. ON EPIGENETIC ROBOTICS (EPIROB)
, 2010
"... The bodily change in infancy due to growth is a fundamental challenge for the bootstrapping of sensorimotor coordination. We argue that learning by doing, and thus a babbling of goals instead of motor commands provides an appealing explanation for the success of infants in that bootstrapping. We sho ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
(Show Context)
The bodily change in infancy due to growth is a fundamental challenge for the bootstrapping of sensorimotor coordination. We argue that learning by doing, and thus a babbling of goals instead of motor commands provides an appealing explanation for the success of infants in that bootstrapping. We show that Goal Babbling allows to bootstrap reaching skills during different growth patterns on a robot arm with five degrees of freedom and on the infant like humanoid iCub. 1.
CSICUPC, Barcelona
"... Abstract—The kinematics of a robot with many degrees of freedom is a very complex function. Learning this function for a large workspace with a good precision requires a huge number of training samples, i.e., robot movements. In this work, we introduce the Kinematic Bézier Map (KBMap), a parametri ..."
Abstract
 Add to MetaCart
(Show Context)
Abstract—The kinematics of a robot with many degrees of freedom is a very complex function. Learning this function for a large workspace with a good precision requires a huge number of training samples, i.e., robot movements. In this work, we introduce the Kinematic Bézier Map (KBMap), a parametrizable model without the generality of other systems, but whose structure readily incorporates some of the geometric constraints of a kinematic function. In this way, the number of training samples required is drastically reduced. Moreover, the simplicity of the model reduces learning to solving a linear least squares problem. Systematic experiments have been carried out showing the excellent interpolation and extrapolation capabilities of KBMaps and their relatively low sensitivity to noise. Index Terms—Learning, robot kinematics, humanoid robots. I.
Revision
, 2010
"... Comparative evaluation of approaches in T.4.14.3 and working definition of adaptive module Authors: ..."
Abstract
 Add to MetaCart
(Show Context)
Comparative evaluation of approaches in T.4.14.3 and working definition of adaptive module Authors:
Dissemination level
, 2011
"... Report on design and evaluation of robotic experimentation in scenario E2.1: combination of skills ..."
Abstract
 Add to MetaCart
(Show Context)
Report on design and evaluation of robotic experimentation in scenario E2.1: combination of skills