Body Schema Learning

@inproceedings{Sturm2012BodySL,
  title={Body Schema Learning},
  author={J{\"u}rgen Sturm and Christian Plagemann and Wolfram Burgard},
  booktitle={Towards Service Robots for Everyday Environments},
  year={2012}
}
Kinematic models are widely used in robotics to describe the mechanism of a robot. For example, the kinematic model of a manipulation robot is typically specified by the position of its joints, and the size and orientation of its links (Craig, 1989; Sciavicco and Siciliano, 2000). Kinematic models are usually derived analytically by a robot engineer and thus rely heavily on prior knowledge about the geometry of the robot. When such a model is applied to a real robot, its parameters have to be… 

Bootstrapping bilinear models of Simple Vehicles

TLDR
This is the first instance of a bootstrapping agent that can learn the model of the dynamics of a relatively large universe of systems and use the models to solve well-defined tasks, with no parameter tuning or hand-designed features.

Sensorimotor Learning for an Artificial Body Schema on Humanoid Robots

zur Erlangung des akademischen Grades eines Doktors der Ingenieurwissenschaften der Fakultat fur Informatik des Karlsruher Instituts fur Technologie (KIT).

Robot End Effector Tracking Using Predictive Multisensory Integration

TLDR
A biologically inspired model that enables a humanoid robot to learn how to track its end effector by integrating visual and proprioceptive cues as it interacts with the environment is proposed, which has properties that are qualitatively similar to the characteristics of human eye-hand coordination.

References

SHOWING 1-10 OF 47 REFERENCES

Automated Synthesis of Body Schema using Multiple Sensor Modalities

TLDR
This paper presents a method that allows a physical robot to automatically synthesize a body schema, using multimodal sensor data that it obtains through interaction with the real world, and refers to this method as the estimation-exploration algorithm, or EEA: the EEA is a co-evolutionary algorithm that maintains populations of models and populations of tests.

Learning omnidirectional path following using dimensionality reduction

TLDR
A method is proposed that uses a (possibly inaccurate) simulator to identify a low-dimensional subspace of policies that spans the variations in model dynamics that can be learned on the real system using much less data than would be required to learn a policy in the original class.

An Automated Method to Calibrate Industrial Robots Using a Virtual Closed Kinematic Chain

TLDR
The resolution of observations is improved, increasing the accuracy of joint angle measurements that are required to calibrate the robot, and it is shown in simulation that the method can be automated by a feedback system that can be implemented in real time.

Learning inverse kinematics

  • Aaron D'SouzaS. VijayakumarS. Schaal
  • Mathematics
    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
TLDR
This paper investigates inverse kinematics learning for resolved motion rate control (RMRC) employing an optimization criterion to resolve kinematic redundancies and demonstrates how a recently developed statistical learning algorithm, locally weighted projection regression, allows efficient learning of inverse k Cinematic mappings in an incremental fashion even when input spaces become rather high dimensional.

Calibrating a Multi-arm Multi-sensor Robot: A Bundle Adjustment Approach

TLDR
An extendable framework that combines measurements from the robot's various sensors (proprioceptive and external) to calibrate the robot’s joint offsets and external sensor locations is proposed, allowing sensors with very different error characteristics to be used side by side in the calibration.

Body Schema in Robotics: A Review

TLDR
The body representations in biology is surveyed from a functional or computational perspective to set ground for a review of the concept of body schema in robotics and identifies trends in these research areas and proposes future research directions.

Efficient exploration and learning of whole body kinematics

TLDR
The exploration process - though not yet fully autonomous - clearly shows that goal-directed exploration can be done very efficiently even for many degrees of freedom and non-linear kinematic configurations as ASIMOs, and provides a fundamental prerequisite for an autonomous and incremental motor learning in an developmentally plausible way.

Adaptive body schema for robotic tool-use

TLDR
It is argued that the temporal integration of multisensory information is a plausible candidate mechanism to explain how manipulated objects can become incorporated into the body schema and suggests that synthetic modeling might not only be a valid avenue towards getting a better grasp on results provided by neuropsychology and neurophysiology, but also a powerful approach for building advanced tool-using robots.

A Bayesian Approach to Nonlinear Parameter Identification for Rigid Body Dynamics

TLDR
This paper develops a Bayesian parameter identification method that can automatically detect noise in both input and output data for the regression algorithm that performs system identification and ensures physically consistent rigid body parameters by nonlinearly projecting the result of the Bayesian estimation onto constraints given by positive definite inertia matrices and the parallel axis theorem.

Learning Forward Models for Robots

TLDR
A system whereby forward models can be learnt and represented as a Bayesian network is described, which can be used by the robot to imitate human movement.