Header logo is


2011


no image
Optimal Reinforcement Learning for Gaussian Systems

Hennig, P.

In Advances in Neural Information Processing Systems 24, pages: 325-333, (Editors: J Shawe-Taylor and RS Zemel and P Bartlett and F Pereira and KQ Weinberger), Twenty-Fifth Annual Conference on Neural Information Processing Systems (NIPS), 2011 (inproceedings)

Abstract
The exploration-exploitation trade-off is among the central challenges of reinforcement learning. The optimal Bayesian solution is intractable in general. This paper studies to what extent analytic statements about optimal learning are possible if all beliefs are Gaussian processes. A first order approximation of learning of both loss and dynamics, for nonlinear, time-varying systems in continuous time and space, subject to a relatively weak restriction on the dynamics, is described by an infinite-dimensional partial differential equation. An approximate finitedimensional projection gives an impression for how this result may be helpful.

ei pn

PDF Web [BibTex]

2011


PDF Web [BibTex]


no image
Following human guidance to cooperatively carry a large object

Stueckler, J., Behnke, S.

In Proc. of the 11th IEEE-RAS Int. Conf. on Humanoid Robots (Humanoids), pages: 218-223, October 2011 (inproceedings)

ev

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Real-Time 3D Perception and Efficient Grasp Planning for Everyday Manipulation Tasks.

Stueckler, J., Steffens, R., Holz, D., Behnke, S.

In Proc. of the European Conf. on Mobile Robots (ECMR), pages: 177-182, 2011 (inproceedings)

ev

link (url) [BibTex]

link (url) [BibTex]


no image
Towards joint attention for a domestic service robot - person awareness and gesture recognition using Time-of-Flight cameras

Droeschel, D., Stueckler, J., Holz, D., Behnke, S.

In Proc. of the IEEE Int. Conf. on Robotics and Automation (ICRA), pages: 1205-1210, May 2011 (inproceedings)

ev

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Compliant Task-Space Control with Back-Drivable Servo Actuators

Stueckler, J., Behnke, S.

In RoboCup, 7416, pages: 78-89, Lecture Notes in Computer Science, Springer, 2011 (inproceedings)

ev

link (url) [BibTex]

link (url) [BibTex]


no image
Interest point detection in depth images through scale-space surface analysis

Stueckler, J., Behnke, S.

In Proc. of the IEEE Int. Conf. on Robotics and Automation (ICRA), pages: 3568-3574, May 2011 (inproceedings)

ev

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Learning to Interpret Pointing Gestures with a Time-of-flight Camera

Droeschel, D., Stueckler, J., Behnke, S.

In Proceedings of the 6th International Conference on Human-robot Interaction, pages: 481-488, ACM, 2011 (inproceedings)

ev

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Efficient Multi-resolution Plane Segmentation of 3D Point Clouds

Oehler, B., Stueckler, J., Welle, J., Schulz, D., Behnke, S.

In Proc. of the Int. Conf. on Intelligent Robotics and Applications (ICIRA), 7102, pages: 145-156, Lecture Notes in Computer Science, Springer Berlin Heidelberg, 2011 (inproceedings)

ev

link (url) DOI [BibTex]

link (url) DOI [BibTex]

2008


no image
In-lane Localization in Road Networks using Curbs Detected in Omnidirectional Height Images

Stueckler, J., Schulz, H., Behnke, S.

In Proceedings of Robotik 2008, 2008 (inproceedings)

ev

link (url) [BibTex]

2008


link (url) [BibTex]


no image
Orthogonal wall correction for visual motion estimation

Stueckler, J., Behnke, S.

In Proc. of the IEEE Int. Conf. on Robotics and Automation (ICRA), pages: 1-6, May 2008 (inproceedings)

ev

link (url) DOI [BibTex]

link (url) DOI [BibTex]

2007


no image
Hierarchical reactive control for a team of humanoid soccer robots

Behnke, S., Stueckler, J., Schreiber, M., Schulz, H., Böhnert, M., Meier, K.

In Proc. of the IEEE-RAS Int. Conf. on Humanoid Robots (Humanoids), pages: 622-629, November 2007 (inproceedings)

ev

link (url) DOI [BibTex]

2007


link (url) DOI [BibTex]