Header logo is


2014


no image
Haptic Robotization of Human Body via Data-Driven Vibrotactile Feedback

Kurihara, Y., Takei, S., Nakai, Y., Hachisu, T., Kuchenbecker, K. J., Kajimoto, H.

Entertainment Computing, 5(4):485-494, December 2014 (article)

hi

[BibTex]

2014


[BibTex]


no image
Modeling and Rendering Realistic Textures from Unconstrained Tool-Surface Interactions

Culbertson, H., Unwin, J., Kuchenbecker, K. J.

IEEE Transactions on Haptics, 7(3):381-292, July 2014 (article)

hi

[BibTex]

[BibTex]


no image
Teaching Forward and Inverse Kinematics of Robotic Manipulators Via MATLAB

Wong, D., Dames, P., J. Kuchenbecker, K.

June 2014, Presented at {\em ICRA Workshop on {MATLAB/Simulink} for Robotics Education and Research}. Oral presentation given by {Dames} and {Wong} (misc)

hi

[BibTex]

[BibTex]


no image
Control of a Virtual Robot with Fingertip Contact, Pressure, Vibrotactile, and Grip Force Feedback

Pierce, R. M., Fedalei, E. A., Kuchenbecker, K. J.

Hands-on demonstration presented at IEEE Haptics Symposium, Houston, Texas, USA, February 2014 (misc)

hi

[BibTex]

[BibTex]


no image
A Modular Tactile Motion Guidance System

Kuchenbecker, K. J., Anon, A. M., Barkin, T., deVillafranca, K., Lo, M.

Hands-on demonstration presented at IEEE Haptics Symposium, Houston, Texas, USA, February 2014 (misc)

hi

[BibTex]

[BibTex]


no image
The Penn Haptic Texture Toolkit

Culbertson, H., Delgado, J. J. L., Kuchenbecker, K. J.

Hands-on demonstration presented at IEEE Haptics Symposium, Houston, Texas, USA, February 2014 (misc)

hi

[BibTex]

[BibTex]


no image
Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers

Rolinek, M., Swoboda, P., Zietlow, D., Paulus, A., Musil, V., Martius, G.

Arxiv (article)

Abstract
Building on recent progress at the intersection of combinatorial optimization and deep learning, we propose an end-to-end trainable architecture for deep graph matching that contains unmodified combinatorial solvers. Using the presence of heavily optimized combinatorial solvers together with some improvements in architecture design, we advance state-of-the-art on deep graph matching benchmarks for keypoint correspondence. In addition, we highlight the conceptual advantages of incorporating solvers into deep learning architectures, such as the possibility of post-processing with a strong multi-graph matching solver or the indifference to changes in the training setting. Finally, we propose two new challenging experimental setups

al

Arxiv [BibTex]