direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments

Roberto Martín-Martín

Lupe

Email: roberto.martinmartin(at)tu-berlin.de

Room: MAR 5.065
Telephone: +49.30.314-73118
Office Hours: on request

Research

In a (near) future I would like to see robots assisting and working autonomously in human environments. However, these environments are highly unpredictable and dynamic. My research interest is to provide robots with the necessary perceptual skills to understand and successfully manipulate these unstructured environments. I believe that the key to a successful understanding of the environment should include three factors: interaction with the world, continuous probabilistic (bayesian) estimation and learning and multimodal perception. By correctly combining these factors the robot can crack the complexity and variety of human environments.

My recent work applies these ideas to the robust perception of degrees of freedom in unstructured environments from interactions. This knowledge is crucial for robots interacting in our homes. Doors, drawers, or scissors are some examples of articulated objects with degrees of freedom that the robot would need to perceive and understand in order to successfully and purposely manipulate them.

Research interests: 

  • Active and Interactive Perception
  • Sensorimotor Contingencies
  • Bayesian State Estimation and Bayesian Exploration
  • Multimodal Perception and Control
  • Machine Learning

Google scholar

Vita

Publications

Clemens Eppner and Sebastian Höfer and Rico Jonschkowski and Roberto Martín-Martín and Arne Sieverling and Vincent Wall and Oliver Brock. Lessons from the Amazon Picking Challenge: Four Aspects of Building Robotic Systems. Proceedings of Robotics: Science and Systems, 2016.

Download Bibtex entry

Rico Jonschkowski and Clemens Eppner and Sebastian Höfer and Roberto Martín-Martín and Oliver Brock. Probabilistic Multi-Class Segmentation for the Amazon Picking Challenge. IEEE/RSJ International Conference on Intelligent Robots and Systems, 2016.

Download Bibtex entry

Dragoljub Surdilovic and Yelve Yakut and T-M. Nguyen and X. B. Pham and Axel Vick and Roberto Martín-Martín. Compliance Control with Dual-Arm Humanoid Robots: Design, Planning and Programming. Proceedings of the International Conference on Humanoid Robots, pp. 275-281, 2010.

Download Bibtex entry

Roberto Martín-Martín and Oliver Brock. Online Interactive Perception of Articulated Objects with Multi-Level Recursive Estimation Based on Task-Specific Priors. Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 2494-2501, 2014.

Download Bibtex entry

Roberto Martín-Martín and Oliver Brock. Deterioration of Depth Measurements due to Interference of Multiple RGB-D Sensors. Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 4205-4212, 2014.

Download Bibtex entry

Roberto Martín-Martín and Arne Sieverling and Oliver Brock. Estimating the Relation of Perception and Action During Interaction. International Workshop on Robotics in the 21st century: Challenges and Promises, 2016.

Download Bibtex entry

Roberto Martín-Martín and Oliver Brock. Building Kinematic and Dynamic Models of Articulated Objects with Multi-Modal Interactive Perception. AAAI Symposium on Interactive Multi-Sensory Object Perception for Embodied Agents 2017.

Download Bibtex entry

Roberto Martín-Martín and Sebastian Höfer and Oliver Brock. An Integrated Approach to Visual Perception of Articulated Objects. Proceedings of the IEEE International Conference on Robotics and Automation, pp. 5091 - 5097, 2016.

Download Bibtex entry

Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe

Auxiliary Functions

Administration

Janika Urig
Tel. +49 30 314-73 110
Fax +49 30 314-21 116
Raum MAR 5.032

Anschrift

TU Berlin
Fakultät IV
Sekretariat MAR 5-1
Marchstraße 23
10587 Berlin