Show filters Hide filters

Refine your search

Publication Year
Publisher
1-15 out of 15 results
Change view
  • Sort by:
15:09 Hochschule Ravensburg-Weingarten German 2014

Institute for Artificial Intelligence (IKI) profile video

Intelligent programs, machines or robots must have the ability to learn like humans. The study of this fascinating problem on real world applications is the job of the IKI. The IKI with Prof. Dr. Wolfgang Ertel as it's head has over 20 years of experience with applications of machine learning in a lot of different areas like medicine, mechanical engineering, robotics, web-applications and e-business.
  • Published: 2014
  • Publisher: Hochschule Ravensburg-Weingarten
  • Language: German
01:50 Hochschule Ravensburg-Weingarten Silent film 2011

Learning from Demonstration - Stacking objects by color (reproduction)

Learning and Application of High-Level Concepts with Conceptual Spaces and PDDL. In Proc. of the 3rd Wokshop on Planning and Learning (PAL), ICAPS 2011, Freiburg, Germany.
  • Published: 2011
  • Publisher: Hochschule Ravensburg-Weingarten
  • Language: Silent film
03:20 Hochschule Ravensburg-Weingarten No linguistic content; Not applicable 2012

Abschlußrennen der Veranstaltung "Künstliche Intelligenz Light"

Das Abschlußrennen der Veranstaltung "Künstliche Intelligenz Light" an der Hochschule Weingarten-Ravensburg. Das Rennen fand am 26.10.2012 statt.
  • Published: 2012
  • Publisher: Hochschule Ravensburg-Weingarten
  • Language: No linguistic content; Not applicable
03:45 Hochschule Ravensburg-Weingarten Silent film 2015

High-Level Learning from Demonstration

A human demonstrates pick&place tasks, the robot applies learned tasks to new situations.
  • Published: 2015
  • Publisher: Hochschule Ravensburg-Weingarten
  • Language: Silent film
02:06 Hochschule Ravensburg-Weingarten Silent film 2012

Dice Detection

A KR 5 SIXX Robot (KUKA) uses a webcam to recognize dices. After a dice is detected the robots points to the object. The image recognition is done on a separate PC. You can see the GUI of the software on the screen next to the robot. The robot and the PC communicate by using an OPC server.
  • Published: 2012
  • Publisher: Hochschule Ravensburg-Weingarten
  • Language: Silent film
00:31 Hochschule Ravensburg-Weingarten Silent film 2011

Learning from Demonstration - Sorting objects by shape (demonstration)

Learning and Application of High-Level Concepts with Conceptual Spaces and PDDL. In Proc. of the 3rd Wokshop on Planning and Learning (PAL), ICAPS 2011, Freiburg, Germany. Sorting objects by shape into specific pallets (demonstration phase)
  • Published: 2011
  • Publisher: Hochschule Ravensburg-Weingarten
  • Language: Silent film
04:04 Hochschule Ravensburg-Weingarten English 2010

Learning from Demonstration - Cube into Cup

Robot Learning by Demonstration with Local Gaussian Process Regression. In Proc. 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, Taipeh, Taiwan, 2010. Learning from Demonstration using a Katana robotic manipulator. Note that in each demonstration the objects' positions change. Learning means to generalize from these training samples to an arbitrary new situation where all the objects can be located at different positions. In the reproduction, the manipulator's trajectory is computed based on the constraints extracted from the recorded demonstrations. Unlike in classical teach-in approaches, this method is able to deal with changing objects' positions.
  • Published: 2010
  • Publisher: Hochschule Ravensburg-Weingarten
  • Language: English
05:18 Hochschule Ravensburg-Weingarten English 2012

Robot Learning from Demonstration by Averaging Trajectories - Pouring into the Cup

Learning from Demonstration by Averaging Trajectories (LAT) has been implemented using a Katana robotic manipulator. LAT works in three phases: Demonstration: Repeated recording of trajectories and detection of involved objects (located at changing positions). Generalisation: Creation of a continuos behaviour model on trajectory level for each object involved. Reproduction: Fusion of the models, adapted to an arbitrary new situation where all the objects again can be located at different positions.
  • Published: 2012
  • Publisher: Hochschule Ravensburg-Weingarten
  • Language: English
05:40 Hochschule Ravensburg-Weingarten English 2010

Learning from Demonstration - Make Coffee

Robot Learning by Demonstration with Local Gaussian Process Regression. In Proc. 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, Taipeh, Taiwan, 2010. Learning from Demonstration using a Katana robotic manipulator. Note that in each demonstration the objects' positions change. Learning means to generalize from these training samples to an arbitrary new situation where all the objects can be located at different positions. In the reproduction, the manipulator's trajectory is computed based on the constraints extracted from the recorded demonstrations. Unlike in classical teach-in approaches, this method is able to deal with changing objects' positions.
  • Published: 2010
  • Publisher: Hochschule Ravensburg-Weingarten
  • Language: English
02:19 Hochschule Ravensburg-Weingarten Silent film 2011

Learning from Demonstration - Sorting objects by shape (reproduction)

Learning and Application of High-Level Concepts with Conceptual Spaces and PDDL. In Proc. of the 3rd Wokshop on Planning and Learning (PAL), ICAPS 2011, Freiburg, Germany. Sorting objects by shape into specific pallets (reproduction phase)
  • Published: 2011
  • Publisher: Hochschule Ravensburg-Weingarten
  • Language: Silent film
00:33 Hochschule Ravensburg-Weingarten Silent film 2011

Learning from Demonstration - Stacking objects by color (demonstration)

Learning and Application of High-Level Concepts with Conceptual Spaces and PDDL. In Proc. of the 3rd Wokshop on Planning and Learning (PAL), ICAPS 2011, Freiburg, Germany.
  • Published: 2011
  • Publisher: Hochschule Ravensburg-Weingarten
  • Language: Silent film
01:51 Hochschule Ravensburg-Weingarten Silent film 2010

Learning from Demonstration

Robot Learning by Demonstration with Local Gaussian Process Regression. In Proc. 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, Taipeh, Taiwan, 2010. Learning from Demonstration using a Katana robotic manipulator. Objects' positions were recorded before demonstrations and reproduction, respectively. Note that in each demonstration the objects' positions change. In the reproduction, the manipulator's trajectory is computed based on the constraints extracted from the recorded demonstrations.
  • Published: 2010
  • Publisher: Hochschule Ravensburg-Weingarten
  • Language: Silent film
02:57 Hochschule Ravensburg-Weingarten Original sound, no spoken text 2014

Robot Learning from Demonstration by Averaging Trajectories - Making Coffee

Learning from Demonstration by Averaging Trajectories (LAT) has been implemented using a Katana robotic manipulator. It uses the ROS operating system.
  • Published: 2014
  • Publisher: Hochschule Ravensburg-Weingarten
  • Language: Original sound, no spoken text
02:15 Hochschule Ravensburg-Weingarten English 2012

Robust Multi-Algorithm Object Recognition Using Machine Learning Methods

Object recognition in a household environment performed by a service robot. The objects are recognized by shape, texture and color-based algorithms whose outputs are then combined to create an object hypothesis. This works score-based, meaning that arbitrary algorithms and recognition frameworks can be combined without changing their outputs. In contrary to similar approaches, the proposed method automatically selects which algorithms to use and how to weigh their outputs. Reference: T. Fromm, B. Staehle, W. Ertel: Robust Multi-Algorithm Object Recognition Using Machine Learning Methods. IEEE International Conference on Multisensor Fusion and Information Integration, Hamburg, Germany, 2012.
  • Published: 2012
  • Publisher: Hochschule Ravensburg-Weingarten
  • Language: English
05:21 Hochschule Ravensburg-Weingarten English 2012

Robot Learning from Demonstration by Averaging Trajectories - Put the Can into the Cup

Learning from Demonstration by Averaging Trajectories (LAT) has been implemented using a Katana robotic manipulator. LAT works in three phases: Demonstration: Repeated recording of trajectories and detection of involved objects (located at changing positions). Generalisation: Creation of a continuos behaviour model on trajectory level for each object involved. Reproduction: Fusion of the models, adapted to an arbitrary new situation where all the objects again can be located at different positions.
  • Published: 2012
  • Publisher: Hochschule Ravensburg-Weingarten
  • Language: English
out of 1 pages
Loading...
Feedback

Timings

   55 ms - page object
   18 ms - search
    1 ms - highlighting
    1 ms - highlighting/30623
    1 ms - highlighting/30619
    1 ms - highlighting/30632
    0 ms - highlighting/30631
    0 ms - highlighting/30628
    0 ms - highlighting/30627
    0 ms - highlighting/30629
    0 ms - highlighting/30624
    0 ms - highlighting/30620
    0 ms - highlighting/30630
    0 ms - highlighting/30626
    0 ms - highlighting/30622
    0 ms - highlighting/30625
    0 ms - highlighting/30618
    0 ms - highlighting/30621

Version

AV-Portal 3.7.0 (943df4b4639bec127ddc6b93adb0c7d8d995f77c)