Quick links
Robot Basketball: Ball Dribbling with a Rigid End Effector
This video shows vision based ball dribbling with an industrial six DOF robot. Based on the visual information the ball trajectory is predicted and the robot trajectory is generated.
size: 448KB ; date: 20.10.2008
ROBOT BASKETBALL: NONPREHENSILE BALL CATCHING
The video shows the nonprehensile catching of a basketball with a six DOF industrial robot. Depending on the predicted ball trajectory, the robot performs either a direct or an indirect catching action.
ROBOT BASKETBALL: BALL DRIBBLING WITH A COMPLIANT END EFFECTOR*
The video shows ball dribbling with a compliant end effector design. In comparison to the rigid end effector design, the elastic element offers a number of benefits: First, a continuous-time control phase is established which facilitates the task execution. Second, the mechanical load for the manipulator is reduced by avoiding instantaneous impacts between manipulator and ball. Third, the actuator requirements are relaxed as kinetic energy can be transformed into potential energy of the spring.
*Cooperation with Dr. Uwe Mettin and Prof. Anton Shiriaev, Department of Engineering Cybernetics, Norwegian University of Science and Technology, NO-7491 Trondheim, Norway.
Reactive Collision Avoidance based on Inevitable Collision States
This video shows the novel reactive collision avoidance algorithm based on the Inevitable Collision State concept. It was published at IROS 2011 in San Francisco.
The corresponding paper can be found in the publication list:
size:83.6MB ; date:21.09.2011
MuJoA - Reactive Collision Avoidance
This video shows the reactive collision avoidance algorithm developed for omnidirectional driven robots. It was published at ICRA 2011 in Shanghai.
The corresponding paper can be found in the publication list:
size:45.9MB ; date:03.05.2011
MuJoA - Robot-Robot and Robot-Human Handover
This video shows the latest MuJoA demonstrator scenario involving two robots: Vicky places an order for a drink in an interactive dialogue with one of the robotic agents (the waiter). A second agent (the bartender) provides the waiter with the requested drink. Finally, the waiter hands the ordered drink to Vicky. While the agents are performing, the process of task decomposition and distribution among the two robotic agents is visualized.
size:11.3MB ; date:15.01.2010
MuJoA - Multi Joint Action
This video shows a brief hardware overview of the MuRoLa demonstrator, followed by an ordering scenario: 'Bring me an item!' In a first phase, the robotic agent receives the task from the human in a multimodal dialogue conducted via speech and headgestures. In a second phase, the task division and execution is performed. The work shown in this video is done in collaboration with the MuJoA project partners.
size:14.3MB ; date:04.03.2009
ACE - Das Autonomous City Explorer Projekt
In diesem Video wird das ACE projekt vorgestellt, dessen Ziel es war, einen Roboter zu erschaffen, der alleine durch eine unbekannte stadtische Umgebung fahren soll.
Dabei stehen dem Roboter weder ein Stadtplan noch ein ein GPS Gerät zur Verfügen. Er muss daher alleine dadurch von der Technischen Universität München zum Marienplatz finden, dass er Passanten nach dem Weg fragt.
Das Video erläutert die Probleme und deren Lösungen in den Bereichen der Navigation, Pfadplanung, Bildverarbeitung, Gestenerkennung und der Mensch-Roboter-Kommunikation.
size:7.83MB ; date:07.11.2008
ACE - The Autonomous City Explorer Project
In this video we present the Autonomous City ExplorerACE project. Its goal was to create a robot capable of navigating unknown urban environments without the use of GPS data or prior map knowledge. The robot had to find its way from the university campus to the town square of Munich solely by interacting with pedestrians and building a topological representation of its surroudings.
This video shows necessary ingredients for successfull low-level navigation on sidewalks, human detection and tracking, information retrieval from pedestrians as well as the construction of a semantic representation of an urban environment.
size: 7.47MB ; date: 02.10.2008
From Karlsplatz to Marienplatz-Part1
This video shows a field test of the Autonomous City Explorer (ACE) finding its way through the pedestrian area in the center of Munich. Ace navigates without GPS and map information, such that it has to find its way to Marienplatz by interacting with pedestrians.
SIZE:14.1MB ; DATE:31.07.2008
From Karlsplatz to Marienplatz-Part2
This video shows a field test of the Autonomous City Explorer (ACE) finding its way through the pedestrian area in the center of Munich. Ace navigates without GPS and map information, such that it has to find its way to Marienplatz by interacting with pedestrians.
SIZE:19.9MB ; DATE:31.07.2008
QC-Tracking_high
In order to determine and to control the absolute position as well as the heading of a quadrotor, a cost effective and easy-to-use tracking system is developed due to sensor drift of inertial sensors and integration errors. LEDs of different colors are used as markers in order to improve robustness towards disturbances.
size:5.39MB ; date:26.08.2008
BARt Test
size:11.5MB ; date:11.10.2007
Exp BARt LSR Step
size:14.9MB ; date:11.10.2007
ViGWaM
size:1.16MB ; date:16.11.2007