Ingo Ahrns - Academia.edu (original) (raw)

Papers by Ingo Ahrns

Lecture Notes in Computer Science, 2002

Traditionally, feature extraction and correspondence determination are handled separately in moti... more Traditionally, feature extraction and correspondence determination are handled separately in motion analysis of (range) image sequences. The correspondence determination methods have typically an exponential computational complexity. In the present paper we introduce a novel framework of motion analysis that unifies feature extraction and correspondence determination in a single process. Under the basic assumption of a small relative motion between the camera and the scene, feature extraction is solved by refining the segmentation result of the previous frame. This way correspondence information becomes directly available as a by-product of the feature extraction process. Due to the coupled processing of frames we also enforce some degree of segmentation stability. First results on real range image sequences have demonstrated the potential of our approach.

Proceedings Cvpr Ieee Computer Society Conference on Computer Vision and Pattern Recognition Ieee Computer Society Conference on Computer Vision and Pattern Recognition, Feb 1, 1999

ABSTRACT

Icann, 1995

Abstract Dynamic Cell Structures (DCS) belong to the class of topology representing networks rece... more Abstract Dynamic Cell Structures (DCS) belong to the class of topology representing networks recently introduced by Ma94]. DCS networks rest upon radial basis function networks (RBF) and an additional lateral connection structure between the neural units. ...

Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170), 2000

ABSTRACT

Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149), 2000

ABSTRACT

Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062), 2000

ABSTRACT Traditionally, feature extraction and correspondence determination are handled separatel... more ABSTRACT Traditionally, feature extraction and correspondence determination are handled separately in motion analysis of (range) image sequences. The correspondence determination methods have typically an exponential computational complexity. We introduce a novel framework of motion analysis that unifies feature extraction and correspondence determination in a single process. Under the basic assumption of a small relative motion between the camera and the scene, feature extraction is solved by refining the segmentation result of the previous frame. In this way, correspondence information becomes directly available as a by-product of the feature extraction process. Due to the coupled processing of frames, we also force some degree of segmentation stability. First results on real range image sequences have demonstrated the potential of our approach

Lecture Notes in Computer Science, 2002

Traditionally, feature extraction and correspondence determination are handled separately in moti... more Traditionally, feature extraction and correspondence determination are handled separately in motion analysis of (range) image sequences. The correspondence determination methods have typically an exponential computational complexity. In the present paper we introduce a novel framework of motion analysis that unifies feature extraction and correspondence determination in a single process. Under the basic assumption of a small relative motion between the camera and the scene, feature extraction is solved by refining the segmentation result of the previous frame. This way correspondence information becomes directly available as a by-product of the feature extraction process. Due to the coupled processing of frames we also enforce some degree of segmentation stability. First results on real range image sequences have demonstrated the potential of our approach.

2009 Asme Iftomm International Conference on Reconfigurable Mechanisms and Robots, Jun 22, 2009

In the project LUNARES (LUNAR Exploration Szenario), a technology demonstration of reconfigurable... more In the project LUNARES (LUNAR Exploration Szenario), a technology demonstration of reconfigurable cooperating robots in extraterrestrial sample return missions is implemented using state-of-the-art robotic technologies. A reconfigurable robot team consisting of a lander equipped with a manipulator, a rover, and a climbing robot is tested and demonstrated in a lunar crater test environment at the DFKI Laboratories. The aim is

There are few existing robots that perform exploratory tasks in extraterrestrial areas, namely Ma... more There are few existing robots that perform exploratory tasks in extraterrestrial areas, namely Mars or Moon. To use these robots efficiently, they can perform certain tasks autonomously. However, no system taking advantage of cooperative behaviour has yet been deployed. In this paper we present and evaluate two scenarios for cooperation in a space mission: (1) a wheeled rover and a legged robot performing a semi-automated docking task in order to improve general reach of the combined system, (2) a lander guiding a wheeled rover to its docking position.

Studies in Fuzziness and Soft Computing, 1998

... Computer Science Institute Daimler-Benz AG Christian-Albrechts-Ulm, Germany University Kiel, ... more ... Computer Science Institute Daimler-Benz AG Christian-Albrechts-Ulm, Germany University Kiel, Germany G. Hailu G. Sommer Computer Science Institute ... This leads to the definition of the induced Delaunay triangulation or perfectly topology preserving map in which ...

Robotics and Autonomous Systems, 1997

In this contribution we want to draw the readers attention to the advantages of dynamic cell stru... more In this contribution we want to draw the readers attention to the advantages of dynamic cell structures (DCSs) for learning reactive behaviors of autonomous robots. These include incremental on-like learning, fast output calculation, a flexible integration of different learning rules and a close connection tofizzy logic. The latter allows for incorporation of prior knowledge and to interpret learning with DCSs as fuzzy rule generation and adaptation.

Lecture Notes in Computer Science, 2000

In order to appropriately act in a dynamic environment, any biological or artificial agent needs ... more In order to appropriately act in a dynamic environment, any biological or artificial agent needs to be able to locate object boundaries and use them to segregate the objects from each other and from the background. Since contrasts in features such as luminance, color, texture, motion and stereo may signal object boundaries, locations of high feature contrast should summon an agent’s attention. In this paper, we present an orientation contrast detection scheme, and show how it can be adapted to work on a cortical data format modeled after the retino-cortical remapping of the visual field in primates. Working on this cortical image is attractive because it yields a high resolution, wide field of view, and a significant data reduction, allowing real-time execution of image processing operations on standard PC hardware. We show how the disadvantages of the cortical image format, namely curvilinear coordinates and the hemispheric divide, can be dealt with by angle correction and filling-in of hemispheric borders.

EADS Astrium has developed the Eurobot Control Station ECoS in the frame of the Eurobot WET Model... more EADS Astrium has developed the Eurobot Control Station ECoS in the frame of the Eurobot WET Model project (Weightless Environmental Test) released by the European Space Agency in 2003. ECoS is the main user interface to the robot for generating, validating and executing mission timelines as well as for controlling manually movable subsystems such as the arms, the pan-tilt camera unit and the video system. It is integral to the safety and robustness of Eurobot operations. ECoS has been used to remotely operate the underwater Eurobot WET Model on a mock-up at EAC, Cologne (D) and at the ALTEC facility, Turin (I). The mock-up was representative of a typical space operational environment for Eurobot. Operational functionality of ECoS consists of system status telemetry (TM) monitoring and the remote manual commanding of the Eurobot hardware (TC) for complex operations beyond routine activities. The remote operator can obtain situational awareness of the worksite environment by viewing s...

Proceedings. 11th IEEE International Workshop on Robot and Human Interactive Communication, 2002

The increased use of production assistants will allow new factory requirements to be fulfilled li... more The increased use of production assistants will allow new factory requirements to be fulfilled like the production of small series, the reduction of innovation cycles and the optimization of factory workload. The possible components of such a production assistant, dedicated to object manipulation tasks, has been investigated by Astrium in the project MORPHA. Two features seem to describe such an

Q-Learning has gained increasing attention as a promising real time learning scheme from delayed ... more Q-Learning has gained increasing attention as a promising real time learning scheme from delayed reinforcement. Being compact, model free and theoretically optimal it is commonly preferred to AHC-Learning and its deriva- tives. However, it has long been noticed that theoretical optimality has to be sac- rificed in order to meet the constraints of most applications. In this article we report

In the project LUNARES (LUNAR Exploration Szenario), a technology demonstration of reconfigurable... more In the project LUNARES (LUNAR Exploration Szenario), a technology demonstration of reconfigurable cooperating robots in extraterrestrial sample return missions is implemented using state-of-the-art robotic technologies. A reconfigurable robot team consisting of a lander equipped with a manipulator, a rover, and a climbing robot is tested and demonstrated in a lunar crater test environment at the DFKI Laboratories. The aim is

Intelligent Service Robotics, 2011

LUNARES (Lunar Exploration Scenario) is a project with the aim to demonstrate the retrieval of an... more LUNARES (Lunar Exploration Scenario) is a project with the aim to demonstrate the retrieval of an a scientific sample with a robotic mission in a permanently shadowed region of a lunar crater. The Shakelton crater at the lunar south pole was chosen as reference for the earth demonstration scenario. For accomplishment of such kind of mission an approach of a heterogeneous robotic team was chosen. A wheeled rover and a legged scout as well as a robotic arm mounted on the landing unit act as a team to reach the mission goal. To prove the feasibility of the chosen approach, an artificial lunar crater environment is established to test and demonstrate the capabilities of the robotic systems. depicts the systems in the artificial crater environment. For LUNARES, preexisting robots are used and integrated into a common system control. A "ground control" station is established in order to simulate the control-conditions of a real mission, were information on autonomous task execution and remote controlled operations are displayed for human operators.

Lecture Notes in Computer Science, 2002

Traditionally, feature extraction and correspondence determination are handled separately in moti... more Traditionally, feature extraction and correspondence determination are handled separately in motion analysis of (range) image sequences. The correspondence determination methods have typically an exponential computational complexity. In the present paper we introduce a novel framework of motion analysis that unifies feature extraction and correspondence determination in a single process. Under the basic assumption of a small relative motion between the camera and the scene, feature extraction is solved by refining the segmentation result of the previous frame. This way correspondence information becomes directly available as a by-product of the feature extraction process. Due to the coupled processing of frames we also enforce some degree of segmentation stability. First results on real range image sequences have demonstrated the potential of our approach.

Proceedings Cvpr Ieee Computer Society Conference on Computer Vision and Pattern Recognition Ieee Computer Society Conference on Computer Vision and Pattern Recognition, Feb 1, 1999

ABSTRACT

Icann, 1995

Abstract Dynamic Cell Structures (DCS) belong to the class of topology representing networks rece... more Abstract Dynamic Cell Structures (DCS) belong to the class of topology representing networks recently introduced by Ma94]. DCS networks rest upon radial basis function networks (RBF) and an additional lateral connection structure between the neural units. ...

Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170), 2000

ABSTRACT

Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149), 2000

ABSTRACT

Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062), 2000

ABSTRACT Traditionally, feature extraction and correspondence determination are handled separatel... more ABSTRACT Traditionally, feature extraction and correspondence determination are handled separately in motion analysis of (range) image sequences. The correspondence determination methods have typically an exponential computational complexity. We introduce a novel framework of motion analysis that unifies feature extraction and correspondence determination in a single process. Under the basic assumption of a small relative motion between the camera and the scene, feature extraction is solved by refining the segmentation result of the previous frame. In this way, correspondence information becomes directly available as a by-product of the feature extraction process. Due to the coupled processing of frames, we also force some degree of segmentation stability. First results on real range image sequences have demonstrated the potential of our approach

Lecture Notes in Computer Science, 2002

Traditionally, feature extraction and correspondence determination are handled separately in moti... more Traditionally, feature extraction and correspondence determination are handled separately in motion analysis of (range) image sequences. The correspondence determination methods have typically an exponential computational complexity. In the present paper we introduce a novel framework of motion analysis that unifies feature extraction and correspondence determination in a single process. Under the basic assumption of a small relative motion between the camera and the scene, feature extraction is solved by refining the segmentation result of the previous frame. This way correspondence information becomes directly available as a by-product of the feature extraction process. Due to the coupled processing of frames we also enforce some degree of segmentation stability. First results on real range image sequences have demonstrated the potential of our approach.

2009 Asme Iftomm International Conference on Reconfigurable Mechanisms and Robots, Jun 22, 2009

In the project LUNARES (LUNAR Exploration Szenario), a technology demonstration of reconfigurable... more In the project LUNARES (LUNAR Exploration Szenario), a technology demonstration of reconfigurable cooperating robots in extraterrestrial sample return missions is implemented using state-of-the-art robotic technologies. A reconfigurable robot team consisting of a lander equipped with a manipulator, a rover, and a climbing robot is tested and demonstrated in a lunar crater test environment at the DFKI Laboratories. The aim is

There are few existing robots that perform exploratory tasks in extraterrestrial areas, namely Ma... more There are few existing robots that perform exploratory tasks in extraterrestrial areas, namely Mars or Moon. To use these robots efficiently, they can perform certain tasks autonomously. However, no system taking advantage of cooperative behaviour has yet been deployed. In this paper we present and evaluate two scenarios for cooperation in a space mission: (1) a wheeled rover and a legged robot performing a semi-automated docking task in order to improve general reach of the combined system, (2) a lander guiding a wheeled rover to its docking position.

Studies in Fuzziness and Soft Computing, 1998

... Computer Science Institute Daimler-Benz AG Christian-Albrechts-Ulm, Germany University Kiel, ... more ... Computer Science Institute Daimler-Benz AG Christian-Albrechts-Ulm, Germany University Kiel, Germany G. Hailu G. Sommer Computer Science Institute ... This leads to the definition of the induced Delaunay triangulation or perfectly topology preserving map in which ...

Robotics and Autonomous Systems, 1997

In this contribution we want to draw the readers attention to the advantages of dynamic cell stru... more In this contribution we want to draw the readers attention to the advantages of dynamic cell structures (DCSs) for learning reactive behaviors of autonomous robots. These include incremental on-like learning, fast output calculation, a flexible integration of different learning rules and a close connection tofizzy logic. The latter allows for incorporation of prior knowledge and to interpret learning with DCSs as fuzzy rule generation and adaptation.

Lecture Notes in Computer Science, 2000

In order to appropriately act in a dynamic environment, any biological or artificial agent needs ... more In order to appropriately act in a dynamic environment, any biological or artificial agent needs to be able to locate object boundaries and use them to segregate the objects from each other and from the background. Since contrasts in features such as luminance, color, texture, motion and stereo may signal object boundaries, locations of high feature contrast should summon an agent’s attention. In this paper, we present an orientation contrast detection scheme, and show how it can be adapted to work on a cortical data format modeled after the retino-cortical remapping of the visual field in primates. Working on this cortical image is attractive because it yields a high resolution, wide field of view, and a significant data reduction, allowing real-time execution of image processing operations on standard PC hardware. We show how the disadvantages of the cortical image format, namely curvilinear coordinates and the hemispheric divide, can be dealt with by angle correction and filling-in of hemispheric borders.

EADS Astrium has developed the Eurobot Control Station ECoS in the frame of the Eurobot WET Model... more EADS Astrium has developed the Eurobot Control Station ECoS in the frame of the Eurobot WET Model project (Weightless Environmental Test) released by the European Space Agency in 2003. ECoS is the main user interface to the robot for generating, validating and executing mission timelines as well as for controlling manually movable subsystems such as the arms, the pan-tilt camera unit and the video system. It is integral to the safety and robustness of Eurobot operations. ECoS has been used to remotely operate the underwater Eurobot WET Model on a mock-up at EAC, Cologne (D) and at the ALTEC facility, Turin (I). The mock-up was representative of a typical space operational environment for Eurobot. Operational functionality of ECoS consists of system status telemetry (TM) monitoring and the remote manual commanding of the Eurobot hardware (TC) for complex operations beyond routine activities. The remote operator can obtain situational awareness of the worksite environment by viewing s...

Proceedings. 11th IEEE International Workshop on Robot and Human Interactive Communication, 2002

The increased use of production assistants will allow new factory requirements to be fulfilled li... more The increased use of production assistants will allow new factory requirements to be fulfilled like the production of small series, the reduction of innovation cycles and the optimization of factory workload. The possible components of such a production assistant, dedicated to object manipulation tasks, has been investigated by Astrium in the project MORPHA. Two features seem to describe such an

Q-Learning has gained increasing attention as a promising real time learning scheme from delayed ... more Q-Learning has gained increasing attention as a promising real time learning scheme from delayed reinforcement. Being compact, model free and theoretically optimal it is commonly preferred to AHC-Learning and its deriva- tives. However, it has long been noticed that theoretical optimality has to be sac- rificed in order to meet the constraints of most applications. In this article we report

In the project LUNARES (LUNAR Exploration Szenario), a technology demonstration of reconfigurable... more In the project LUNARES (LUNAR Exploration Szenario), a technology demonstration of reconfigurable cooperating robots in extraterrestrial sample return missions is implemented using state-of-the-art robotic technologies. A reconfigurable robot team consisting of a lander equipped with a manipulator, a rover, and a climbing robot is tested and demonstrated in a lunar crater test environment at the DFKI Laboratories. The aim is

Intelligent Service Robotics, 2011

LUNARES (Lunar Exploration Scenario) is a project with the aim to demonstrate the retrieval of an... more LUNARES (Lunar Exploration Scenario) is a project with the aim to demonstrate the retrieval of an a scientific sample with a robotic mission in a permanently shadowed region of a lunar crater. The Shakelton crater at the lunar south pole was chosen as reference for the earth demonstration scenario. For accomplishment of such kind of mission an approach of a heterogeneous robotic team was chosen. A wheeled rover and a legged scout as well as a robotic arm mounted on the landing unit act as a team to reach the mission goal. To prove the feasibility of the chosen approach, an artificial lunar crater environment is established to test and demonstrate the capabilities of the robotic systems. depicts the systems in the artificial crater environment. For LUNARES, preexisting robots are used and integrated into a common system control. A "ground control" station is established in order to simulate the control-conditions of a real mission, were information on autonomous task execution and remote controlled operations are displayed for human operators.