Christian Plagemann | Google - Academia.edu (original) (raw)

Papers by Christian Plagemann

International Joint Conference on Artificial Intelligence, 2009

Robots operating in home environments must be able to interact with articulated objects such as d... more Robots operating in home environments must be able to interact with articulated objects such as doors or drawers. Ideally, robots are able to autonomously infer articulation models by observation. In this paper, we present an approach to learn kinematic models by inferring the connectivity of rigid parts and the articulation models for the corresponding links. Our method uses a mixture of parameterized and parameter-free (Gaussian process) representations and finds low-dimensional manifolds that provide the best explanation of the given observations. Our approach has been implemented and evaluated using real data obtained in various realistic home environment settings.

Robotics: Science and Systems, 2007

Three-dimensional digital terrain models are of fundamental importance in many areas such as the ... more Three-dimensional digital terrain models are of fundamental importance in many areas such as the geo-sciences and outdoor robotics. Accurate modeling requires the ability to deal with a varying data density and to balance smoothing against the preservation of discontinuities. The latter is particularly important for robotics applications, as discontinuities that arise, for example, at steps, stairs, or building walls are

In this paper, we consider the problem of learning a two dimensional spatial model of a gas distr... more In this paper, we consider the problem of learning a two dimensional spatial model of a gas distribution with a mobile robot. Building maps that can be used to accurately predict the gas concentration at query locations is a challenging task due to the chaotic nature of gas dispersal. We present an approach that formulates this task as a regression problem. To deal with the specific properties of typical gas distributions, we propose a sparse Gaussian process mixture model. This allows us to accurately represent the smooth background signal as well as areas of high concentration. We integrate the sparsification of the training data into an EM procedure used for learning the mixture components and the gating function. Our approach has been implemented and tested using datasets recorded with a real mobile robot equipped with an electronic nose. We demonstrate that our models are well suited for predicting gas concentrations at new query locations and that they outperform alternative methods used in robotics to carry out in this task.

Robotics: Science and Systems, 2007

In probabilistic mobile robotics, the development of measurement models plays a crucial role as i... more In probabilistic mobile robotics, the development of measurement models plays a crucial role as it directly influences the efficiency and the robustness of the robot's performance in a great variety of tasks including localization, tracking, and map building. In this paper, we present a novel probabilistic measurement model for range finders, called Gaussian beam processes, which treats the measurement modeling

International Joint Conference on Artificial Intelligence, 2007

The ability to detect failures and to analyze their causes is one of the preconditions of truly a... more The ability to detect failures and to analyze their causes is one of the preconditions of truly au- tonomous mobile robots. Especially online fail- ure detection is a complex task, since the effects of failures are typically difficult to model and often resemble the noisy system behavior in a fault-free operational mode. The extremely low a priori like- lihood of

Studies in Classification, Data Analysis, and Knowledge Organization, 2008

Artificial systems with a high degree of autonomy require reliable semantic information about the... more Artificial systems with a high degree of autonomy require reliable semantic information about the context they operate in. State interpretation, however, is a difficult task. Interpretations may depend on a history of states and there may be more than one valid interpretation. We propose a model for spatio-temporal situations using hidden Markov models based on relational state descriptions, which are extracted from the estimated state of an underlying dynamic system. Our model covers concurrent situations, scenarios with multiple agents, and situations of varying durations. To evaluate the practical usefulness of our model, we apply it to the concrete task of online traffic analysis.

Lecture Notes in Computer Science, 2008

Gaussian processes using nonstationary covariance functions are a powerful tool for Bayesian regr... more Gaussian processes using nonstationary covariance functions are a powerful tool for Bayesian regression with input-dependent smoothness. A common approach is to model the local smoothness by a latent process that is integrated over using Markov chain Monte Carlo approaches. In this paper, we show that a simple approximation that uses the estimated mean of the local smoothness yields good results and allows one to employ efficient gradient-based optimization techniques for learning the parameters of the latent and the observed processes jointly. Extensive experiments on both synthetic and real-world data, including challenging problems in robotics, show the relevance and feasibility of our approach.

Sequential Parameter Estimation for Fault Diagnosis in Mobile Robots Using Particle Filters

Informatik aktuell, 2006

ABSTRACT

2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2007

Range sensors are popular for localization since they directly measure the geometry of the local ... more Range sensors are popular for localization since they directly measure the geometry of the local environment. Another distinct benefit is their typically high accuracy and spatial resolution. It is a well-known problem, however, that the high precision of these sensors leads to practical problems in probabilistic localization approaches such as Monte Carlo localization (MCL), because the likelihood function becomes extremely peaked if no means of regularization are applied. In practice, one therefore artificially smoothes the likelihood function or only integrates a small fraction of the measurements. In this paper we present a more fundamental and robust approach, that provides a smooth likelihood model for entire range scans. Additionally, it is location-dependent. In practical experiments we compare our approach to previous methods and demonstrate that it leads to a more robust localization.

Proceedings of the 24th international conference on Machine learning - ICML '07, 2007

This paper presents a novel Gaussian process (GP) approach to regression with inputdependent nois... more This paper presents a novel Gaussian process (GP) approach to regression with inputdependent noise rates. We follow Goldberg et al.'s approach and model the noise variance using a second GP in addition to the GP governing the noise-free output value. In contrast to Goldberg et al., however, we do not use a Markov chain Monte Carlo method to approximate the posterior noise variance but a most likely noise approach. The resulting model is easy to implement and can directly be used in combination with various existing extensions of the standard GPs such as sparse approximations. Extensive experiments on both synthetic and real-world data, including a challenging perception problem in robotics, show the effectiveness of most likely heteroscedastic GP regression.

2009 IEEE International Conference on Robotics and Automation, 2009

In recent years, there has been an increasing interest within the robotics community in investiga... more In recent years, there has been an increasing interest within the robotics community in investigating whether Radio Frequency Identification (RFID) technology can be utilized to solve localization and mapping problems in the context of mobile robots. We present a novel sensor model which can be utilized for localizing RFID tags and for tracking a mobile agent moving through an RFID-equipped environment. The proposed probabilistic sensor model characterizes the received signal strength indication (RSSI) information as well as the tag detection events to achieve a higher modeling accuracy compared to state-of-the-art models which deal with one of these aspects only. We furthermore propose a method that is able to bootstrap such a sensor model in a fully unsupervised fashion. Real-world experiments demonstrate the effectiveness of our approach also in comparison to existing techniques.

Unsupervised body scheme learning through self-perception

2008 IEEE International Conference on Robotics and Automation, 2008

Abstract— In this paper, we present an approach allowing a robot to learn a generative model of i... more Abstract— In this paper, we present an approach allowing a robot to learn a generative model of its own,physical body from scratch using self-perception with a single monocular camera. Our approach,yields a compact Bayesian network for the robot’s kinematic structure including the forward and inverse models relating action commands,and body pose. We propose to simultaneously learn local action models for all pairs of perceivable body parts from data generated through random “motor babbling.” From this repertoire of local models, we construct a Bayesian network for the full system using the pose prediction accuracy on a separate cross validation data set as the criterion for model selection. The resulting model can be used to predict the body pose when no perception is available and allows for gradient-based posture control. In experiments with real and simulated manipulator arms, we show that our system is able to quickly learn compact and accurate models and to robustly deal with noisy observations. I. I NTRODUCTION Kinematic models are widely used in robotics, in particular

2008 IEEE International Conference on Robotics and Automation, 2008

One of the key tasks during the realization of probabilistic approaches to localization is the de... more One of the key tasks during the realization of probabilistic approaches to localization is the design of a proper sensor model, that calculates the likelihood of a measurement given the current pose of the vehicle and the map of the environment. In the past, range sensors have become popular for mobile robot localization since they directly measure distance. However, in situations in which the robot operates close to edges of obstacles or in highly cluttered environments, small changes in the pose of the robot can lead to large variations in the acquired range scans. If the sensor model used does not appropriately characterize the resulting fluctuations, the performance of probabilistic approaches may substantially degrade. A common solution is to artificially smooth the likelihood function or to only integrate a small fraction of the measurements. In this paper we present a more fundamental and robust approach which uses mixtures of Gaussians to model the likelihood function for single range measurements. In practical experiments we compare our approach to previous methods and demonstrate that it yields a substantially increase in robustness.

Truly versatile robots operating in the real world have to be able to learn about objects and the... more Truly versatile robots operating in the real world have to be able to learn about objects and their properties autonomously, that is, without being provided with carefully engineered training data. This paper presents an approach that allows a robot to discover object classes in three-dimensional range data in an unsupervised fashion and without a-priori knowledge about the observed objects. Our

Robotics: Science and Systems, 2008

In this paper, we consider the problem of learning a two dimensional spatial model of a gas distr... more In this paper, we consider the problem of learning a two dimensional spatial model of a gas distribution with a mobile robot. Building maps that can be used to accurately predict the gas concentration at query locations is a challenging task due to the chaotic nature of gas dispersal. We present an approach that formulates this task as a regression problem. To deal with the specific properties of typical gas distributions, we propose a sparse Gaussian process mixture model. This allows us to accurately represent the smooth background signal as well as areas of high concentration. We integrate the sparsification of the training data into an EM procedure used for learning the mixture components and the gating function. Our approach has been implemented and tested using datasets recorded with a real mobile robot equipped with an electronic nose. We demonstrate that our models are well suited for predicting gas concentrations at new query locations and that they outperform alternative methods used in robotics to carry out in this task.

Springer Tracts in Advanced Robotics, 2006

In this paper, we consider the problem of online failure detection and isolation for mobile robot... more In this paper, we consider the problem of online failure detection and isolation for mobile robots. The goal is to enable a mobile robot to determine whether the system is running free of faults or to identify the cause for faulty behavior. In general, failures cannot be detected by solely monitoring the process model for the error free mode because if certain model assumptions are violated the observation likelihood might not indicate a defect. Existing approaches therefore use comparably complex system models to cover all possible system behaviors. In this paper, we propose the mixed-abstraction particle filter as an efficient way of dealing with potential failures of mobile robots. It uses a hierarchy of process models to actively validate the model assumptions and distribute the computational resources between the models adaptively. We present an implementation of our algorithm and discuss results obtained from simulated and real-robot experiments.

Lecture Notes in Computer Science, 2005

The ability to accurately localize objects in an observed scene is regarded as an important preco... more The ability to accurately localize objects in an observed scene is regarded as an important precondition for many practical applications including automatic manufacturing, quality assurance, or human-robot interaction. A popular method to recognize three-dimensional objects in two-dimensional images is to apply so-called view-based approaches.

Body Schema Learning

Springer Tracts in Advanced Robotics, 2012

2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2008

The problem of estimating the positions of landmarks using a mobile robot equipped with a camera ... more The problem of estimating the positions of landmarks using a mobile robot equipped with a camera has intensively been studied in the past. In this paper, we consider a variant of this problem in which the robot should estimate the locations of observed landmarks based on a sparse set of geo-referenced images for which no heading information is available. Sources for such kind of data are image portals such as Flickr or Google Image Search. We formulate the problem of estimating the landmark locations as an optimization problem and show that it is possible to accurately localize the landmarks in real world settings.

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010

Markerless tracking of human pose is a hard yet relevant problem. In this paper, we derive an eff... more Markerless tracking of human pose is a hard yet relevant problem. In this paper, we derive an efficient filtering algorithm for tracking human pose using a stream of monocular depth images. The key idea is to combine an accurate generative model-which is achievable in this setting using programmable graphics hardware-with a discriminative model that provides data-driven evidence about body part locations. In each filter iteration, we apply a form of local model-based search that exploits the nature of the kinematic chain. As fast movements and occlusion can disrupt the local search, we utilize a set of discriminatively trained patch classifiers to detect body parts. We describe a novel algorithm for propagating this noisy evidence about body part locations up the kinematic chain using the unscented transform. The resulting distribution of body configurations allows us to reinitialize the model-based search. We provide extensive experimental results on 28 real-world sequences using automatic ground-truth annotations from a commercial motion capture system.

International Joint Conference on Artificial Intelligence, 2009

Robots operating in home environments must be able to interact with articulated objects such as d... more Robots operating in home environments must be able to interact with articulated objects such as doors or drawers. Ideally, robots are able to autonomously infer articulation models by observation. In this paper, we present an approach to learn kinematic models by inferring the connectivity of rigid parts and the articulation models for the corresponding links. Our method uses a mixture of parameterized and parameter-free (Gaussian process) representations and finds low-dimensional manifolds that provide the best explanation of the given observations. Our approach has been implemented and evaluated using real data obtained in various realistic home environment settings.

Robotics: Science and Systems, 2007

Three-dimensional digital terrain models are of fundamental importance in many areas such as the ... more Three-dimensional digital terrain models are of fundamental importance in many areas such as the geo-sciences and outdoor robotics. Accurate modeling requires the ability to deal with a varying data density and to balance smoothing against the preservation of discontinuities. The latter is particularly important for robotics applications, as discontinuities that arise, for example, at steps, stairs, or building walls are

In this paper, we consider the problem of learning a two dimensional spatial model of a gas distr... more In this paper, we consider the problem of learning a two dimensional spatial model of a gas distribution with a mobile robot. Building maps that can be used to accurately predict the gas concentration at query locations is a challenging task due to the chaotic nature of gas dispersal. We present an approach that formulates this task as a regression problem. To deal with the specific properties of typical gas distributions, we propose a sparse Gaussian process mixture model. This allows us to accurately represent the smooth background signal as well as areas of high concentration. We integrate the sparsification of the training data into an EM procedure used for learning the mixture components and the gating function. Our approach has been implemented and tested using datasets recorded with a real mobile robot equipped with an electronic nose. We demonstrate that our models are well suited for predicting gas concentrations at new query locations and that they outperform alternative methods used in robotics to carry out in this task.

Robotics: Science and Systems, 2007

In probabilistic mobile robotics, the development of measurement models plays a crucial role as i... more In probabilistic mobile robotics, the development of measurement models plays a crucial role as it directly influences the efficiency and the robustness of the robot's performance in a great variety of tasks including localization, tracking, and map building. In this paper, we present a novel probabilistic measurement model for range finders, called Gaussian beam processes, which treats the measurement modeling

International Joint Conference on Artificial Intelligence, 2007

The ability to detect failures and to analyze their causes is one of the preconditions of truly a... more The ability to detect failures and to analyze their causes is one of the preconditions of truly au- tonomous mobile robots. Especially online fail- ure detection is a complex task, since the effects of failures are typically difficult to model and often resemble the noisy system behavior in a fault-free operational mode. The extremely low a priori like- lihood of

Studies in Classification, Data Analysis, and Knowledge Organization, 2008

Artificial systems with a high degree of autonomy require reliable semantic information about the... more Artificial systems with a high degree of autonomy require reliable semantic information about the context they operate in. State interpretation, however, is a difficult task. Interpretations may depend on a history of states and there may be more than one valid interpretation. We propose a model for spatio-temporal situations using hidden Markov models based on relational state descriptions, which are extracted from the estimated state of an underlying dynamic system. Our model covers concurrent situations, scenarios with multiple agents, and situations of varying durations. To evaluate the practical usefulness of our model, we apply it to the concrete task of online traffic analysis.

Lecture Notes in Computer Science, 2008

Gaussian processes using nonstationary covariance functions are a powerful tool for Bayesian regr... more Gaussian processes using nonstationary covariance functions are a powerful tool for Bayesian regression with input-dependent smoothness. A common approach is to model the local smoothness by a latent process that is integrated over using Markov chain Monte Carlo approaches. In this paper, we show that a simple approximation that uses the estimated mean of the local smoothness yields good results and allows one to employ efficient gradient-based optimization techniques for learning the parameters of the latent and the observed processes jointly. Extensive experiments on both synthetic and real-world data, including challenging problems in robotics, show the relevance and feasibility of our approach.

Sequential Parameter Estimation for Fault Diagnosis in Mobile Robots Using Particle Filters

Informatik aktuell, 2006

ABSTRACT

2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2007

Range sensors are popular for localization since they directly measure the geometry of the local ... more Range sensors are popular for localization since they directly measure the geometry of the local environment. Another distinct benefit is their typically high accuracy and spatial resolution. It is a well-known problem, however, that the high precision of these sensors leads to practical problems in probabilistic localization approaches such as Monte Carlo localization (MCL), because the likelihood function becomes extremely peaked if no means of regularization are applied. In practice, one therefore artificially smoothes the likelihood function or only integrates a small fraction of the measurements. In this paper we present a more fundamental and robust approach, that provides a smooth likelihood model for entire range scans. Additionally, it is location-dependent. In practical experiments we compare our approach to previous methods and demonstrate that it leads to a more robust localization.

Proceedings of the 24th international conference on Machine learning - ICML '07, 2007

This paper presents a novel Gaussian process (GP) approach to regression with inputdependent nois... more This paper presents a novel Gaussian process (GP) approach to regression with inputdependent noise rates. We follow Goldberg et al.'s approach and model the noise variance using a second GP in addition to the GP governing the noise-free output value. In contrast to Goldberg et al., however, we do not use a Markov chain Monte Carlo method to approximate the posterior noise variance but a most likely noise approach. The resulting model is easy to implement and can directly be used in combination with various existing extensions of the standard GPs such as sparse approximations. Extensive experiments on both synthetic and real-world data, including a challenging perception problem in robotics, show the effectiveness of most likely heteroscedastic GP regression.

2009 IEEE International Conference on Robotics and Automation, 2009

In recent years, there has been an increasing interest within the robotics community in investiga... more In recent years, there has been an increasing interest within the robotics community in investigating whether Radio Frequency Identification (RFID) technology can be utilized to solve localization and mapping problems in the context of mobile robots. We present a novel sensor model which can be utilized for localizing RFID tags and for tracking a mobile agent moving through an RFID-equipped environment. The proposed probabilistic sensor model characterizes the received signal strength indication (RSSI) information as well as the tag detection events to achieve a higher modeling accuracy compared to state-of-the-art models which deal with one of these aspects only. We furthermore propose a method that is able to bootstrap such a sensor model in a fully unsupervised fashion. Real-world experiments demonstrate the effectiveness of our approach also in comparison to existing techniques.

Unsupervised body scheme learning through self-perception

2008 IEEE International Conference on Robotics and Automation, 2008

Abstract— In this paper, we present an approach allowing a robot to learn a generative model of i... more Abstract— In this paper, we present an approach allowing a robot to learn a generative model of its own,physical body from scratch using self-perception with a single monocular camera. Our approach,yields a compact Bayesian network for the robot’s kinematic structure including the forward and inverse models relating action commands,and body pose. We propose to simultaneously learn local action models for all pairs of perceivable body parts from data generated through random “motor babbling.” From this repertoire of local models, we construct a Bayesian network for the full system using the pose prediction accuracy on a separate cross validation data set as the criterion for model selection. The resulting model can be used to predict the body pose when no perception is available and allows for gradient-based posture control. In experiments with real and simulated manipulator arms, we show that our system is able to quickly learn compact and accurate models and to robustly deal with noisy observations. I. I NTRODUCTION Kinematic models are widely used in robotics, in particular

2008 IEEE International Conference on Robotics and Automation, 2008

One of the key tasks during the realization of probabilistic approaches to localization is the de... more One of the key tasks during the realization of probabilistic approaches to localization is the design of a proper sensor model, that calculates the likelihood of a measurement given the current pose of the vehicle and the map of the environment. In the past, range sensors have become popular for mobile robot localization since they directly measure distance. However, in situations in which the robot operates close to edges of obstacles or in highly cluttered environments, small changes in the pose of the robot can lead to large variations in the acquired range scans. If the sensor model used does not appropriately characterize the resulting fluctuations, the performance of probabilistic approaches may substantially degrade. A common solution is to artificially smooth the likelihood function or to only integrate a small fraction of the measurements. In this paper we present a more fundamental and robust approach which uses mixtures of Gaussians to model the likelihood function for single range measurements. In practical experiments we compare our approach to previous methods and demonstrate that it yields a substantially increase in robustness.

Truly versatile robots operating in the real world have to be able to learn about objects and the... more Truly versatile robots operating in the real world have to be able to learn about objects and their properties autonomously, that is, without being provided with carefully engineered training data. This paper presents an approach that allows a robot to discover object classes in three-dimensional range data in an unsupervised fashion and without a-priori knowledge about the observed objects. Our

Robotics: Science and Systems, 2008

In this paper, we consider the problem of learning a two dimensional spatial model of a gas distr... more In this paper, we consider the problem of learning a two dimensional spatial model of a gas distribution with a mobile robot. Building maps that can be used to accurately predict the gas concentration at query locations is a challenging task due to the chaotic nature of gas dispersal. We present an approach that formulates this task as a regression problem. To deal with the specific properties of typical gas distributions, we propose a sparse Gaussian process mixture model. This allows us to accurately represent the smooth background signal as well as areas of high concentration. We integrate the sparsification of the training data into an EM procedure used for learning the mixture components and the gating function. Our approach has been implemented and tested using datasets recorded with a real mobile robot equipped with an electronic nose. We demonstrate that our models are well suited for predicting gas concentrations at new query locations and that they outperform alternative methods used in robotics to carry out in this task.

Springer Tracts in Advanced Robotics, 2006

In this paper, we consider the problem of online failure detection and isolation for mobile robot... more In this paper, we consider the problem of online failure detection and isolation for mobile robots. The goal is to enable a mobile robot to determine whether the system is running free of faults or to identify the cause for faulty behavior. In general, failures cannot be detected by solely monitoring the process model for the error free mode because if certain model assumptions are violated the observation likelihood might not indicate a defect. Existing approaches therefore use comparably complex system models to cover all possible system behaviors. In this paper, we propose the mixed-abstraction particle filter as an efficient way of dealing with potential failures of mobile robots. It uses a hierarchy of process models to actively validate the model assumptions and distribute the computational resources between the models adaptively. We present an implementation of our algorithm and discuss results obtained from simulated and real-robot experiments.

Lecture Notes in Computer Science, 2005

The ability to accurately localize objects in an observed scene is regarded as an important preco... more The ability to accurately localize objects in an observed scene is regarded as an important precondition for many practical applications including automatic manufacturing, quality assurance, or human-robot interaction. A popular method to recognize three-dimensional objects in two-dimensional images is to apply so-called view-based approaches.

Body Schema Learning

Springer Tracts in Advanced Robotics, 2012

2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2008

The problem of estimating the positions of landmarks using a mobile robot equipped with a camera ... more The problem of estimating the positions of landmarks using a mobile robot equipped with a camera has intensively been studied in the past. In this paper, we consider a variant of this problem in which the robot should estimate the locations of observed landmarks based on a sparse set of geo-referenced images for which no heading information is available. Sources for such kind of data are image portals such as Flickr or Google Image Search. We formulate the problem of estimating the landmark locations as an optimization problem and show that it is possible to accurately localize the landmarks in real world settings.

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010

Markerless tracking of human pose is a hard yet relevant problem. In this paper, we derive an eff... more Markerless tracking of human pose is a hard yet relevant problem. In this paper, we derive an efficient filtering algorithm for tracking human pose using a stream of monocular depth images. The key idea is to combine an accurate generative model-which is achievable in this setting using programmable graphics hardware-with a discriminative model that provides data-driven evidence about body part locations. In each filter iteration, we apply a form of local model-based search that exploits the nature of the kinematic chain. As fast movements and occlusion can disrupt the local search, we utilize a set of discriminatively trained patch classifiers to detect body parts. We describe a novel algorithm for propagating this noisy evidence about body part locations up the kinematic chain using the unscented transform. The resulting distribution of body configurations allows us to reinitialize the model-based search. We provide extensive experimental results on 28 real-world sequences using automatic ground-truth annotations from a commercial motion capture system.