Jose Luis Blanco (Jose-Luis Blanco-Claraco) | Universidad de Almeria (original) (raw)

Uploads

Papers by Jose Luis Blanco (Jose-Luis Blanco-Claraco)

Computers & Education, 2012

a b s t r a c t LEGO Mindstorms NXT robots are being increasingly used in undergraduate courses, ... more a b s t r a c t LEGO Mindstorms NXT robots are being increasingly used in undergraduate courses, mostly in roboticsrelated subjects. But other engineering topics, like the ones found in data acquisition, control and realtime subjects, also have difficult concepts that can be well understood only with good lab exercises. Such exercises require physical educational tools that should be low cost, easy to configure and use, multipurpose and motivational for the students, being all of this hard to achieve with a single device. The "classical" solution has been to acquire specific commercial kits for each subject, or even topic, usually proprietary and expensive. Our work extends the already existing alternative of using the LEGO Mindstorms NXT robots as a training platform, but not by imitating the same approach of commercial kits (e.g., to isolate some part of the robot for teaching a particular topic); we rather aim at accomplishing all the mentioned requirements simultaneously. For that purpose, we have used only one out-of-the-box, complete robot configuration, to be shared among different subjects without hardware/software/firmware modifications. This has reduced significantly the effort of a group of professors when preparing exercises, and encouraged the reuse of their work among several topics and subjects. Also, we have collected a number of surveys on students and the professors' experiences. In this paper we describe our approach and present in detail the results, which assess the higher motivational adequacy of using a complete robot in these subjects and also the real fulfillment of the other requirements along several academic years.

International Journal of Advanced Robotic Systems, 2015

Autonomous Robots, 2015

ABSTRACT This paper addresses the problem of estimating the spatial distribution of volatile subs... more ABSTRACT This paper addresses the problem of estimating the spatial distribution of volatile substances using a mobile robot equipped with an electronic nose. Our work contributes an effective solution to two important problems that have been disregarded so far: First, obstacles in the environment (walls, furniture,...) do affect the gas spatial distribution. Second, when combining odor measurements taken at different instants of time, their ‘ages’ must be taken into account to model the ephemeral nature of gas distributions. In order to incorporate these two characteristics into the mapping process we propose modeling the spatial distribution of gases as a Gaussian Markov random field. This mathematical framework allows us to consider both: (i) the vanishing information of gas readings by means of a time-increasing uncertainty in sensor measurements, and (ii) the influence of objects in the environment by means of correlations among the different areas. Experimental validation is provided with both, simulated and real-world datasets, demonstrating the out-performance of our method when compared to previous standard techniques in gas mapping.

ABSTRACT Gas leak localization, drug finding, explosive search or detection of fires at early sta... more ABSTRACT Gas leak localization, drug finding, explosive search or detection of fires at early stages are some of the many potential applications claimed for mobile robots equipped with an electronic nose (e-nose). Indeed, these applications present ideal scenarios where a mobile robot equipped with the capabilities of identifying different volatile organic compounds and providing their respective concentrations would be of great help. Nevertheless, and despite the increase of attention paid by the research community to the field, current olfaction robot prototypes are still far of accomplishing such goals. The main reason behind the impossibility of real robots to tackle such applications lies in the complex gas dispersion mechanisms dominated by turbulent advection [1] and influenced by temperature, pressure, airflows and even the own robot movement. This strongly limits the possibility of deriving a ground truth (GT) representation of the gas distribution in the environment, making difficult to validate new algorithms or to compare different proposals aiming at the same objective. For the same reason, real experiments usually employ complex setups with the intention of controlling, as much as possible, the dispersion of volatiles (generation of plumes with fans, shutting doors and windows to reduce airflows, etc.), but even then the results cannot be completely validated because of the lack of information about the real state of the gas dispersion. In this work we present a simulation framework for mobile robotics olfaction which provides the necessary mechanisms for efficiently testing and validating algorithms related, but not limited to, gas distribution mapping (GDM) and gas source localization (GSL).

ABSTRACT Out of all the components of a mobile robot, its sensorial system is undoubtedly among t... more ABSTRACT Out of all the components of a mobile robot, its sensorial system is undoubtedly among the most critical ones when operating in real environments. Till now, these sensorial systems mostly rely on range sensors (laser scanner, sonar, active triangulation) and cameras, while electronic noses have barely been employed despite they can provide a complementary sensory information, vital for some applications, as it happens for humans. This paper analyzes the motivation of providing a robot with smelling capabilities and also singles out some of the hurdles that are preventing smell to achieve the importance of other sensing modalities in robotics. Although we address these subjects from a wide perspective, we are particularly interested in indoor social robots, a field in which we provide our own research experience regarding three important robot olfaction problems: sensor modeling, gas distribution mapping and odor classification. We present some illustrative examples aimed at gaining a better insight into the challenges and real possibilities that olfaction offers to robots.

ABSTRACT In this paper we defend the superior scalability of the Relative Bundle Adjustment (RBA)... more ABSTRACT In this paper we defend the superior scalability of the Relative Bundle Adjustment (RBA) framework for tackling with the SLAM problem. Although such a statement was already done with the introduction of the sliding window (SW) solution to RBA [16], we claim that the map extension that can be maintained locally consistent for some fixed computational cost critically depends on the specific pattern in which new keyframes are connected to previous ones. By rethinking from scratch what we call loop closures in relative coordinates we will show the unexploited flexibility of the RBA framework, which allows us a continuum of strategies from pure relative BA to hybrid submapping with local maps. In this work we derive a systematic way of constructing the problem graph which lies close to submapping and which generates graphs that can be solved more efficiently than those built as previously reported in the literature. As a necessary tool we also present an algorithm for incrementally updating all the spanning-trees demanded by any efficient solution to RBA. Under weak assumptions on the map, and implemented on carefully designed data structures, it is demonstrated to run in bounded time, no matter how large the map becomes. We also present experiments with a synthetic dataset of 55K keyframes in a world of 4.3M landmarks. Our C++ implementation has been released as open source.

2013 IEEE International Conference on Robotics and Automation, 2013

ABSTRACT This paper presents ERODE, an efficient outlier detector with a quality similar to that ... more ABSTRACT This paper presents ERODE, an efficient outlier detector with a quality similar to that of standard RANSAC but at a fraction of its computational cost. In contrast to RANSAC-based methods which follow a hypothesis-and-verify approach, ERODE employs instead the whole set of observations together with a robust kernel to perform robustified least-squares minimization. Our proposal has important practical applications among computer vision problems, which we demonstrate with stereovisual odometry experiments with both simulated and real data.

Pattern Analysis and Applications, 2015

ABSTRACT Odor classification by a robot equipped with an electronic nose (e-nose) is a challengin... more ABSTRACT Odor classification by a robot equipped with an electronic nose (e-nose) is a challenging task for pattern recognition since volatiles have to be classified quickly and reliably even in the case of short measurement sequences, gathered under operation in the field. Signals obtained in these circumstances are characterized by a high-dimensionality, which limits the use of classical classification techniques based on unsupervised and semi-supervised settings, and where predictive variables can be only identified using wrapper or post-processing techniques. In this paper, we consider generative topographic mapping through time (GTM-TT) as an unsupervised model for time-series inspection, based on hidden Markov models regularized by topographic constraints. We further extend the model such that supervised classification and relevance learning can be integrated, resulting in supervised GTM-TT. Then, we evaluate the suitability of this new technique for the odor classification problem in robotics applications. The performance is compared with classical techniques as nearest neighbor, as an absolute baseline, support vector machine and a recent time-series kernel approach, demonstrating the eligibility of our approach for high-dimensional data. Additionally, we exploit the learning system introduced in this work, providing a measure of the relevance of each sensor and individual time points in the classification process, from which important information can be extracted.

2012 IEEE Sensors, 2012

Abstract—Calibration of metal oxide (MOX) gas sensor for continuous monitoring is a complex probl... more Abstract—Calibration of metal oxide (MOX) gas sensor for continuous monitoring is a complex problem due to the highly dynamic characteristics of the gas sensor signal when exposed to natural environment (Open Sampling System-OSS). This work presents a probabilistic approach to the calibration of a MOX gas sensor based on Gaussian Processes (GP). The proposed approach estimates for every sensor measurement a probability distribution of the gas concentration. This enables the calculation of confidence intervals ...

Proceedings of the 28th Annual ACM Symposium on Applied Computing - SAC '13, 2013

Abstract—Building a model of gas concentrations has important industrial and environmental applic... more Abstract—Building a model of gas concentrations has important industrial and environmental applications, and mobile robots on their own or in cooperation with stationary sensors play an important role in this task. Since an exact analytical description of turbulent flow remains an intractable problem, we propose an approximate approach which not only estimates the concentrations but also their variances for each location. Our point of view is that of sequential Bayesian estimation given a lattice of 2D cells treated as hidden ...

Sensors and Actuators B: Chemical, 2013

ABSTRACT Gas quantification based on the response of an array of metal oxide (MOX) gas sensors in... more ABSTRACT Gas quantification based on the response of an array of metal oxide (MOX) gas sensors in an open sampling system is a complex problem due to the highly dynamic characteristic of turbulent airflow and the slow dynamics of the MOX sensors. However, many gas related applications require to deter-mine the gas concentration the sensors are being exposed to. Due to the chaotic nature that dominates gas dispersal, in most cases it is desirable to provide, together with an estimate of the mean concentration, an estimate of the uncertainty of the prediction. This work presents a probabilistic ap-proach for gas quantification with an array of MOX gas sensors based on Gaussian Processes, estimating for every measurement of the sensors a pos-terior distribution of the concentration, from which confidence intervals can be obtained. The proposed approach has been tested with an experimental setup where an array of MOX sensors and a Photo Ionization Detector (PID), used to obtain ground truth concentration, are placed downwind with respect to the gas source. Our approach has been implemented and compared with standard gas quantification methods, demonstrating the advantages when estimating gas concentrations.

Computers & Education, 2012

a b s t r a c t LEGO Mindstorms NXT robots are being increasingly used in undergraduate courses, ... more a b s t r a c t LEGO Mindstorms NXT robots are being increasingly used in undergraduate courses, mostly in roboticsrelated subjects. But other engineering topics, like the ones found in data acquisition, control and realtime subjects, also have difficult concepts that can be well understood only with good lab exercises. Such exercises require physical educational tools that should be low cost, easy to configure and use, multipurpose and motivational for the students, being all of this hard to achieve with a single device. The "classical" solution has been to acquire specific commercial kits for each subject, or even topic, usually proprietary and expensive. Our work extends the already existing alternative of using the LEGO Mindstorms NXT robots as a training platform, but not by imitating the same approach of commercial kits (e.g., to isolate some part of the robot for teaching a particular topic); we rather aim at accomplishing all the mentioned requirements simultaneously. For that purpose, we have used only one out-of-the-box, complete robot configuration, to be shared among different subjects without hardware/software/firmware modifications. This has reduced significantly the effort of a group of professors when preparing exercises, and encouraged the reuse of their work among several topics and subjects. Also, we have collected a number of surveys on students and the professors' experiences. In this paper we describe our approach and present in detail the results, which assess the higher motivational adequacy of using a complete robot in these subjects and also the real fulfillment of the other requirements along several academic years.

International Journal of Advanced Robotic Systems, 2015

Autonomous Robots, 2015

ABSTRACT This paper addresses the problem of estimating the spatial distribution of volatile subs... more ABSTRACT This paper addresses the problem of estimating the spatial distribution of volatile substances using a mobile robot equipped with an electronic nose. Our work contributes an effective solution to two important problems that have been disregarded so far: First, obstacles in the environment (walls, furniture,...) do affect the gas spatial distribution. Second, when combining odor measurements taken at different instants of time, their ‘ages’ must be taken into account to model the ephemeral nature of gas distributions. In order to incorporate these two characteristics into the mapping process we propose modeling the spatial distribution of gases as a Gaussian Markov random field. This mathematical framework allows us to consider both: (i) the vanishing information of gas readings by means of a time-increasing uncertainty in sensor measurements, and (ii) the influence of objects in the environment by means of correlations among the different areas. Experimental validation is provided with both, simulated and real-world datasets, demonstrating the out-performance of our method when compared to previous standard techniques in gas mapping.

ABSTRACT Gas leak localization, drug finding, explosive search or detection of fires at early sta... more ABSTRACT Gas leak localization, drug finding, explosive search or detection of fires at early stages are some of the many potential applications claimed for mobile robots equipped with an electronic nose (e-nose). Indeed, these applications present ideal scenarios where a mobile robot equipped with the capabilities of identifying different volatile organic compounds and providing their respective concentrations would be of great help. Nevertheless, and despite the increase of attention paid by the research community to the field, current olfaction robot prototypes are still far of accomplishing such goals. The main reason behind the impossibility of real robots to tackle such applications lies in the complex gas dispersion mechanisms dominated by turbulent advection [1] and influenced by temperature, pressure, airflows and even the own robot movement. This strongly limits the possibility of deriving a ground truth (GT) representation of the gas distribution in the environment, making difficult to validate new algorithms or to compare different proposals aiming at the same objective. For the same reason, real experiments usually employ complex setups with the intention of controlling, as much as possible, the dispersion of volatiles (generation of plumes with fans, shutting doors and windows to reduce airflows, etc.), but even then the results cannot be completely validated because of the lack of information about the real state of the gas dispersion. In this work we present a simulation framework for mobile robotics olfaction which provides the necessary mechanisms for efficiently testing and validating algorithms related, but not limited to, gas distribution mapping (GDM) and gas source localization (GSL).

ABSTRACT Out of all the components of a mobile robot, its sensorial system is undoubtedly among t... more ABSTRACT Out of all the components of a mobile robot, its sensorial system is undoubtedly among the most critical ones when operating in real environments. Till now, these sensorial systems mostly rely on range sensors (laser scanner, sonar, active triangulation) and cameras, while electronic noses have barely been employed despite they can provide a complementary sensory information, vital for some applications, as it happens for humans. This paper analyzes the motivation of providing a robot with smelling capabilities and also singles out some of the hurdles that are preventing smell to achieve the importance of other sensing modalities in robotics. Although we address these subjects from a wide perspective, we are particularly interested in indoor social robots, a field in which we provide our own research experience regarding three important robot olfaction problems: sensor modeling, gas distribution mapping and odor classification. We present some illustrative examples aimed at gaining a better insight into the challenges and real possibilities that olfaction offers to robots.

ABSTRACT In this paper we defend the superior scalability of the Relative Bundle Adjustment (RBA)... more ABSTRACT In this paper we defend the superior scalability of the Relative Bundle Adjustment (RBA) framework for tackling with the SLAM problem. Although such a statement was already done with the introduction of the sliding window (SW) solution to RBA [16], we claim that the map extension that can be maintained locally consistent for some fixed computational cost critically depends on the specific pattern in which new keyframes are connected to previous ones. By rethinking from scratch what we call loop closures in relative coordinates we will show the unexploited flexibility of the RBA framework, which allows us a continuum of strategies from pure relative BA to hybrid submapping with local maps. In this work we derive a systematic way of constructing the problem graph which lies close to submapping and which generates graphs that can be solved more efficiently than those built as previously reported in the literature. As a necessary tool we also present an algorithm for incrementally updating all the spanning-trees demanded by any efficient solution to RBA. Under weak assumptions on the map, and implemented on carefully designed data structures, it is demonstrated to run in bounded time, no matter how large the map becomes. We also present experiments with a synthetic dataset of 55K keyframes in a world of 4.3M landmarks. Our C++ implementation has been released as open source.

2013 IEEE International Conference on Robotics and Automation, 2013

ABSTRACT This paper presents ERODE, an efficient outlier detector with a quality similar to that ... more ABSTRACT This paper presents ERODE, an efficient outlier detector with a quality similar to that of standard RANSAC but at a fraction of its computational cost. In contrast to RANSAC-based methods which follow a hypothesis-and-verify approach, ERODE employs instead the whole set of observations together with a robust kernel to perform robustified least-squares minimization. Our proposal has important practical applications among computer vision problems, which we demonstrate with stereovisual odometry experiments with both simulated and real data.

Pattern Analysis and Applications, 2015

ABSTRACT Odor classification by a robot equipped with an electronic nose (e-nose) is a challengin... more ABSTRACT Odor classification by a robot equipped with an electronic nose (e-nose) is a challenging task for pattern recognition since volatiles have to be classified quickly and reliably even in the case of short measurement sequences, gathered under operation in the field. Signals obtained in these circumstances are characterized by a high-dimensionality, which limits the use of classical classification techniques based on unsupervised and semi-supervised settings, and where predictive variables can be only identified using wrapper or post-processing techniques. In this paper, we consider generative topographic mapping through time (GTM-TT) as an unsupervised model for time-series inspection, based on hidden Markov models regularized by topographic constraints. We further extend the model such that supervised classification and relevance learning can be integrated, resulting in supervised GTM-TT. Then, we evaluate the suitability of this new technique for the odor classification problem in robotics applications. The performance is compared with classical techniques as nearest neighbor, as an absolute baseline, support vector machine and a recent time-series kernel approach, demonstrating the eligibility of our approach for high-dimensional data. Additionally, we exploit the learning system introduced in this work, providing a measure of the relevance of each sensor and individual time points in the classification process, from which important information can be extracted.

2012 IEEE Sensors, 2012

Abstract—Calibration of metal oxide (MOX) gas sensor for continuous monitoring is a complex probl... more Abstract—Calibration of metal oxide (MOX) gas sensor for continuous monitoring is a complex problem due to the highly dynamic characteristics of the gas sensor signal when exposed to natural environment (Open Sampling System-OSS). This work presents a probabilistic approach to the calibration of a MOX gas sensor based on Gaussian Processes (GP). The proposed approach estimates for every sensor measurement a probability distribution of the gas concentration. This enables the calculation of confidence intervals ...

Proceedings of the 28th Annual ACM Symposium on Applied Computing - SAC '13, 2013

Abstract—Building a model of gas concentrations has important industrial and environmental applic... more Abstract—Building a model of gas concentrations has important industrial and environmental applications, and mobile robots on their own or in cooperation with stationary sensors play an important role in this task. Since an exact analytical description of turbulent flow remains an intractable problem, we propose an approximate approach which not only estimates the concentrations but also their variances for each location. Our point of view is that of sequential Bayesian estimation given a lattice of 2D cells treated as hidden ...

Sensors and Actuators B: Chemical, 2013

ABSTRACT Gas quantification based on the response of an array of metal oxide (MOX) gas sensors in... more ABSTRACT Gas quantification based on the response of an array of metal oxide (MOX) gas sensors in an open sampling system is a complex problem due to the highly dynamic characteristic of turbulent airflow and the slow dynamics of the MOX sensors. However, many gas related applications require to deter-mine the gas concentration the sensors are being exposed to. Due to the chaotic nature that dominates gas dispersal, in most cases it is desirable to provide, together with an estimate of the mean concentration, an estimate of the uncertainty of the prediction. This work presents a probabilistic ap-proach for gas quantification with an array of MOX gas sensors based on Gaussian Processes, estimating for every measurement of the sensors a pos-terior distribution of the concentration, from which confidence intervals can be obtained. The proposed approach has been tested with an experimental setup where an array of MOX sensors and a Photo Ionization Detector (PID), used to obtain ground truth concentration, are placed downwind with respect to the gas source. Our approach has been implemented and compared with standard gas quantification methods, demonstrating the advantages when estimating gas concentrations.

One of the major disadvantages of the use of Metal Oxide Semiconductor (MOS) technology as a tran... more One of the major disadvantages of the use of Metal Oxide Semiconductor (MOS) technology as a transducer for electronic gas sensing devices (e-noses) is the long recovery period needed after each gas exposure. This severely restricts its usage in applications where the gas concentrations may change rapidly, as in mobile robotic olfaction, where allowing for sensor recovery forces the robot to move at a very low speed, almost incompatible with any practical robot operation. This paper describes the design of a new e-nose which overcomes, to a great extent, such a limitation. The proposed e-nose, called Multi-Chamber Electronic Nose (MCE-nose), comprises several identical sets of MOS sensors accommodated in separate chambers (four in our current prototype), which alternate between sensing and recovery states, providing, as a whole, a device capable of sensing changes in chemical concentrations faster. The utility and performance of the MCE-nose in mobile robotic olfaction is shown through several experiments involving rapid sensing of gas concentration and mobile robot gas mapping.