To Örebro University

The problem of gas detection is relevant to manyreal-world applications, such as leak detection in industrialsettings and surveillance. In this paper we address the problemof gas detection in large areas with a mobile robotic platformequipped with a remote gas sensor. We propose a novelmethod based on convex relaxation for quickly finding anexploration plan that guarantees a complete coverage of theenvironment. Our method proves to be highly efficient in termsof computational requirements and to provide nearly-optimalsolutions. We validate our approach both in simulation andin real environments, thus demonstrating its applicability toreal-world problems.

The problem of gas detection is relevant to many real-world applications, such as leak detection in industrial settings and landfill monitoring. In this paper, we address the problem of gas detection in large areas with a mobile robotic platform equipped with a remote gas sensor. We propose an algorithm that leverages a novel method based on convex relaxation for quickly solving sensor placement problems, and for generating an efficient exploration plan for the robot. To demonstrate the applicability of our method to real-world environments, we performed a large number of experimental trials, both on randomly generated maps and on the map of a real environment. Our approach proves to be highly efficient in terms of computational requirements and to provide nearly-optimal solutions.

In this paper we present an inspection robot to produce gas distribution maps and localize gas sources in large outdoor environments. The robot is equipped with a 3D laser range finder and a remote gas sensor that returns integral concentration measurements. We apply principles of tomography to create a spatial gas distribution model from integral gas concentration measurements. The gas distribution algorithm is framed as a convex optimization problem and it models the mean distribution and the fluctuations of gases. This is important since gas dispersion is not an static phenomenon and furthermore, areas of high fluctuation can be correlated with the location of an emitting source. We use a compact surface representation created from the measurements of the 3D laser range finder with a state of the art mapping algorithm to get a very accurate localization and estimation of the path of the laser beams. In addition, a conic model for the beam of the remote gas sensor is introduced. We observe a substantial improvement in the gas source localization capabilities over previous state-of-the-art in our evaluation carried out in an open field environment.

The response of zeolite-modified sensors, prepared by screen printing layers of chromium titanium oxide (CTO), were compared to unmodified tin oxide sensors using amplitude and transient responses. For transient responses we used a family of features, derived from the exponential moving average (EMA), to characterize chemo-resistive responses. All sensors were tested simultaneously against 20 individual volatile compounds from four chemical groups. The responses of the two types of sensors showed some independence. The zeolite modified CTO sensors discriminated compounds better using either amplitude response or EMA features and CTO-modified sensors also responded three times faster.

In this paper, we introduce a Bayesian time series model approach for gas concentration estimation using Metal Oxide (MOX) sensors in Open Sampling System (OSS). Our approach focuses on the compensation of the slow response of MOX sensors, while concurrently solving the problem of estimating the gas concentration in OSS. The proposed Augmented Switching Linear System model allows to include all the sources of uncertainty arising at each step of the problem in a single coherent probabilistic formulation. In particular, the problem of detecting on-line the current sensor dynamical regime and estimating the underlying gas concentration under environmental disturbances and noisy measurements is formulated and solved as a statistical inference problem. Our model improves, with respect to the state of the art, where system modeling approaches have been already introduced, but only provided an indirect relative measures proportional to the gas concentration and the problem of modeling uncertainty was ignored. Our approach is validated experimentally and the performances in terms of speed of and quality of the gas concentration estimation are compared with the ones obtained using a photo-ionization detector.

Chemical detection systems based on chemo-resistive sensors usually include a gas chamber to control the sample air flow and to minimize turbulence. However, such a kind of experimental setup does not reproduce the gas concentration fluctuations observed in natural environments and destroys the spatio-temporal information contained in gas plumes. Aiming at reproducing more realistic environments, we utilize a wind tunnel with two independent gas sources that get naturally mixed along a turbulent flow. For the first time, chemo-resistive gas sensors are exposed to dynamic gas mixtures generated with several concentration levels at the sources. Moreover, the ground truth of gas concentrations at the sensor location was estimated by means of gas chromatography-mass spectrometry. We used a support vector machine as a tool to show that chemo-resistive transduction can be utilized to reliably identify chemical components in dynamic turbulent mixtures, as long as sufficient gas concentration coverage is used. We show that in open sampling systems, training the classifiers only on high concentrations of gases produces less effective classification and that it is important to calibrate the classification method with data at low gas concentrations to achieve optimal performance.

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 determine 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 approach for gas quantification with an array of MOX gas sensors based on Gaussian Processes, estimating for every measurement of the sensors a posterior 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.

Roboticists often take inspiration from animals for designing sensors, actuators, or algorithms that control the behavior of robots. Bio-inspiration is motivated with the uncanny ability of animals to solve complex tasks like recognizing and manipulating objects, walking on uneven terrains, or navigating to the source of an odor plume. In particular the task of tracking an odor plume up to its source has nearly exclusively been addressed using biologically inspired algorithms and robots have been developed, for example, to mimic the behavior of moths, dung beetles, or lobsters. In this paper we argue that biomimetic approaches to gas source localization are of limited use, primarily because animals differ fundamentally in their sensing and actuation capabilities from state-of-the-art gas-sensitive mobile robots. To support our claim, we compare actuation and chemical sensing available to mobile robots to the corresponding capabilities of moths. We further characterize airflow and chemosensor measurements obtained with three different robot platforms (two wheeled robots and one flying micro-drone) in four prototypical environments and show that the assumption of a constant and unidirectional airflow, which is the basis of many gas source localization approaches, is usually far from being valid. This analysis should help to identify how underlying principles, which govern the gas source tracking behavior of animals, can be usefully translated into gas source localization approaches that fully take into account the capabilities of mobile robots. We also describe the requirements for a reference application, monitoring of gas emissions at landfill sites with mobile robots, and discuss an engineered gas source localization approach based on statistics as an alternative to biologically inspired algorithms.

Gas distribution mapping is a crucial task in emission monitoring and search and rescue applications. A common assumption made by state-of-the art mapping algorithms is that only one type of gaseous substance is present in the environment. For real world applications, this assumption can become very restrictive. In this paper we present an algorithm that creates gas concentration maps in a scenario where multiple heterogeneous gas sources are present. First, using an array of metal oxide (MOX) sensors and a pattern recognition algorithm, the chemical compound is identified. Then, for each chemical compound a gas concentration map using the readings of a Photo Ionization Detector (PID) is created. The proposed approach has been validated in experiments with the sensors mounted on a mobile robot which performed a predefined trajectory in a room where two gas sources emitting respectively ethanol and 2-propanol have been placed.

Due to its environmental, economical and safety implications, methane leak detection is a crucial task to address in the biogas production industry. In this paper, we introduce Gasbot, a robotic platform that aims to automatize methane emission monitoring in landfills and biogas production sites. The distinctive characteristic of the Gasbot platform is the use of a Tunable Laser Absorption Spectroscopy (TDLAS) sensor. This sensor provides integral concentration measurements over the path of the laser beam. Existing gas distribution mapping algorithms can only handle local measurements obtained from traditional in-situ chemical sensors. In this paper we also describe an algorithm to generate 3D methane concentration maps from integral concentration and depth measurements. The Gasbot platform has been tested in two different scenarios: an underground corridor, where a pipeline leak was simulated and in a decommissioned landfill site, where an artificial methane emission source was introduced.

In this paper, we address the task of gas distribution modeling in scenarios where multiple heterogeneous compounds are present. Gas distribution modeling is particularly useful in emission monitoring applications where spatial representations of the gaseous patches can be used to identify emission hot spots. In realistic environments, the presence of multiple chemicals is expected and therefore, gas discrimination has to be incorporated in the modeling process. The approach presented in this work addresses the task of gas distribution modeling by combining different non selective gas sensors. Gas discrimination is addressed with an open sampling system, composed by an array of metal oxide sensors and a probabilistic algorithm tailored to uncontrolled environments. For each of the identified compounds, the mapping algorithm generates a calibrated gas distribution model using the classification uncertainty and the concentration readings acquired with a photo ionization detector. The meta parameters of the proposed modeling algorithm are automatically learned from the data. The approach was validated with a gas sensitive robot patrolling outdoor and indoor scenarios, where two different chemicals were released simultaneously. The experimental results show that the generated multi compound maps can be used to accurately predict the location of emitting gas sources.

This work presents a gas discrimination approachfor Open Sampling Systems (OSS), composed of non-specificmetal oxide sensors only. In an OSS, as used on robots or insensor networks, the sensors are exposed to the dynamics of theenvironment and thus, most of the data corresponds to highlydiluted samples while high concentrations are sparse. In addition,a positive correlation between class separability and concentra-tion level can be observed. The proposed approach computes theclass posteriors by coupling the pairwise probabilities betweenthe compounds to a confidence model based on an estimation ofthe concentration. In this way a rejection posterior, analogous tothe detection limit of the human nose, is learned. Evaluation wasconducted in indoor and outdoor sites, with an OSS equippedrobot, in the presence of two gases. The results show that theproposed approach achieves a high classification performancewith a low sensitivity to the selection of meta parameters.

Methane (CH₄) based combustibles, such as Natural Gas (NG) and BioGas (BG), are considered bridge fuels towards a decarbonized global energy system. NG emits less CO₂ during combustion than other fossil fuels and BG can be produced from organic waste. However, at BG production sites, leaks are common and CH₄ can escape through fissures in pipes and insulation layers. While by regulation BG producers shall issue monthly CH₄ emission reports, measurements are sparsely collected, only at a few predefined locations. Due to the high global warming potential of CH₄, efficient leakage detection systems are critical. We present a robotics approach to localize CH₄ leaks. In Robot assisted Gas Tomography (RGT), a mobile robot is equipped with remote gas sensors to create gas distribution maps, which can be used to infer the location of emitting sources. Spectroscopy based remote gas sensors report integral concentrations, which means that the measurements are spatially unresolved, with neither information regarding the gas distribution over the optical path nor the length of the s beam. Thus, RGT fuses different sensing modalities, such as range sensors for robot localization and ray tracing, in order to infer plausible gas distribution models that explain the acquired integral concentration measurements.

The ability to produce truthful maps of the distribution of one or more gases is beneficial for applications ranging from environmental monitoring to mines and industrial plants surveillance. Realistic environments are often too complicated for applying analytical gas plume models or performing reliable CFD simulations, making data-driven statistical gas distribution models the most attractive alternative. However, statistical models for gas distribution modelling, often rely on a set of meta-parameters that need to be learned from the data through Cross Validation (CV) techniques. CV techniques are computationally expensive and therefore need to be computed offline. As a faster alternative, we propose a parameter selection method based on Virtual Leave-One-Out Cross Validation (VLOOCV) that enables online learning of meta-parameters. In particular, we consider the Kernel DM+V, one of the most well studied algorithms for statistical gas distribution mapping, which relies on a meta-parameter, the kernel bandwidth. We validate the proposed VLOOCV method on a set of indoor and outdoor experiments where a mobile robot with a Photo Ionization Detector (PID) was collecting gas measurements. The approximation provided by the proposed VLOOCV method achieves very similar results to plain Cross Validation at a fraction of the computational cost. This is an important step in the development of on-line statistical gas distribution modelling algorithms.

Gas distribution modelling constitutes an ideal application area for mobile robots, which – as intelligent mobile gas sensors – offer several advantages compared to stationary sensor networks. In this paper we propose the Kernel DM+V algorithm to learn a statistical 2-d gas distribution model from a sequence of localized gas sensor measurements. The algorithm does not make strong assumptions about the sensing locations and can thus be applied on a mobile robot that is not primarily used for gas distribution monitoring, and also in the case of stationary measurements. Kernel DM+V treats distribution modelling as a density estimation problem. In contrast to most previous approaches, it models the variance in addition to the distribution mean. Estimating the predictive variance entails a significant improvement for gas distribution modelling since it allows to evaluate the model quality in terms of the data likelihood. This offers a solution to the problem of ground truth evaluation, which has always been a critical issue for gas distribution modelling. Estimating the predictive variance also provides the means to learn meta parameters and to suggest new measurement locations based on the current model. We derive the Kernel DM+V algorithm and present a method for learning the hyper-parameters. Based on real world data collected with a mobile robot we demonstrate the consistency of the obtained maps and present a quantitative comparison, in terms of the data likelihood of unseen samples, with an alternative approach that estimates the predictive variance.

In this paper we introduce a novel gas distribution mapping algorithm, Bayesian Spatial Event Distribution (BASED), that, instead of modeling the spatial distribution of the gas concentration, models the spatial distribution of events of detection and non-detection of a target gas. The proposed algorithm is based on the Bayesian inference framework and models the likelihood of events at a certain location with a Bernoulli distribution. In order to avoid overfitting a Bayesian approach is used with a beta distribution prior for the parameter u that governs the Bernoulli distribution. In this way, the posterior distribution maintains the same form of the prior, i.e. will be a beta distribution, enabling a simple approach for sequential learning. To learn a field of beta distributions, we discretize the inspection area into a grid map and extrapolate from local measurements using Gaussian kernels. We demonstrate the proposed algorithm for different sensors mounted on a mobile robot and show how qualitatively similar maps are obtained from very different gas sensors.

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 for the predicted concentrations. This is particularly important since exact calibration is hard to obtain due to the chaotic nature that dominates gas dispersal. The proposed approach has been tested with an experimental setup where an array of MOX sensors and a Photo Ionization Detector (PID) are placed downwind w.r.t. the gas source. The PID is used to obtain ground truth concentration. Comparison with standard calibration methods demonstrates the advantage of the proposed approach.

In this work is used the two-dimensional discrete wavelet transform as a feature extractor of time responses from a porous silicon optical gas sensor for gas identification. The wavelet decomposition allows us to have a more in-deep sight of the sensor response. In addition, using a linear support vector machine (SVM) as classifier we evaluate our approach for a six-analyte discrimination problem.

 The detection of changes in the response of metal oxide (MOX) gas sensors deployed in an open sampling system is a hard problem. It is relevant for applications such as gas leak detection in mines or large-scale pollution monitoring where it is impractical to continuously store or transfer sensor readings and reliable calibration is hard to achieve. Under these circumstances, it is desirable to detect points in the signal where a change indicates a significant event, e.g. the presence of gas or a sudden change of concentration. The key idea behind the proposed change detection approach is that a change in the emission modality of a gas source appears locally as an exponential function in the response of MOX sensors due to their long response and recovery times. The algorithm proposed in this paper, rTREFEX, is an extension of the previously proposed TREFEX algorithm. rTREFEX interprets the sensor response by fitting piecewise exponential functions with different time constants for the response and recovery phase. The number of exponentials, which has to be kept as low as possible, is determined automatically using an iterative approach that solves a sequence of convex optimization problems based on l₁-norm. The algorithm is evaluated with an experimental setup where a gas source changes in intensity, compound, and mixture ratio, and the gas source is delivered to the sensors exploiting natural advection and turbulence mechanisms. rTREFEX is compared against the previously proposed TREFEX, which already proved superior to other algorithms.

Many applications of metal oxide gas sensors can benefit from reliable algorithmsto detect significant changes in the sensor response. Significant changes indicate a changein the emission modality of a distant gas source and occur due to a sudden change ofconcentration or exposure to a different compound. As a consequence of turbulent gastransport and the relatively slow response and recovery times of metal oxide sensors,their response in open sampling configuration exhibits strong fluctuations that interferewith the changes of interest. In this paper we introduce TREFEX, a novel change pointdetection algorithm, especially designed for metal oxide gas sensors in an open samplingsystem. TREFEX models the response of MOX sensors as a piecewise exponentialsignal and considers the junctions between consecutive exponentials as change points. Weformulate non-linear trend filtering and change point detection as a parameter-free convexoptimization problem for single sensors and sensor arrays. We evaluate the performanceof the TREFEX algorithm experimentally for different metal oxide sensors and severalgas emission profiles. A comparison with the previously proposed GLR method shows aclearly superior performance of the TREFEX algorithm both in detection performance andin estimating the change time.

Detecting changes in the response of metal oxide (MOX) gas sensors deployed in an open sampling system is a hard problem. It is relevant for applicationssuch as gas leak detection in coal mines[1],[2] or large scale pollution monitoring [3],[4] where it is unpractical to continuously store or transfer sensor readings and reliable calibration is hard to achieve. Under these circumstances it is desirable to detect points in the signal where a change indicates a significant event, e.g. the presence of gas or a sudden change of concentration. The key idea behind the proposed change detection approach isthat a change in the emission modality of a gas source appears locally as an exponential function in the response of MOX sensors due to their long response and recovery times. The proposed method interprets the sensor responseby fitting piecewise exponential functions with different time constants for the response and recovery phase. The number of exponentials is determined automatically using an approximate method based on the L1-norm. This asymmetric exponential trend filtering problem is formulated as a convex optimization problem, which is particularly advantageous from the computational point of view. The algorithm is evaluated with an experimental setup where a gas source changes in intensity, compound, and mixture ratio, and it is compared against the previously proposed Generalized Likelihood Ratio (GLR) based algorithm [6].

In this article we present an algorithm for online detection of change points in the response of an array of metal oxide (MOX) gas sensors deployed in an open sampling system.True change points occur due to changes in the emission modality of the gas source. The main challenge for change point detection in an open sampling system is the chaotic nature of gas dispersion, which causes fluctuations in the sensor response that are not related to changes in the gas source. These fluctuations should not be considered change points in the sensor response. The presented algorithm is derived from the well known Generalized Likelihood Ratio algorithm and it is used both on the output of a single sensor as well on the output of two or more sensors on the array. The algorithm is evaluated with an experimental setup where a gas source changes in intensity, compound, or mixture ratio. The performance measures considered are the detection rate, the number of false alarms and the delay of detection.

We address the problem of detecting changes in the activity of a distant gas source from the response of an array of metal oxide (MOX) gas sensors deployed in an open sampling system. The main challenge is the turbulent nature of gas dispersion and the response dynamics of the sensors. We propose a change point detection approach and evaluate it on individual gas sensors in an experimental setup where a gas source changes in intensity, compound, or mixture ratio. We also introduce an efficient sensor selection algorithm and evaluate the change point detection approach with the selected sensor array subsets.

Chemical plume source localization algorithms can be classified either as reactive plume tracking or gas distribution mapping approaches. Here, we focus on gas distribution mapping methods where the robot does not need to track the plume to find the source and can be used for other tasks. Probabilistic mapping approaches have been previously applied to real-world data successfully; e.g., in the approach proposed by Pang and Farrell. Instead of the quasi-continuous gas measurement values, this algorithm considers events (detections and non-detections) based on whether the sensor response is above or below a threshold to update recursively a source probability grid map; thus, discarding important information. We developed an extension of this event-based approach, integrating chemical concentrations directly instead of binary information. In this work, both algorithms are compared using real-world data obtained from a photo-ionization detector (PID), a non-selective gas sensor, and an anemometer in real environments. We validate simulation results and demonstrate that the concentration-based approach is more accurate in terms of a higher probability at the ground truth source location, a smaller distance between the probability maximum and the source location, and a more peaked probability distribution, measured in terms of the overall entropy.

In this paper we introduce a novel gas distribution mapping algorithm, Bayesian Spatial Event Distribution (BASED), that, instead of modeling the spatial distribution of a quasi-continuous gas concentration, models the spatial distribution of gas events, for example detection and non-detection of a target gas. The proposed algorithm is based on the Bayesian Inference framework and models the likelihood of events at a certain location with a Bernoulli distribution. In order to avoid overfitting, a Bayesian approach is used with a beta distribution prior for the parameter μ that governs the Bernoulli distribution. In this way, the posterior distribution maintains the same form of the prior, i.e., will be a beta distribution as well, enabling a simple approach for sequential learning. To learn a map composed of beta distributions, we discretize the inspection area into a grid and extrapolate from local measurements using Gaussian kernels. We demonstrate the proposed algorithm for MOX sensors and a photo ionization detector mounted on a mobile robot and show how qualitatively similar maps are obtained from very different gas sensors.

The problem addressed in this thesis is discrimination of gases with an array of partially selective gas sensors. Metal oxide gas sensors are the most common gas sensing technology since they have, compared to other gas sensing technologies, a high sensitivity to the target compounds, a fast response time,they show a good stability of the response over time and they are commercially available. One of the most severe limitation of metal oxide gas sensors is the scarce selectivity, that means that they do not respond only to the compound for which they are optimized but also to other compounds. One way to enhance the selectivity of metal oxide gas sensors is to build an array of sensorswith different, and partially overlapping, selectivities and then analyze the response of the array with a pattern recognition algorithm. The concept of anarray of partially selective gas sensors used together with a pattern recognition algorithm is known as an electronic nose (e-nose).In this thesis the attention is focused on e-nose applications related mobile robotics. A mobile robot equipped with an e-nose can address tasks like environmental monitoring, search and rescue operations or exploration of hazardous areas. In e-noses mounted on mobile robots the sensing array is most often directly exposed to the environment without the use of a sensing chamber.This choice is often made because of constraints in weight, costs and because the dynamic response obtained by the direct interaction of the sensors with the gas plume contains valuable information. However, this setup introduces additional challenges due to the gas dispersion that characterize natural environments.Turbulent and chaotic gas dispersal causes the array of sensors to be exposed to rapid changes in concentration that cause the sensor response to behighly dynamic and to seldom reach a steady state. Therefore the discriminationof gases has to be performed on features extracted from the dynamics of the signal. The problem is further complicated by variations in temperature and humidity, physical variables to which metal oxide gas sensors are crossensitive.For these reasons the problem of discrimination of gases when an array of sensors is directly exposed to the environment is different from when the array of sensors is in a controlled chamber.

This thesis is a compilation of papers whose contributions are two folded.On one side new algorithms for discrimination of gases with an array of sensors directly exposed to the environment are presented. On the other side, innovative experimental setups are proposed. These experimental setups enable the collection of high quality data that allow a better insight in the problem of discrimination of gases with mobile robots equipped with an e-nose. The algorithmic contributions start with the design and validation of a gas discrimination algorithm for gas sensors array directly exposed to the environment. The algorithmis then further developed in order to be able to run online on a robot, thereby enabling the possibility of creating an olfactory driven path-planning strategy. Additional contributions aim at maximizing the generalization capabilitiesof the gas discrimination algorithm with respect to variations in the environmental conditions. First an approach in which the odor discrimination is performed by an ensemble of linear classifiers is considered. Then a feature selection method that aims at finding a feature set that is insensitive to variations in environmental conditions is designed. Finally, a further contribution in this thesis is the design of a pattern recognition algorithm for identification of bacteria from blood vials. In this case the array of gas sensors was deployed ina controlled sensing chamber.

Robots with gas sensing capabilities can address tasks like monitoring of polluted areas, detection of gas leaks, exploration of hazardous zones or search for explosives. Most of the currently available gas sensing technologies suffer from a number of shortcomings like lack of selectivity (the sensor responds to more than one chemical compound), slow response, drift in the response, and cross-sensitivity to physical variables like temperature and humidity. The main topic of this dissertation is the discrimination of gases, therefore the scarce selectivity and slow response are the limitations of direct concern. One of the possible solutions to overcome the poor selectivity of a single sensor is to use an array of gas sensors and to interpret the response of the whole array using signal processing techniques and pattern recognition algorithms. This is an established technology as long as the sensors are placed in a measuring chamber. However, discrimination of gases with a mobile robot presents additional challenges because the sensors are directly exposed to the highly dynamic environment to be analyzed. Given the slow dynamics of the sensors, the steady-state of the response is never achieved and therefore the discrimination has to be performed on the transient phase. The contributions presented in the summarized thesis focus around the design of algorithms for gas identification in the transient phase, thus they are particularly suited to mobile robotics applications.

This paper investigates the classification of odours using an electronic nose mounted on a mobile robot. The samples are collected as the robot explores the environment. Under such conditions, the sensor response differs from typical three phase sampling processes. In this paper, we focus particularly on the classification problem and how it is influenced by the movement of the robot. To cope with these influences, an algorithm consisting of an ensemble of classifiers is resented. Experimental results show that this algorithm increases classification performance compared to other traditional classification methods.

Classification of odours with an array of gas sensors mounted on a mobile robot is a challenging and still relatively unexplored topic. Mobile robots able to classify an odour could navigate to a specific source or isolate high concentration areas in applications such as environmental monitoring. A key aspect to classification is to be able to process the data collected while moving the robot and using a simple and compact sensor system. In order to achieve this, we present a classification algorithm that is based in the transient response from the sensors. An analysis of how classification results vary with regards to the movement of the robot is provided and subsequently the experimental validations show that the classification performance depends more on how

the robot traverses the odour plume and the quality of the transient than on the distance from the source location. The experimental validation has been done in a large unmodified indoor environment.

In this paper, we investigate the classification performance of an electronic nose system, based on tin dioxide gas sensors. In contrast to previous studies, the electronic nose is mounted on a mobile platform and samples are analyzed using only transient information in the signals. The motivation behind this work is to explore the feasibility of using electronic nose devices for odour classification in a number of future application domains which require fast and possibly real-time odour identification. To perform transient based analysis of the signals, a comparative study of different methods for feature extraction was performed. Additionally, the application of a relevance vector machine classifier is explored to further analyze the classification performance based on quality of the obtained samples. The results presented in this study can be used for the development of electronic nose devices particularly suitable for environmental monitoring applications.

In this paper we investigate how a mobile robot equipped with tin dioxide gas sensors and an anemometer can use an online classification algorithm in order to improve the exploration strategy. The purpose of the platform is to establish the character of a gas source with accuracy while minimizing the time required for exploration. For this to be possible, the output of the classification algorithm is probabilistic, feeding in a sequence of posterior probabilities to a path planner. To further assist path planning, a 3d-ultrasonic anemometer is available which give indication on the average wind speed and direction. In addition to evaluating different olfaction driven path planning strategies, experimental validations also evaluate the classification algorithms and its application to different environments with varying characteristics.

In this paper, we introduce a method for identification of bacteria in human blood culture samples using an electronic nose. The method uses features, which capture the static (steady state) and dynamic (transient) properties of the signal from the gas sensor array and proposes a means to ensemble results from consecutive samples. The underlying mechanism for ensembling is based on an estimation of posterior probability, which is extracted from a support vector machine classifier. A large dataset representing ten different bacteria cultures has been used to validate the presented methods. The results detail the performance of the proposed algorithm and show that through ensembling decisions on consecutive samples, significant reliability in classification accuracy can be achieved.

Applications related to industrial plant surveillance and environmental monitoring often require the creation of gas distribution maps (GDM). In this paper an approach for creating a gas distribution map using a Tunable Diode Laser Absorption Spectroscopy (TDLAS) sensor and a laser range scanner mounted on a pan tilt unit is presented. The TDLAS sensor can remotely sense the target gas, in this case methane, requiring novel GDM algorithms compared to the ones developed for traditional in-situ chemical sensors. The presented setup makes it possible to create a 3D model of the environment and to calculate the path travelled by the TDLAS beam. The knowledge of the beam path is of crucial importance since a TDLAS sensor provides an integral measurement of the gas concentration over that path. An efficient GDM algorithm based on a quadratic programming formulation is proposed. The approach is tested in an indoor scenario where transparent bottles filled with methane are successfully localized.

Odour discrimination with a sensor array directly exposed to the environment is of great interest in many applications ranging from environmental monitoring to search and rescue and exploration of hazardous areas. Metal oxide based sensors are typically used in such applications for gas detection as they are compact, low costing and exhibit fast response time to an analyte. Given the characteristics of the metal oxide sensors as well as the chaotic nature of the airflow in a natural environment, it has been assumed that a reliable odour discrimination system working in this condition has to work with features that capture the transient characteristics of the signal. In this work we present an experimental setup that enables a deeper insight into transient-based analysis for open sampling systems. Observations on the  properties of the signal collected under a controlled experimental condition using an open sampling system are presented. These observations suggest that in a scenario in which the sensors are exposed to different compounds without the possibility to recover the baseline value in between a gas identification, a model of the dynamics of the system is needed and a notion of the sensor state should be maintained that captures the past history of the sensor response.

In this paper we analyze the problem of discrimination of gases with mobile robots. Previously, it has been shown that the conditions in which data is collected heavily influence the characteristics of the signal to be identified. As a result, the already difficult task of selecting features which characterize a gas is made more challenging by the absence of a steady state response. This is often due to the movement of the robot, and/or the physical properties of the environment, e. g., turbulent airflow creating patches and eddies in the plume. In this work we compare two approaches for feature selection which are able to consider explicitly the information on the experimental setup and optimize the subset of features used in the recognition process. The approaches are tested on a large data set collected with a mobile robot moving in different environments (outdoors and indoors). The results show that the classification performance is improved resulting in a higher average accuracy and lower variance in the accuracy across the different experimental setups.

In this paper we present initial experiments towards environmental monitoring with a mobile platform. A prototype of a pollution monitoring robot was set up which measures the gas distribution using an “electronic nose” and provides three dimensional wind measurements using an ultrasonic anemometer. We describe the design of the robot and the experimental setup used to run trials under varying environmental conditions. We then present the results of the gas distribution mapping. The trials which were carried out in three uncontrolled environments with very different properties:

an enclosed indoor area, a part of a long corridor with open ends and a high ceiling, and an outdoor scenario are presented and discussed.

Chemo-resistive transduction is essential for capturing the spatio-temporal structure of chemical compounds dispersed in different environments. Due to gas dispersion mechanisms, namely diffusion, turbulence and advection, the sensors in an open sampling system, i.e. directly exposed to the environment to be monitored, are exposed to low concentrations of gases with many fluctuations making, as a consequence, the identification and monitoring of the gases even more complicated and challenging than in a controlled laboratory setting. Therefore, tuning the value of the operating temperature becomes crucial for successfully identifying and monitoring the pollutant gases, particularly in applications such as exploration of hazardous areas, air pollution monitoring, and search and rescue I. In this study we demonstrate the benefit of optimizing the sensor's operating temperature when the sensors are deployed in an open sampling system, i.e. directly exposed to the environment to be monitored.

Chemo-resistive transduction presents practical advantages for capturing the spatio-temporal and structural organization of chemical compounds dispersed in different human habitats. In an open sampling system, however, where the chemo-sensory elements are directly exposed to the environment being monitored, the identification and monitoring of chemical substances present a more difficult challenge due to the dispersion mechanisms of gaseous chemical analytes, namely diffusion, turbulence, and advection. The success of such actively changeable practice is influenced by the adequate implementation of algorithmically driven formalisms combined with the appropriate design of experimental protocols. On the basis of this functional joint-formulation, in this study we examine an innovative methodology based on the inhibitory processing mechanisms encountered in the structural assembly of the insect's brain, namely Inhibitory Support Vector Machine (ISVM) applied to training a sensor array platform and evaluate its capabilities relevant to odor detection and identification under complex environmental conditions. We generated - and made publicly available - an extensive and unique dataset with a chemical detection platform consisting of 72 conductometric metal-oxide based chemical sensors in a custom-designed wind tunnel test-bed facility to test our methodology. Our findings suggest that the aforementioned methodology can be a valuable tool to guide the decision of choosing the training conditions for a cost-efficient system calibration as well as an important step toward the understanding of the degradation level of the sensory system when the environmental conditions change.

In this paper, we present our initial experiments to collect a database for studying mobile robot olfaction. Mobile robots with olfactory sensing capabilities are expected to be used in various applications including gas distribution mapping and gas source localization. Owing to the turbulent nature of the airflow field and the gas distribution, these robots must be equipped with algorithms that can cope with chaotic environments. Since it is important to check the applicability of such algorithms in a diversity of environments, we propose to build a database with which the users can test the performances of their own algorithms in various environments. The database collected so far consists of two parts: a basic data set collected in a well-characterized controlled indoor environment and applied data sets collected in uncontrolled indoor and outdoor environments. A result of applying the database for testing a gas-source localization algorithm are shown as an example. We believe that such database will accelerate the research advancements on mobile robot olfaction.