oru.sePublications
Change search
Link to record
Permanent link

Direct link
BETA
Publications (10 of 31) Show all publications
Fan, H., Hernandez Bennetts, V., Schaffernicht, E. & Lilienthal, A. (2018). A cluster analysis approach based on exploiting density peaks for gas discrimination with electronic noses in open environments. Sensors and actuators. B, Chemical, 259, 183-203
Open this publication in new window or tab >>A cluster analysis approach based on exploiting density peaks for gas discrimination with electronic noses in open environments
2018 (English)In: Sensors and actuators. B, Chemical, ISSN 0925-4005, E-ISSN 1873-3077, Vol. 259, p. 183-203Article in journal (Refereed) Published
Abstract [en]

Gas discrimination in open and uncontrolled environments based on smart low-cost electro-chemical sensor arrays (e-noses) is of great interest in several applications, such as exploration of hazardous areas, environmental monitoring, and industrial surveillance. Gas discrimination for e-noses is usually based on supervised pattern recognition techniques. However, the difficulty and high cost of obtaining extensive and representative labeled training data limits the applicability of supervised learning. Thus, to deal with the lack of information regarding target substances and unknown interferents, unsupervised gas discrimination is an advantageous solution. In this work, we present a cluster-based approach that can infer the number of different chemical compounds, and provide a probabilistic representation of the class labels for the acquired measurements in a given environment. Our approach is validated with the samples collected in indoor and outdoor environments using a mobile robot equipped with an array of commercial metal oxide sensors. Additional validation is carried out using a multi-compound data set collected with stationary sensor arrays inside a wind tunnel under various airflow conditions. The results show that accurate class separation can be achieved with a low sensitivity to the selection of the only free parameter, namely the neighborhood size, which is used for density estimation in the clustering process.

Place, publisher, year, edition, pages
Amsterda, Netherlands: Elsevier, 2018
Keywords
Gas discrimination, environmental monitoring, metal oxide sensors, cluster analysis, unsupervised learning
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-63468 (URN)10.1016/j.snb.2017.10.063 (DOI)000424877600023 ()2-s2.0-85038032167 (Scopus ID)
Projects
SmokBot
Funder
EU, Horizon 2020, 645101
Available from: 2017-12-19 Created: 2017-12-19 Last updated: 2018-09-17Bibliographically approved
Banaee, H., Schaffernicht, E. & Loutfi, A. (2018). Data-Driven Conceptual Spaces: Creating Semantic Representations for Linguistic Descriptions of Numerical Data. The journal of artificial intelligence research, 63, 691-742
Open this publication in new window or tab >>Data-Driven Conceptual Spaces: Creating Semantic Representations for Linguistic Descriptions of Numerical Data
2018 (English)In: The journal of artificial intelligence research, ISSN 1076-9757, E-ISSN 1943-5037, Vol. 63, p. 691-742Article in journal (Refereed) Published
Abstract [en]

There is an increasing need to derive semantics from real-world observations to facilitate natural information sharing between machine and human. Conceptual spaces theory is a possible approach and has been proposed as mid-level representation between symbolic and sub-symbolic representations, whereby concepts are represented in a geometrical space that is characterised by a number of quality dimensions. Currently, much of the work has demonstrated how conceptual spaces are created in a knowledge-driven manner, relying on prior knowledge to form concepts and identify quality dimensions. This paper presents a method to create semantic representations using data-driven conceptual spaces which are then used to derive linguistic descriptions of numerical data. Our contribution is a principled approach to automatically construct a conceptual space from a set of known observations wherein the quality dimensions and domains are not known a priori. This novelty of the approach is the ability to select and group semantic features to discriminate between concepts in a data-driven manner while preserving the semantic interpretation that is needed to infer linguistic descriptions for interaction with humans. Two data sets representing leaf images and time series signals are used to evaluate the method. An empirical evaluation for each case study assesses how well linguistic descriptions generated from the conceptual spaces identify unknown observations. Furthermore,  comparisons are made with descriptions derived on alternative approaches for generating semantic models.

Place, publisher, year, edition, pages
AAAI Press, 2018
Keywords
conceptual spaces, concept formation, semantic representation, linguistic description, natural language generation
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-70433 (URN)10.1613/jair.1.11258 (DOI)
Available from: 2018-12-04 Created: 2018-12-04 Last updated: 2018-12-05Bibliographically approved
Wiedemann, T., Shutin, D., Hernandez Bennetts, V., Schaffernicht, E. & Lilienthal, A. (2017). Bayesian Gas Source Localization and Exploration with a Multi-Robot System Using Partial Differential Equation Based Modeling. In: 2017 ISOCS/IEEE International Symposium on Olfaction and Electronic Nose (ISOEN 2017): Proceedings. Paper presented at International Symposium on Olfaction and Electronic Nose (ISOEN 2017), Montreal, Canada, May 28-31, 2017 (pp. 122-124).
Open this publication in new window or tab >>Bayesian Gas Source Localization and Exploration with a Multi-Robot System Using Partial Differential Equation Based Modeling
Show others...
2017 (English)In: 2017 ISOCS/IEEE International Symposium on Olfaction and Electronic Nose (ISOEN 2017): Proceedings, 2017, p. 122-124Conference paper, Published paper (Refereed)
Abstract [en]

Here we report on active water sampling devices forunderwater chemical sensing robots. Crayfish generate jetlikewater currents during food search by waving theflagella of their maxillipeds. The jets generated toward theirsides induce an inflow from the surroundings to the jets.Odor sample collection from the surroundings to theirolfactory organs is promoted by the generated inflow.Devices that model the jet discharge of crayfish have beendeveloped to investigate the effectiveness of the activechemical sampling. Experimental results are presented toconfirm that water samples are drawn to the chemicalsensors from the surroundings more rapidly by using theaxisymmetric flow field generated by the jet discharge thanby centrosymmetric flow field generated by simple watersuction. Results are also presented to show that there is atradeoff between the angular range of chemical samplecollection and the sample collection time.

National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-60688 (URN)9781509023936 (ISBN)9781509023929 (ISBN)
Conference
International Symposium on Olfaction and Electronic Nose (ISOEN 2017), Montreal, Canada, May 28-31, 2017
Available from: 2017-09-08 Created: 2017-09-08 Last updated: 2018-08-06Bibliographically approved
Canelhas, D. R., Schaffernicht, E., Stoyanov, T., Lilienthal, A. & Davison, A. J. (2017). Compressed Voxel-Based Mapping Using Unsupervised Learning. Robotics, 6(3), Article ID 15.
Open this publication in new window or tab >>Compressed Voxel-Based Mapping Using Unsupervised Learning
Show others...
2017 (English)In: Robotics, E-ISSN 2218-6581, Vol. 6, no 3, article id 15Article in journal (Refereed) Published
Abstract [en]

In order to deal with the scaling problem of volumetric map representations, we propose spatially local methods for high-ratio compression of 3D maps, represented as truncated signed distance fields. We show that these compressed maps can be used as meaningful descriptors for selective decompression in scenarios relevant to robotic applications. As compression methods, we compare using PCA-derived low-dimensional bases to nonlinear auto-encoder networks. Selecting two application-oriented performance metrics, we evaluate the impact of different compression rates on reconstruction fidelity as well as to the task of map-aided ego-motion estimation. It is demonstrated that lossily reconstructed distance fields used as cost functions for ego-motion estimation can outperform the original maps in challenging scenarios from standard RGB-D (color plus depth) data sets due to the rejection of high-frequency noise content.

Place, publisher, year, edition, pages
Basel, Switzerland: MDPI AG, 2017
Keywords
3D mapping, TSDF, compression, dictionary learning, auto-encoder, denoising
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:oru:diva-64420 (URN)10.3390/robotics6030015 (DOI)000419218300002 ()2-s2.0-85030989493 (Scopus ID)
Note

Funding Agencies:

European Commission  FP7-ICT-270350 

H-ICT  732737 

Available from: 2018-01-19 Created: 2018-01-19 Last updated: 2018-01-19Bibliographically approved
Kucner, T. P., Magnusson, M., Schaffernicht, E., Hernandez Bennetts, V. M. & Lilienthal, A. (2017). Enabling Flow Awareness for Mobile Robots in Partially Observable Environments. IEEE Robotics and Automation Letters, 2(2), 1093-1100
Open this publication in new window or tab >>Enabling Flow Awareness for Mobile Robots in Partially Observable Environments
Show others...
2017 (English)In: IEEE Robotics and Automation Letters, ISSN 2377-3766, E-ISSN 1949-3045, Vol. 2, no 2, p. 1093-1100Article in journal (Refereed) Published
Abstract [en]

Understanding the environment is a key requirement for any autonomous robot operation. There is extensive research on mapping geometric structure and perceiving objects. However, the environment is also defined by the movement patterns in it. Information about human motion patterns can, e.g., lead to safer and socially more acceptable robot trajectories. Airflow pattern information allow to plan energy efficient paths for flying robots and improve gas distribution mapping. However, modelling the motion of objects (e.g., people) and flow of continuous media (e.g., air) is a challenging task. We present a probabilistic approach for general flow mapping, which can readily handle both of these examples. Moreover, we present and compare two data imputation methods allowing to build dense maps from sparsely distributed measurements. The methods are evaluated using two different data sets: one with pedestrian data and one with wind measurements. Our results show that it is possible to accurately represent multimodal, turbulent flow using a set of Gaussian Mixture Models, and also to reconstruct a dense representation based on sparsely distributed locations.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2017
Keywords
Field robots; mapping; social human-robot interaction
National Category
Robotics
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-55174 (URN)10.1109/LRA.2017.2660060 (DOI)000413736600094 ()
Projects
ILIAD
Funder
Knowledge Foundation, 20140220 20130196
Note

Funding Agencies:

EU project SPENCER  ICT-2011-600877 

H2020-ICT project SmokeBot  645101 

H2020-ICT project ILIAD  732737 

Available from: 2017-02-01 Created: 2017-02-01 Last updated: 2017-11-23Bibliographically approved
Vuka, M., Schaffernicht, E., Schmuker, M., Hernandez Bennetts, V., Amigoni, F. & Lilienthal, A. J. (2017). Exploration and Localization of a Gas Source with MOX Gas Sensorson a Mobile Robot: A Gaussian Regression Bout Amplitude Approach. In: 2017 ISOCS/IEEE International Symposium on Olfaction and Electronic Nose (ISOEN 2017): Proceedings. Paper presented at IEEE International Symposium on Olfaction and Electronic Nose (ISOEN 2017), Montreal, QC, Canada, May 28-31, 2017 (pp. 164-166). IEEE
Open this publication in new window or tab >>Exploration and Localization of a Gas Source with MOX Gas Sensorson a Mobile Robot: A Gaussian Regression Bout Amplitude Approach
Show others...
2017 (English)In: 2017 ISOCS/IEEE International Symposium on Olfaction and Electronic Nose (ISOEN 2017): Proceedings, IEEE, 2017, p. 164-166Conference paper, Published paper (Refereed)
Abstract [en]

Mobile robot olfaction systems combine gas sensorswith mobility provided by robots. They relief humansof dull, dirty and dangerous tasks in applications such assearch & rescue or environmental monitoring. We address gassource localization and especially the problem of minimizingexploration time of the robot, which is a key issue due toenergy constraints. We propose an active search approach forrobots equipped with MOX gas sensors and an anemometer,given an occupancy map. Events of rapid change in the MOXsensor signal (“bouts”) are used to estimate the distance to agas source. The wind direction guides a Gaussian regression,which interpolates distance estimates. The contributions of thispaper are two-fold. First, we extend previous work on gassource distance estimation with MOX sensors and propose amodification to cope better with turbulent conditions. Second,we introduce a novel active search gas source localizationalgorithm and validate it in a real-world environment.

Place, publisher, year, edition, pages
IEEE, 2017
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-60672 (URN)10.1109/ISOEN.2017.7968898 (DOI)2-s2.0-85027226540 (Scopus ID)
Conference
IEEE International Symposium on Olfaction and Electronic Nose (ISOEN 2017), Montreal, QC, Canada, May 28-31, 2017
Available from: 2017-09-08 Created: 2017-09-08 Last updated: 2018-08-06Bibliographically approved
Fan, H., Arain, M. A., Hernandez Bennetts, V., Schaffernicht, E. & Lilienthal, A. J. (2017). Improving Gas Dispersal Simulation For Mobile Robot Olfaction: Using Robotcreatedoccupancy Maps And Remote Gas Sensors In The Simulation Loop. In: 2017 ISOCS/IEEE International Symposium on Olfaction andElectronic Nose (ISOEN 2017) Proceedings: . Paper presented at 2017 ISOCS/IEEE International Symposium on Olfaction and Electronic Nose (ISOEN) 28-31 May 2017 Montreal, QC, Canada. IEEE conference proceedings, Article ID 17013581.
Open this publication in new window or tab >>Improving Gas Dispersal Simulation For Mobile Robot Olfaction: Using Robotcreatedoccupancy Maps And Remote Gas Sensors In The Simulation Loop
Show others...
2017 (English)In: 2017 ISOCS/IEEE International Symposium on Olfaction andElectronic Nose (ISOEN 2017) Proceedings, IEEE conference proceedings, 2017, article id 17013581Conference paper, Published paper (Refereed)
Abstract [en]

Mobile robot platforms equipped with olfaction systems have been used in many gas sensing applications. However, in-field validation of mobile robot olfaction systems is time consuming, expensive, cumbersome and lacks repeatability. In order to address these issues, simulation tools are used. However, the available mobile robot olfaction simulations lack models for remote gas sensors, and the possibility to import geometrical representations of actual real-world environments in a convenient way. In this paper, we describe extensions to an open-source CFD-based filament gas dispersal simulator. These improvements arrow to use robot-created occupancy maps and offer remote sensing capabilities in the simulation loop. We demonstrate the novel features in an example application: we created a 3D map a complex indoor environment, and performed a gas emission monitoring task with a Tunable Diode Laser Absorption Spectroscopy based remote gas sensor in a simulated version of the environment.

Place, publisher, year, edition, pages
IEEE conference proceedings, 2017
National Category
Computer Sciences Robotics
Identifiers
urn:nbn:se:oru:diva-60633 (URN)10.1109/ISOEN.2017.7968874 (DOI)978-1-5090-2392-9 (ISBN)978-1-5090-2393-6 (ISBN)
Conference
2017 ISOCS/IEEE International Symposium on Olfaction and Electronic Nose (ISOEN) 28-31 May 2017 Montreal, QC, Canada
Available from: 2017-09-06 Created: 2017-09-06 Last updated: 2018-02-01Bibliographically approved
Arain, M. A., Fan, H., Hernandez Bennetts, V., Schaffernicht, E. & Lilienthal, A. J. (2017). Improving Gas Tomography With Mobile Robots: An Evaluation of Sensing Geometries in Complex Environments. In: 2017 ISOCS/IEEE International Symposium on Olfaction andElectronic Nose (ISOEN 2017) Proceedings: . Paper presented at 2017 ISOCS/IEEE International Symposium on Olfaction and Electronic Nose (ISOEN) 28-31 May 2017 Montreal QC, Canada. , Article ID 7968895.
Open this publication in new window or tab >>Improving Gas Tomography With Mobile Robots: An Evaluation of Sensing Geometries in Complex Environments
Show others...
2017 (English)In: 2017 ISOCS/IEEE International Symposium on Olfaction andElectronic Nose (ISOEN 2017) Proceedings, 2017, article id 7968895Conference paper, Published paper (Refereed)
Abstract [en]

An accurate model of gas emissions is of high importance in several real-world applications related to monitoring and surveillance. Gas tomography is a non-intrusive optical method to estimate the spatial distribution of gas concentrations using remote sensors. The choice of sensing geometry, which is the arrangement of sensing positions to perform gas tomography, directly affects the reconstruction quality of the obtained gas distribution maps. In this paper, we present an investigation of criteria that allow to determine suitable sensing geometries for gas tomography. We consider an actuated remote gas sensor installed on a mobile robot, and evaluated a large number of sensing configurations. Experiments in complex settings were conducted using a state-of-the-art CFD-based filament gas dispersal simulator. Our quantitative comparison yields preferred sensing geometries for sensor planning, which allows to better reconstruct gas distributions.

National Category
Computer Sciences Robotics
Identifiers
urn:nbn:se:oru:diva-60646 (URN)10.1109/ISOEN.2017.7968895 (DOI)978-1-5090-2392-9 (ISBN)978-1-5090-2393-6 (ISBN)
Conference
2017 ISOCS/IEEE International Symposium on Olfaction and Electronic Nose (ISOEN) 28-31 May 2017 Montreal QC, Canada
Available from: 2017-09-06 Created: 2017-09-06 Last updated: 2018-01-13Bibliographically approved
Xing, Y., Vincent, T. A., Cole, M., Gardner, J. W., Fan, H., Hernandez Bennetts, V., . . . Lilienthal, A. (2017). Mobile robot multi-sensor unit for unsupervised gas discrimination in uncontrolled environments. In: IEEE SENSORS 2017: Conference Proceedings. Paper presented at 16th IEEE Sensors Conference, Glasgow, Scotland, UK, October 29 - November 1, 2017 (pp. 1691-1693). New York: Institute of Electrical and Electronics Engineers (IEEE)
Open this publication in new window or tab >>Mobile robot multi-sensor unit for unsupervised gas discrimination in uncontrolled environments
Show others...
2017 (English)In: IEEE SENSORS 2017: Conference Proceedings, New York: Institute of Electrical and Electronics Engineers (IEEE), 2017, p. 1691-1693Conference paper, Published paper (Refereed)
Abstract [en]

In this work we present a novel multi-sensor unit to detect and discriminate unknown gases in uncontrolled environments. The unit includes three metal oxide (MOX) sensors with CMOS micro heaters, a plasmonic enhanced non-dispersive infra-red (NDIR) sensor, a commercial temperature humidity sensor, and a flow sensor. The proposed sensing unit was evaluated with plumes of gases (propanol, ethanol and acetone) in both, a laboratory setup on a gas testing bench and on-board a mobile robot operating in an indoor workshop. It offers significantly improved performance compared to commercial systems, in terms of power consumption, response time and physical size. We verified the ability to discriminate gases in an unsupervised manner, with data collected on the robot and high accuracy was obtained in the classification of propanol versus acetone (96%), and ethanol versus acetone (90%).

Place, publisher, year, edition, pages
New York: Institute of Electrical and Electronics Engineers (IEEE), 2017
Series
Proceedings of IEEE Sensors, ISSN 1930-0395
Keywords
Gas sensor, mobile robot, MOX, open sampling system, gas discrimination
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-64463 (URN)10.1109/ICSENS.2017.8234440 (DOI)000427677500564 ()2-s2.0-85044276510 (Scopus ID)978-1-5090-1012-7 (ISBN)978-1-5090-1013-4 (ISBN)
Conference
16th IEEE Sensors Conference, Glasgow, Scotland, UK, October 29 - November 1, 2017
Projects
SmokeBot
Funder
EU, Horizon 2020, 645101
Available from: 2018-01-23 Created: 2018-01-23 Last updated: 2018-04-25Bibliographically approved
Schaffernicht, E., Hernandez Bennetts, V. & Lilienthal, A. (2017). Mobile robots for learning spatio-temporal interpolation models in sensor networks - The Echo State map approach: The Echo State map approach. In: 2017 IEEE International Conference on Robotics and Automation (ICRA): . Paper presented at 2017 IEEE International Conference on Robotics and Automation (ICRA), Singapore, Singapore, May 27-June 3, 2017 (pp. 2659-2665). Institute of Electrical and Electronics Engineers (IEEE)
Open this publication in new window or tab >>Mobile robots for learning spatio-temporal interpolation models in sensor networks - The Echo State map approach: The Echo State map approach
2017 (English)In: 2017 IEEE International Conference on Robotics and Automation (ICRA), Institute of Electrical and Electronics Engineers (IEEE), 2017, p. 2659-2665Conference paper, Published paper (Refereed)
Abstract [en]

Sensor networks have limited capabilities to model complex phenomena occuring between sensing nodes. Mobile robots can be used to close this gap and learn local interpolation models. In this paper, we utilize Echo State Networks in order to learn the calibration and interpolation model between sensor nodes using measurements collected by a mobile robot. The use of Echo State Networks allows to deal with temporal dependencies implicitly, while the spatial mapping with a Gaussian Process estimator exploits the fact that Echo State Networks learn linear combinations of complex temporal dynamics. The resulting Echo State Map elegantly combines spatial and temporal cues into a single representation. We showcase the method in the exposure modeling task of building dust distribution maps for foundries, a challenge which is of great interest to occupational health researchers. Results from simulated data and real world experiments highlight the potential of Echo State Maps. While we focus on particulate matter measurements, the method can be applied for any other environmental variables like temperature or gas concentration.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2017
Keywords
Gaussian processes, learning (artificial intelligence), mobile robots, neurocontrollers, wireless sensor networks, Gaussian process estimator, echo state map approach, gas concentration, mobile robots, particulate matter measurement, sensor networks, spatio-temporal interpolation model learning, temperature concentration, Foundries, Interpolation, Mobile robots, Robot sensing systems, Wireless sensor networks
National Category
Robotics
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-63792 (URN)10.1109/ICRA.2017.7989310 (DOI)2-s2.0-85028014826 (Scopus ID)
Conference
2017 IEEE International Conference on Robotics and Automation (ICRA), Singapore, Singapore, May 27-June 3, 2017
Projects
RAISE
Funder
Knowledge Foundation, 20130196
Available from: 2018-01-03 Created: 2018-01-03 Last updated: 2018-01-09Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0002-0804-8637

Search in DiVA

Show all publications