Matching entries: 0
settings...
Bernardi RL, Berdja A, Guzmán CD, Torres-Torriti M and Roth MM (2021), "Restoration of images with a spatially varying PSF of the T80-S telescope optical model using neural networks", Monthly Notices of the Royal Astronomical Society., December, 2021. Vol. 510(3), pp. 4284-4294.
Abstract: Most image restoration methods in astronomy rely upon probabilistic tools that infer the best solution for a deconvolution problem. They achieve good performances when the point spread function (PSF) is spatially invariant in the image plane. However, this condition is not always satisfied in real optical systems. We propose a new method for the restoration of images affected by static and anisotropic aberrations using Deep Neural Networks that can be directly applied to sky images. The network is trained using simulated sky images corresponding to the T80-S Telescope optical model, a 80-cm survey imager at Cerro Tololo (Chile), which are synthesized using a Zernike polynomial representation of the optical system. Once trained, the network can be used directly on sky images, outputting a corrected version of the image that has a constant and known PSF across its field of view. The method is to be tested on the T80-S Telescope. We present the method and results on synthetic data.
BibTeX:
@article{Bernardi2021,
  author = {Bernardi, Rafael L and Berdja, Amokrane and Guzmán, Christian Dani and Torres-Torriti, Miguel and Roth, Martin M},
  title = {Restoration of images with a spatially varying PSF of the T80-S telescope optical model using neural networks},
  journal = {Monthly Notices of the Royal Astronomical Society},
  year = {2021},
  volume = {510},
  number = {3},
  pages = {4284-4294},
  url = {https://doi.org/10.1093/mnras/stab3400},
  doi = {10.1093/mnras/stab3400}
}
Prado AJ, Torres-Torriti M and Cheein FA (2021), "Distributed Tube-Based Nonlinear MPC for Motion Control of Skid-Steer Robots With Terra-Mechanical Constraints", IEEE Robotics and Automation Letters., October, 2021. Vol. 6(4), pp. 8045-8052.
BibTeX:
@article{Prado2021,
  author = {Prado, Alvaro J. and Torres-Torriti, Miguel and Cheein, Fernando A.},
  title = {Distributed Tube-Based Nonlinear MPC for Motion Control of Skid-Steer Robots With Terra-Mechanical Constraints},
  journal = {IEEE Robotics and Automation Letters},
  year = {2021},
  volume = {6},
  number = {4},
  pages = {8045-8052},
  doi = {10.1109/LRA.2021.3102328}
}
Yandun F, Torres-Torriti M and Auat Cheein F (2021), "Markov Chain Monte Carlo Parameter Estimation for Nonzero Slip Models of Wheeled Mobile Robots: A Skid-Steer Case Study", Journal of Mechanisms and Robotics., May, 2021. Vol. 13(5), pp. 1-19.
Abstract: An accurate modeling, simulation, and estimation of the wheel-terrain interaction and its effects on a robot movement plays a key role in control and navigation tasks, specially in constantly changing environments. We study the calibration of wheel slip models using Particle Markov Chain Monte Carlo methods to approximate the posterior distributions of their parameters. In contrast to classic identification approaches, considering the parameters as random variables allows to obtain a probability measure of the parameter estimations and subsequently propagate their uncertainty to wheel slip-related variables. Extensive simulation and experimental results showed that the proposed methodology can effectively get reliable posterior approximations from noisy sensor measurements in changing terrains. Validation tests also include the applicability assessment of the proposed methodology by comparing it with the integrated prediction error minimization methodology. Field results presented up to 66% of improvement in the robot motion prediction with the proposed calibration approach.
BibTeX:
@article{Yandun2021,
  author = {Yandun, Francisco and Torres-Torriti, Miguel and Auat Cheein, Fernando},
  title = {Markov Chain Monte Carlo Parameter Estimation for Nonzero Slip Models of Wheeled Mobile Robots: A Skid-Steer Case Study},
  journal = {Journal of Mechanisms and Robotics},
  year = {2021},
  volume = {13},
  number = {5},
  pages = {1--19},
  note = {050902, paper JMR-21-1027},
  url = {https://doi.org/10.1115/1.4051016},
  doi = {10.1115/1.4051016}
}
Guevara DJ, Gené-Mola J, Gregorio E, Torres-Torriti M, Reina G and Cheein FAA (2021), "Comparison of 3D scan matching techniques for autonomous robot navigation in urban and agricultural environments", Journal of Applied Remote Sensing., April, 2021. Vol. 15(2), pp. 1 - 23. SPIE.
Abstract: Global navigation satellite system (GNSS) is the standard solution for solving the localization problem in outdoor environments, but its signal might be lost when driving in dense urban areas or in the presence of heavy vegetation or overhanging canopies. Hence, there is a need for alternative or complementary localization methods for autonomous driving. In recent years, exteroceptive sensors have gained much attention due to significant improvements in accuracy and cost-effectiveness, especially for 3D range sensors. By registering two successive 3D scans, known as scan matching, it is possible to estimate the pose of a vehicle. This work aims to provide in-depth analysis and comparison of the state-of-the-art 3D scan matching approaches as a solution to the localization problem of autonomous vehicles. Eight techniques (deterministic and probabilistic) are investigated: iterative closest point (with three different embodiments), normal distribution transform, coherent point drift, Gaussian mixture model, support vector-parametrized Gaussian mixture and the particle filter implementation. They are demonstrated in long path trials in both urban and agricultural environments and compared in terms of accuracy and consistency. On the one hand, most of the techniques can be successfully used in urban scenarios with the probabilistic approaches that show the best accuracy. On the other hand, agricultural settings have proved to be more challenging with significant errors even in short distance trials due to the presence of featureless natural objects. The results and discussion of this work will provide a guide for selecting the most suitable method and will encourage building of improvements on the identified limitations.
BibTeX:
@article{Guevara2021,
  author = {Dario J. Guevara and Jordi Gené-Mola and Eduard Gregorio and Miguel Torres-Torriti and Giulio Reina and Fernando A. A. Cheein},
  title = {Comparison of 3D scan matching techniques for autonomous robot navigation in urban and agricultural environments},
  journal = {Journal of Applied Remote Sensing},
  publisher = {SPIE},
  year = {2021},
  volume = {15},
  number = {2},
  pages = {1 -- 23},
  url = {https://doi.org/10.1117/1.JRS.15.024508},
  doi = {10.1117/1.JRS.15.024508}
}
Guevara J, Arevalo-Ramirez T, Yandun F, Torres-Torriti M and Cheein FA (2020), "Point cloud-based estimation of effective payload volume for earthmoving loaders", Automation in Construction. Vol. 117, pp. 103207.
Abstract: Construction and mining require high levels of planning and productivity. Planning and management of operational targets and performance requires taking into account several variables, among which the amount of moved, loaded and unloaded material is one the main ones. This motivates the development of an approach for the estimation of the volume of material transported in field operations by loader trucks. The proposed methodology employs a three-dimensional point cloud representation of the volume and is tested using a skid-steer loader. The volume estimation process involves the segmentation of the loader's bucket from the raw point cloud using machine learning techniques. The segmented point cloud is associated with a pre-constructed reference model of the empty bucket. The volume is computed from a surface model built using the alpha shape algorithm applied to the Delaunay triangulation of the segmented point cloud. Several field experiments were carried out using a stereo camera for five different volumes of material and the bucket at different heights. A 95% accuracy was obtained on average. The encouraging results suggest that effective volume estimation for different bucket types would be possible using the proposed methodology.
BibTeX:
@article{Guevara2020,
  author = {Javier Guevara and Tito Arevalo-Ramirez and Francisco Yandun and M. Torres-Torriti and Fernando Auat Cheein},
  title = {Point cloud-based estimation of effective payload volume for earthmoving loaders},
  journal = {Automation in Construction},
  year = {2020},
  volume = {117},
  pages = {103207},
  url = {https://www.sciencedirect.com/science/article/pii/S0926580519302717},
  doi = {10.1016/j.autcon.2020.103207}
}
Prado ÁJ, Torres-Torriti M, Yuz J and Auat Cheein F (2020), "Tube-based nonlinear model predictive control for autonomous skid-steer mobile robots with tire–terrain interactions", Control Engineering Practice., May, 2020. Vol. 101, pp. 104451.
Abstract: This work addresses the problem of robust tracking control for skid-steer mobile platforms, using tube-based Nonlinear Model Predictive Control. The strategy seeks to mitigate the impact of disturbances propagated to autonomous vehicles originated by traction losses. To this end, a dynamical model composed by two coupled sub-systems stands for lateral and longitudinal vehicle dynamics and tire behavior. The controller is aimed at tracking prescribed stable operation points of the slip and side-slip beyond the robot pose and speeds. To reach robust tracking performance on the global system, a centralized control scheme operates under a predictive control framework composed by three control actions. The first one compensates for disturbances using the reference trajectory-feedforward control. The second control action corrects the errors generated by the modeling mismatch. The third one is devoted to ensure robustness on the closed-loop system whilst compensating for deviations of the state trajectories from the nominal ones (i.e. disturbance-free). The strategy ensures robust feasibility even when tightening constraints are met. Such constraints are calculated on-line based on robust positively invariant sets characterized by polytopic sets (tubes), including a terminal region to guarantee robustness. The benefits of the controller regarding tracking performance, constraint satisfaction and computational practicability were tested through simulations with a Cat® 262C skid-steer model. Then, in field tests, the controller evidenced high tracking accuracy against terrain disturbances when benchmarking performance with respect to inherent robust predictive controllers.
BibTeX:
@article{Prado2020,
  author = {Álvaro Javier Prado and Miguel Torres-Torriti and Juan Yuz and Fernando Auat Cheein},
  title = {Tube-based nonlinear model predictive control for autonomous skid-steer mobile robots with tire–terrain interactions},
  journal = {Control Engineering Practice},
  year = {2020},
  volume = {101},
  pages = {104451},
  url = {https://www.sciencedirect.com/science/article/pii/S0967066120300927},
  doi = {10.1016/j.conengprac.2020.104451}
}
Rigotti-Thompson M, Torres-Torriti M, Auat Cheein FA and Troni G (2020), "ℋ_∞-Based Terrain Disturbance Rejection for Hydraulically Actuated Mobile Manipulators With a Nonrigid Link", IEEE/ASME Transactions on Mechatronics., March, 2020. Vol. 25(5), pp. 2523-2533.
BibTeX:
@article{RigottiThompson2020,
  author = {Rigotti-Thompson, Mattia and Torres-Torriti, Miguel and Auat Cheein, Fernando A. and Troni, Giancarlo},
  title = {ℋ_∞-Based Terrain Disturbance Rejection for Hydraulically Actuated Mobile Manipulators With a Nonrigid Link},
  journal = {IEEE/ASME Transactions on Mechatronics},
  year = {2020},
  volume = {25},
  number = {5},
  pages = {2523-2533},
  doi = {10.1109/TMECH.2020.2983072}
}
Flores-Calero M, Torres-Torriti M, Retamales-Ortega F and Rosas-Díaz F (2020), "Plataforma de presencia virtual de bajo costo para personas con discapacidades motoras severas", Revista Iberoamericana de Automática e Informática industrial., abr., 2020. Vol. 17(2), pp. 215–228.
BibTeX:
@article{FloresCalero2020,
  author = {Flores-Calero, M. and Torres-Torriti, M. and Retamales-Ortega, F. and Rosas-Díaz, F.},
  title = {Plataforma de presencia virtual de bajo costo para personas con discapacidades motoras severas},
  journal = {Revista Iberoamericana de Automática e Informática industrial},
  year = {2020},
  volume = {17},
  number = {2},
  pages = {215–228},
  url = {https://polipapers.upv.es/index.php/RIAI/article/view/10634},
  doi = {10.4995/riai.2019.10634}
}
Auat Cheein F, Torres-Torriti M and Rosell-Polo JR (2019), "Usability analysis of scan matching techniques for localization of field machinery in avocado groves", Computers and Electronics in Agriculture. Vol. 162, pp. 941-950.
Abstract: When working in agricultural environments, specially in groves with dense foliage, machinery positioning systems might suffer from loss of GNSS (Global Navigation Satellite System) signal. The latter motivated the development of new localization strategies that use the environment information to localize the machinery and thus fulfil the required agricultural task. In this work, the usability of five well known scan matching algorithms as sole localization systems using a 2D LiDAR (Light Detection and Ranging) scanner is tested in an avocado grove. The aim is to show the pros and cons of such techniques when the machinery faces a real agricultural environment: presence of slippage, absence of GNSS signal, non-flat terrains in a non-experimental grove and noisy LiDAR readings. The analysis presented herein concludes with a localization error evaluation when the machinery has to travel through a rough avocado alley, showing that amongst all the techniques implemented, the Probabilistic Iterative Correspondence (PIC) and the Sum of Gaussian Scan Correlation (SGSC) presented the lowest localization estimation error and remained consistent from a localization point of view.
BibTeX:
@article{AuatCheein2019,
  author = {Fernando Auat Cheein and Miguel Torres-Torriti and Joan Ramón Rosell-Polo},
  title = {Usability analysis of scan matching techniques for localization of field machinery in avocado groves},
  journal = {Computers and Electronics in Agriculture},
  year = {2019},
  volume = {162},
  pages = {941-950},
  url = {https://www.sciencedirect.com/science/article/pii/S0168169918314625},
  doi = {10.1016/j.compag.2019.05.024}
}
Amato NM, Hager G, Thomas S and Torres-Torriti M (2019), "Special issue on the International Symposium on Robotics Research, 2017", The International Journal of Robotics Research. Vol. 38(12-13), pp. 1327-1328.
BibTeX:
@article{Amato2019,
  author = {Nancy M Amato and Greg Hager and Shawna Thomas and Miguel Torres-Torriti},
  title = {Special issue on the International Symposium on Robotics Research, 2017},
  journal = {The International Journal of Robotics Research},
  year = {2019},
  volume = {38},
  number = {12-13},
  pages = {1327-1328},
  url = {https://doi.org/10.1177/0278364919877027},
  doi = {10.1177/0278364919877027}
}
Zubiaguirre-Bergen I, Torres-Torriti M and Flores-Calero M (2018), "Generación de Regiones con Potencial de Contener Peatones usando Reconstrucción 3D No Densa a partir de Visión Monocular", Revista Iberoamericana de Automática e Informática industrial. Vol. 15(3), pp. 243-251.
Abstract: Los accidentes de tráfico son un problema de salud pública a escala mundial, por el alto número de víctimas humanas y los elevados costos económicos y sociales que generan. En este contexto, los peatones se encuentran entre los elementos más importantes y vulnerables de la escena vial que necesitan ser protegidos. Es así que en este trabajo se presenta una innovadora propuesta utilizado la información visual monocular para emular la visión estéreo, y a partir de ello: i) generar regiones de interés (ROIs) con alta posibilidad de contener un peatón, y ii) estimar la trayectoria del vehículo. Los experimentos han sido desarrollados sobre una base de datos de imágenes tomadas en varias calles de la ciudad de Santiago (Región-Metropolitana), Chile. Esta información fue obtenida usando una plataforma experimental en condiciones reales de conducción durante el día. La tasa de detección de ROIs es del 86.6% para distancias menores a 20 metros, 82.9% para distancias menores a 30 metros y del 76.2% para distancias menores a 40 metros.
BibTeX:
@article{ZubiaguirreBergen2018,
  author = {Ignacio Zubiaguirre-Bergen and Miguel Torres-Torriti and Marco Flores-Calero},
  title = {Generación de Regiones con Potencial de Contener Peatones usando Reconstrucción 3D No Densa a partir de Visión Monocular},
  journal = {Revista Iberoamericana de Automática e Informática industrial},
  year = {2018},
  volume = {15},
  number = {3},
  pages = {243--251},
  url = {https://polipapers.upv.es/index.php/RIAI/article/view/8825},
  doi = {10.4995/riai.2017.8825}
}
Prado J, Yandun F, Torres Torriti M and Auat Cheein F (2018), "Overcoming the Loss of Performance in Unmanned Ground Vehicles Due to the Terrain Variability", IEEE Access. Vol. 6, pp. 17391-17406.
Abstract: Performance in autonomous driven vehicles is susceptible of degradation when traversing different terrains, thus needing motion controllers to be tuned for different terrain profiles. Such tuning stage is a time consuming process for the programmer or operator, and it is often based on intuition or heuristic approaches, and once tuned, the performance of the vehicle varies according to the terrain nature. In this context, we provide a visual based approach to identify terrain variability and its transitions, while observing and learning the performance of the vehicle using machine learning techniques. Based on the identified terrain and the knowledge regarding the performance of the vehicle, our system self-tunes the motion controller, in real time, to enhance its performance. In particular, the trajectory tracking errors are reduced, the control input effort is decreased, and the effects of the wheel-terrain interaction are mitigated preserving the system robustness. The tests were carried out by simulation and experimentation using a robotized commercial platform. Finally, implementation details and results are included in this paper, showing an enhancement in the motion performance up to 92.4% when the highest accuracy of the terrain classifier was 84.3%.
BibTeX:
@article{Prado2018,
  author = {Prado, Javier and Yandun, Francisco and Torres Torriti, Miguel and Auat Cheein, Fernando},
  title = {Overcoming the Loss of Performance in Unmanned Ground Vehicles Due to the Terrain Variability},
  journal = {IEEE Access},
  year = {2018},
  volume = {6},
  pages = {17391-17406},
  doi = {10.1109/ACCESS.2018.2808538}
}
Prado AJ, Auat Cheein FA, Blazic S and Torres-Torriti M (2018), "Probabilistic self-tuning approaches for enhancing performance of autonomous vehicles in changing terrains", Journal of Terramechanics. Vol. 78, pp. 39-51.
Abstract: Motion controllers usually require a tuning stage to ensure an acceptable performance of the vehicle during operation in challenging scenarios. However, such tuning stage is a time consuming process for the programmer and often is based on intuition or heuristic approaches. In addition, once tuned, the vehicle performance varies according to the nature of the terrain. In this work, we study the use of well-known probabilistic techniques for self-tuning trajectory tracking controllers for service units based on the idea of saving both vehicle’s resources and human labour force time. The proposed strategies are based on Monte Carlo and Bayesian approaches to find the best set of gains to tune the controller both off-line and on-line, thus enhancing the controller performance in the presence of changing terrains. The approaches are implemented and validated on a skid-steer mini-loader vehicle usually used for mining purposes. Implementation details and both simulation and empirical results are included in this work, showing that when using our approaches, effort can be saved up to 30% and tracking errors reduced up to 75%.
BibTeX:
@article{Prado2018a,
  author = {Alvaro Javier Prado and Fernando A. Auat Cheein and Saso Blazic and Miguel Torres-Torriti},
  title = {Probabilistic self-tuning approaches for enhancing performance of autonomous vehicles in changing terrains},
  journal = {Journal of Terramechanics},
  year = {2018},
  volume = {78},
  pages = {39-51},
  url = {https://www.sciencedirect.com/science/article/pii/S0022489817301532},
  doi = {10.1016/j.jterra.2018.04.001}
}
Pérez-Zavala R, Torres-Torriti M, Cheein FA and Troni G (2018), "A pattern recognition strategy for visual grape bunch detection in vineyards", Computers and Electronics in Agriculture. Vol. 151, pp. 136-149.
Abstract: Automating grapevine growth monitoring, spraying, leaf thinning and harvesting tasks, as well as improving yield estimation and plant phenotyping, requires reliable methods for detecting grape bunches across different vineyard environmental and plant variety conditions, in which illumination, occlusions, colors and contrast are the main challenges to computer vision techniques. This work presents a method that employs visible spectrum cameras for robust grape berries recognition and grape bunch detection that does not require artificial illumination nor is limited to red or purple grape varieties. The proposed approach relies on shape and texture information together with a strategy to separate regions of clustered pixels into grape bunches. The approach employs histograms of oriented gradients (HOG) as shape descriptor and local binary patterns (LBP) to obtain texture information. A review of the existing methods and comparative analysis of different feature vectors (DAISY, DSIFT, HOG, LBP) and support vector classifiers (SVM-RBF, SVDD) is also presented. Datasets from four countries containing 163 images of different grapevine varieties acquired under different vineyard illumination and occlusion levels were employed to assess the approach. Grapes bunches are detected with an average precision of 88.61% and average recall of 80.34%. Single berries are detected with precision rates above 99% and recall rates between 84.0% and 92.5% on average. The proposed approach should facilitate the estimation of yield, crop thinning measurements and the computation of leaf removal indicators, as well as the implementation guidance strategies for precise robotic harvesters.
BibTeX:
@article{PerezZavala2018,
  author = {Rodrigo Pérez-Zavala and Miguel Torres-Torriti and Fernando Auat Cheein and Giancarlo Troni},
  title = {A pattern recognition strategy for visual grape bunch detection in vineyards},
  journal = {Computers and Electronics in Agriculture},
  year = {2018},
  volume = {151},
  pages = {136-149},
  url = {https://www.sciencedirect.com/science/article/pii/S0168169917310682},
  doi = {10.1016/j.compag.2018.05.019}
}
Yandun Narváez F, Gregorio E, Escolà A, Rosell-Polo JR, Torres-Torriti M and Auat Cheein F (2018), "Terrain classification using ToF sensors for the enhancement of agricultural machinery traversability", Journal of Terramechanics. Vol. 76, pp. 1-13.
Abstract: Ground properties influence various aspects of mobile machinery navigation including localization, mobility status or task execution. Excessive slipping, skidding or trapping situations can compromise the vehicle itself or other elements in the workspace. Thus, detecting the soil surface characteristics is an important issue for performing different activities in an efficient, safe and satisfactory manner. In agricultural applications, this point is specially important since activities such as seeding, fertilizing, or ploughing are carried on within off-road landscapes which contain a diversity of terrains that modify the navigation behaviour of the vehicle. Thus, the machinery requires a cognitive capability to understand the surrounding terrain type or its characteristics in order to take the proper guidance or control actions. This work is focused on the soil surface classification by implementing a visual system capable to distinguish between five usual types of off-road terrains. Computer vision and machine learning techniques are applied to characterize the texture and color of images acquired with a Microsoft Kinect V2 sensor. In a first stage, development tests showed that only infra-red and RGB streams are useful to obtain satisfactory accuracy rates (above 90%). The second stage included field trials with the sensor mounted on a mobile robot driving through various agricultural landscapes. These scenarios did not present illumination restrictions nor ideal driving roads; hence, conditions can resemble real agricultural operations. In such circumstances, the proposed approach showed robustness and reliability, obtaining an average of 85.20% of successful classifications when tested along 17 trials within agricultural landscapes.
BibTeX:
@article{YandunNarvaez2018,
  author = {Francisco Yandun Narváez and Eduard Gregorio and Alexandre Escolà and Joan R. Rosell-Polo and Miguel Torres-Torriti and Fernando Auat Cheein},
  title = {Terrain classification using ToF sensors for the enhancement of agricultural machinery traversability},
  journal = {Journal of Terramechanics},
  year = {2018},
  volume = {76},
  pages = {1-13},
  url = {https://www.sciencedirect.com/science/article/pii/S0022489817300733},
  doi = {10.1016/j.jterra.2017.10.005}
}
Dauvin L, Drass H, Vanzi L, Dünner R, Torres M, Béchet C, Boettger D, Rojas F and Shen T-C (2018), "Optimization of Temperature, Targets, and Illumination for High Precision Photogrammetric Measurements", IEEE Sensors Journal., Feb, 2018. Vol. 18(4), pp. 1449-1456.
Abstract: The cameras of a close-range photogrammetry system must be calibrated to find their positions and optical properties. This is a crucial step in ensuring the performance of the complete system, especially if micrometric precision over a large field of view and long-term reproducibility is required. The target positions within the images for camera calibration and measurements are perturbed if stability between images is not achieved. This paper aims to evaluate the optimal conditions to guarantee the stability of the target images during measurements and calibration. The effect of temperature on the target positions is estimated to be about 0.1 pixels during a camera warm-up period of 20 min or more. This effect is reduced to about 0.02 pixels after a warm-up period of less than 10 min by developing a controller for the camera's pixel clock. Additionally, an approximately 22% variation of illumination intensity is found to cause a small, but clearly measurable effect between images. Other aspects studied here are the illumination angle and the target characteristics. A 180° movement of the illumination source with respect to the camera produces a 0.3 pixel change in the target locations when masked retroreflective targets are involved. In contrast, this effect is diminished by a factor of about ten with the use of larger, opaque targets.
BibTeX:
@article{Dauvin2018,
  author = {Dauvin, Louise and Drass, Holger and Vanzi, Leonardo and Dünner, Rolando and Torres, Miguel and Béchet, Clémentine and Boettger, David and Rojas, Felipe and Shen, Tzu-Chiang},
  title = {Optimization of Temperature, Targets, and Illumination for High Precision Photogrammetric Measurements},
  journal = {IEEE Sensors Journal},
  year = {2018},
  volume = {18},
  number = {4},
  pages = {1449-1456},
  doi = {10.1109/JSEN.2017.2777940}
}
(2017), "Guest Editorial Focused Section on Mechatronics Applications in Agriculture", IEEE/ASME Transactions on Mechatronics. Vol. 22(6), pp. 2397-2400.
BibTeX:
@article{TorresTorriti2017,,
  title = {Guest Editorial Focused Section on Mechatronics Applications in Agriculture},
  journal = {IEEE/ASME Transactions on Mechatronics},
  year = {2017},
  volume = {22},
  number = {6},
  pages = {2397-2400},
  doi = {10.1109/TMECH.2017.2774106}
}
Villalón-Sepúlveda G, Torres-Torriti M and Flores-Calero M (2017), "Sistema de detección de señales de tráfico para la localización de intersecciones viales y frenado anticipado", Revista Iberoamericana de Automática e Informática industrial. Vol. 14(2), pp. 152-162.
Abstract: En este trabajo se presenta un sistema de detección de señales de tráfico aledañas a intersecciones viales y rotondas, y un análisis para conocer su capacidad de detección en función de la distancia. El método propuesto está basado en la segmentación por color sobre el espacio RGB-normalizado (ErEgEb) para la generación de regiones de interés (ROIs), la clasificación del tipo de señal usando los espacios YCbCr y ErEgEb para construir una plantilla estadística, donde para eliminar el fondo se ha propuesto una función de distribución de probabilidad que modeliza el color de los objetos de interés. El sistema está especializado en dos tipos de señales: disco Pare y triángulo invertido de Ceda el Paso. Luego se analiza su desempeño, al compararlo con el método de Viola & Jones, donde se verifica la capacidad de detección a diferentes distancias. Para distancias menores a 48 metros, el método propuesto ha logrado una tasa de detección del 87.5% en el caso de la señal de Ceda el Paso, y del 95.4% en el caso del disco Pare, mientras que para distancias inferiores a 30 metros la detección lograda es del 100%. Estos resultados son superiores a los reportados en la mayoría de la literatura existente, la cual a diferencia del presente trabajo no aborda la sensibilidad de los métodos propuestos ante la variación de la distancia a las señales de tráfico aún cuando esto es uno de los principales desafíos en la implementación de sistemas de asistencia al conductor aplicables al mundo real. Los experimentos han sido desarrollados sobre una base de datos de señales de tráfico, generadas a partir de imágenes tomadas en varias calles de la ciudad de Santiago, Región Metropolitana, Chile, usando un vehículo experimental diseñado para desarrollar sistemas inteligentes.
BibTeX:
@article{Sepulveda2017,
  author = {Gabriel Villalón-Sepúlveda and Miguel Torres-Torriti and Marco Flores-Calero},
  title = {Sistema de detección de señales de tráfico para la localización de intersecciones viales y frenado anticipado},
  journal = {Revista Iberoamericana de Automática e Informática industrial},
  year = {2017},
  volume = {14},
  number = {2},
  pages = {152--162},
  url = {https://polipapers.upv.es/index.php/RIAI/article/view/9217},
  doi = {10.1016/j.riai.2016.09.010}
}
Villalón-Sepúlveda G, Torres-Torriti M and Flores-Calero M (2017), "Traffic Sign Detection System for Locating Road Intersections and Roundabouts: The Chilean Case", Sensors. Vol. 17(6)
Abstract: This paper presents a traffic sign detection method for signs close to road intersections and roundabouts, such as stop and yield (give way) signs. The proposed method relies on statistical templates built using color information for both segmentation and classification. The segmentation method uses the RGB-normalized (ErEgEb) color space for ROIs (Regions of Interest) generation based on a chromaticity filter, where templates at 10 scales are applied to the entire image. Templates consider the mean and standard deviation of normalized color of the traffic signs to build thresholding intervals where the expected color should lie for a given sign. The classification stage employs the information of the statistical templates over YCbCr and ErEgEb color spaces, for which the background has been previously removed by using a probability function that models the probability that the pixel corresponds to a sign given its chromaticity values. This work includes an analysis of the detection rate as a function of the distance between the vehicle and the sign. Such information is useful to validate the robustness of the approach and is often not included in the existing literature. The detection rates, as a function of distance, are compared to those of the well-known Viola–Jones method. The results show that for distances less than 48 m, the proposed method achieves a detection rate of 87.5% and 95.4% for yield and stop signs, respectively. For distances less than 30 m, the detection rate is 100% for both signs. The Viola–Jones approach has detection rates below 20% for distances between 30 and 48 m, and barely improves in the 20–30 m range with detection rates of up to 60% . Thus, the proposed method provides a robust alternative for intersection detection that relies on statistical color-based templates instead of shape information. The experiments employed videos of traffic signs taken in several streets of Santiago, Chile, using a research platform implemented at the Robotics and Automation Laboratory of PUC to develop driver assistance systems.
BibTeX:
@article{VillalonSepulveda2017,
  author = {Villalón-Sepúlveda, Gabriel and Torres-Torriti, Miguel and Flores-Calero, Marco},
  title = {Traffic Sign Detection System for Locating Road Intersections and Roundabouts: The Chilean Case},
  journal = {Sensors},
  year = {2017},
  volume = {17},
  number = {6},
  url = {https://www.mdpi.com/1424-8220/17/6/1207},
  doi = {10.3390/s17061207}
}
Auat Cheein F, Torres-Torriti M, Hopfenblatt NB, Prado ÁJ and Calabi D (2017), "Agricultural service unit motion planning under harvesting scheduling and terrain constraints", Journal of Field Robotics. Vol. 34(8), pp. 1531-1542.
Abstract: Abstract Most of the existing harvesting strategies rely on traditional path planners that only minimize the length of the path or energy consumption, ignoring the state of the crops and production process. Furthermore, the existing approaches use simplified kinematic models that neglect the robots' dynamics and their interaction with the terrain. To address these limitations, we propose and test in the field a harvesting and motion-planning strategy that explicitly considers the expected plant yield and the terrain's traversability. The latter has direct impact in the energy management of the agricultural service unit. A map with the predicted yield of each plant is employed to determine a priority queue of harvesting points. The priority queue, together with the harvesting rate and the robot's payload capacity, are used to generate a harvesting schedule for the different locations in the grove. The joint harvesting and motion-planning strategy applied is evaluated using field data from a Chilean avocado grove during the harvesting season. The results show that the proposed strategy provides a useful approach to automate the harvest points scheduling and motion planning while saving machinery resources.
BibTeX:
@article{AuatCheein2017,
  author = {Auat Cheein, Fernando and Torres-Torriti, Miguel and Hopfenblatt, Nicolás Busch and Prado, Álvaro Javier and Calabi, Daniel},
  title = {Agricultural service unit motion planning under harvesting scheduling and terrain constraints},
  journal = {Journal of Field Robotics},
  year = {2017},
  volume = {34},
  number = {8},
  pages = {1531-1542},
  url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/rob.21738},
  doi = {10.1002/rob.21738}
}
Yandun Narvaez F, Reina G, Torres-Torriti M, Kantor G and Cheein FA (2017), "A Survey of Ranging and Imaging Techniques for Precision Agriculture Phenotyping", IEEE/ASME Transactions on Mechatronics., Dec, 2017. Vol. 22(6), pp. 2428-2439.
Abstract: Agricultural production must double by 2050 in order to meet the expected food demand due to population growth. Precision agriculture is the key to improve productivity and efficiency in the use of resources, thus helping to achieve this goal under the diverse challenges currently faced by agriculture mainly due to climate changes, land degradation, availability of farmable land, labor force shortage, and increasing costs. To face these challenges, precision agriculture uses and develops sensing methodologies that provide information about crop growth and health indicators. This paper presents a survey of the state-of-the-art in optical visible and near-visible spectrum sensors and techniques to estimate phenotyping variables from intensity, spectral, and volumetric measurements. The sensing methodologies are classified into three areas according to the purpose of the measurements: 1) plant structural characterization; 2) plant/fruit detection; and 3) plant physiology assessment. This paper also discusses the progress in data processing methods and the current open challenges in agricultural tasks in which the development of innovative sensing methodologies is required, such as pruning, fertilizer and pesticide management, crop monitoring, and automated harvesting.
BibTeX:
@article{YandunNarvaez2017,
  author = {Yandun Narvaez, Francisco and Reina, Giulio and Torres-Torriti, Miguel and Kantor, George and Cheein, Fernando Auat},
  title = {A Survey of Ranging and Imaging Techniques for Precision Agriculture Phenotyping},
  journal = {IEEE/ASME Transactions on Mechatronics},
  year = {2017},
  volume = {22},
  number = {6},
  pages = {2428-2439},
  doi = {10.1109/TMECH.2017.2760866}
}
Aguilera-Marinovic S, Torres-Torriti M and Auat-Cheein F (2017), "General Dynamic Model for Skid-Steer Mobile Manipulators With Wheel–Ground Interactions", IEEE/ASME Transactions on Mechatronics., Feb, 2017. Vol. 22(1), pp. 433-444.
Abstract: The design of motion controllers that could reduce terrain disturbances propagated to the arm and optimize the trajectories of skid-steer mobile manipulators (SSMMs) working in agricultural, construction, or mining environments requires accurate physical models capable of correctly representing disturbances caused by changes in terrain slope, loss of traction, and other wheel-ground interactions. Therefore, this paper develops the forward dynamics equations of motion and proposes a general model for SSMMs. The novelty of the model is that it considers a floating-base with nonpermanent wheel-ground contacts, i.e., the mobile base has 6-degree of freedom (DOF) and the wheels may lose contact with the terrain. Unlike the existing models, the proposed one is general because the procedure can be extended to MMs with an arbitrary number of arms or wheels and does not restrict the mobile base to planar 2-D motions. Furthermore, it takes into account the loss of traction and the deformation of the wheel-ground contacts. The experimental results involving a small SSMM with a 3-DOF arm and an industrial skid-steer loader validate the physical fidelity of the model. Although the focus of this paper is not in control aspects, one of the examples shows the role physically accurate models can have in the design of end-effector motion controllers, and its potential application to the design of controllers capable of decoupling the arm motion from ground disturbances.
BibTeX:
@article{AguileraMarinovic2017,
  author = {Aguilera-Marinovic, Sergio and Torres-Torriti, Miguel and Auat-Cheein, Fernando},
  title = {General Dynamic Model for Skid-Steer Mobile Manipulators With Wheel–Ground Interactions},
  journal = {IEEE/ASME Transactions on Mechatronics},
  year = {2017},
  volume = {22},
  number = {1},
  pages = {433-444},
  doi = {10.1109/TMECH.2016.2601308}
}
Torres-Torriti M, Arredondo T and Castillo-Pizarro P (2016), "Survey and comparative study of free simulation software for mobile robots", Robotica. Vol. 34(4), pp. 791-822. Cambridge University Press.
BibTeX:
@article{Torres-Torriti2016,
  author = {Torres-Torriti, M. and Arredondo, T. and Castillo-Pizarro, P.},
  title = {Survey and comparative study of free simulation software for mobile robots},
  journal = {Robotica},
  publisher = {Cambridge University Press},
  year = {2016},
  volume = {34},
  number = {4},
  pages = {791--822},
  doi = {10.1017/S0263574714001866}
}
Yandún Narváez FJ, Salvo del Pedregal J, Prieto PA, Torres-Torriti M and Auat Cheein FA (2016), "LiDAR and thermal images fusion for ground-based 3D characterisation of fruit trees", Biosystems Engineering. Vol. 151, pp. 479-494.
Abstract: The thermal behaviour of an orchard is intrinsically related to the plant physiological status and it is commonly observed using thermal imagery, in most cases, provided by a drone or by a satellite. Such remote sensing methods are currently popular since they allow to analyse large amounts of land data with few sensor readings. However, they are restricted by the spatial resolution of the images, which always correspond to top views of the canopies. The latter does not allow for a side recording or analysis of the orchard. In this work, we design and evaluate a portable ground-based system for a manual thermal and geometrical characterisation of an orchard, merging thermal images with LiDAR-based range readings in order to obtain a 3D thermal reconstruction of the crop to overcome the previously mentioned issues. The proposed system can work in Global Navigation Satellite System (GNSS) denied environments and delivers multiple views of the orchard, offering the user a three-dimensional view of the thermal behaviour of the grove. Further, the implemented algorithm classifies points from the LiDAR measurements which correspond to the canopy using a supervised classifier. Later, a matching procedure is performed between such points and the thermal information provided by the thermal camera. In order to reconstruct the entire orchard or only a section of the grove, several frames are registered using the Iterative Closest Point algorithm. The system was tested in two conditions: in laboratory and in field within a plantation of Hass avocado, which is one of the main fruit trees growing in Chile, and its performance is compared with an LI-6400 Infra-red Gas Analyser (IRGA) portable photosynthesis system (LI-COR, Lincoln, NE).
BibTeX:
@article{YandunNarvaez2016,
  author = {Francisco J. Yandún Narváez and Jaime Salvo del Pedregal and Pablo A. Prieto and Miguel Torres-Torriti and Fernando A. Auat Cheein},
  title = {LiDAR and thermal images fusion for ground-based 3D characterisation of fruit trees},
  journal = {Biosystems Engineering},
  year = {2016},
  volume = {151},
  pages = {479-494},
  url = {https://www.sciencedirect.com/science/article/pii/S1537511016300563},
  doi = {10.1016/j.biosystemseng.2016.10.012}
}
Auat Cheein FA, Scaglia G, Torres-Torriti M, Guivant J, Prado AJ, Arnò J, Escolà A and Rosell-Polo JR (2016), "Algebraic path tracking to aid the manual harvesting of olives using an automated service unit", Biosystems Engineering. Vol. 142, pp. 117-132.
Abstract: Service units used in precision agriculture are able to improve processes such as harvesting, sowing, agrochemical application, and manure spreading. This two-part work presents, a path tracking controller based on an algebraic approach for an articulated service unit, suitable for embedded applications, and its implementation to a hierarchical navigation strategy to aid a manual harvesting process. The path tracking controller approach can be scaled to several trailers attached to the service unit. For harvesting, the service unit drives within an olive grove environment following the previously developed path and a trailer is used as a mobile hopper where olives, collected by human labour, are deposited. The service unit also registers and geo-references the amount of olives (mass) collected for the subsequent creation of yield maps. The developed navigation strategy improved the time associated with harvesting olives by approximately 42–45%. The mathematical formulation of the problem, some real time experimental results, the creation of a yield map and the statistical analysis that validated the method are included.
BibTeX:
@article{AuatCheein2016,
  author = {Fernando A. Auat Cheein and Gustavo Scaglia and Miguel Torres-Torriti and José Guivant and Alvaro Javier Prado and Jaume Arnò and Alexandre Escolà and Joan R. Rosell-Polo},
  title = {Algebraic path tracking to aid the manual harvesting of olives using an automated service unit},
  journal = {Biosystems Engineering},
  year = {2016},
  volume = {142},
  pages = {117--132},
  url = {https://www.sciencedirect.com/science/article/pii/S1537511015300830},
  doi = {10.1016/j.biosystemseng.2015.12.006}
}
Auat Cheein FA, Guivant J, Sanz R, Escola A, Yandun F, Torres-Torriti M and Rosell-Polo JR (2015), "Real-time approaches for characterization of fully and partially scanned canopies in groves", Computers and Electronics in Agriculture. Vol. 118, pp. 361-371.
Abstract: Efficient information management in orchard characterization leads to more efficient agricultural processes. In this brief, a set of computational geometry methods are presented and evaluated for orchard characterization; in particular, for the estimation of canopy volume and shape in groves and orchards using a LiDAR (Light Detection And Ranging) sensor mounted on an agricultural service unit. The proposed approaches were evaluated and validated in the field, showing they are convergent in the estimation process and that they are able to estimate the crown volume for fully scanned canopies in real time; for partially observed tree crowns, accuracy decreases up to 30% (the worst case). The latter is the major contribution of this brief since it implies that the automated service unit does not need to cover all alley-ways for an accurate modeling of the orchard, thus saving valuable resources.
BibTeX:
@article{AuatCheein2015,
  author = {Fernando A. Auat Cheein and José Guivant and Ricardo Sanz and Alexandre Escola and Francisco Yandun and Miguel Torres-Torriti and Joan R. Rosell-Polo},
  title = {Real-time approaches for characterization of fully and partially scanned canopies in groves},
  journal = {Computers and Electronics in Agriculture},
  year = {2015},
  volume = {118},
  pages = {361--371},
  url = {https://www.sciencedirect.com/science/article/pii/S0168169915002926},
  doi = {10.1016/j.compag.2015.09.017}
}
Tapia-Espinoza R and Torres-Torriti M (2013), "Robust lane sensing and departure warning under shadows and occlusions", Sensors., March, 2013. Vol. 13(3), pp. 3270-3298. MDPI AG.
BibTeX:
@article{Tapia-Espinoza2013,
  author = {Tapia-Espinoza, Rodolfo and Torres-Torriti, Miguel},
  title = {Robust lane sensing and departure warning under shadows and occlusions},
  journal = {Sensors},
  publisher = {MDPI AG},
  year = {2013},
  volume = {13},
  number = {3},
  pages = {3270--3298},
  url = {http://dx.doi.org/10.3390/s130303270},
  doi = {10.3390/s130303270}
}
Jiménez-Pinto J and Torres-Torriti M (2013), "Optical Flow and Driver’s Kinematics Analysis for State of Alert Sensing", Sensors., March, 2013. Vol. 13(4), pp. 4225-4257. MDPI AG.
BibTeX:
@article{Jimenez-Pinto2013,
  author = {Jiménez-Pinto, Javier and Torres-Torriti, Miguel},
  title = {Optical Flow and Driver’s Kinematics Analysis for State of Alert Sensing},
  journal = {Sensors},
  publisher = {MDPI AG},
  year = {2013},
  volume = {13},
  number = {4},
  pages = {4225--4257},
  url = {http://dx.doi.org/10.3390/s130404225},
  doi = {10.3390/s130404225}
}
Jiménez-Pinto J and Torres-Torriti M (2012), "Face salient points and eyes tracking for robust drowsiness detection", Robotica. Vol. 30(5), pp. 731-741. Cambridge University Press.
BibTeX:
@article{Jimenez-Pinto2012,
  author = {Jiménez-Pinto, J. and Torres-Torriti, M.},
  title = {Face salient points and eyes tracking for robust drowsiness detection},
  journal = {Robotica},
  publisher = {Cambridge University Press},
  year = {2012},
  volume = {30},
  number = {5},
  pages = {731--741},
  doi = {10.1017/S0263574711000749}
}
Garcia-Bunster G, Torres-Torriti M and Oberli C (2012), "Crowded pedestrian counting at bus stops from perspective transformations of foreground areas", IET Computer Vision., July, 2012. Vol. 6(4), pp. 296-305.
Abstract: Automated bus fleet scheduling and dispatch require an accurate measurements of current passenger demand. This study presents an effective holistic approach for estimating the number of people waiting at regular open bus stops by means of image processing. This is a non-trivial problem because of several varying conditions that complicate the detection process, such as illumination, crowdedness and different people poses, to name a few. The proposed method estimates the pedestrian count using measurements of foreground areas corrected by perspective. Four approaches are evaluated to find the best mapping between the area measurements and the people count. These mappings include two parametric (standard linear regression model, linear discriminant analysis) and two non-parametric (probabilistic neural network, k-nearest neighbours) approaches. This study also evaluates the performance of the algorithm when thermal and panoramic catadioptric cameras are used instead of standard perspective colour cameras. The proposed method is shown to yield better pedestrian count estimates than those obtained using milestone detectors, and requires model fitting procedures than can be easily implemented without requiring very large datasets for proper classifier training. The approach can also be employed to count people in other public spaces, such as buildings and crosswalks.
BibTeX:
@article{Garcia-Bunster2012,
  author = {G. Garcia-Bunster and M. Torres-Torriti and C. Oberli},
  title = {Crowded pedestrian counting at bus stops from perspective transformations of foreground areas},
  journal = {IET Computer Vision},
  year = {2012},
  volume = {6},
  number = {4},
  pages = {296--305},
  doi = {10.1049/iet-cvi.2011.0138}
}
Caro L, Correa J, Espinace P, Langdon D, Maturana D, Mitnik R, Montabone S, Pszczolkowski S, Araneda A, Mery D, Torres M and Soto A (2012), "Indoor mobile robotics at Grima, PUC", Journal of Intelligent & Robotic Systems., April, 2012. Vol. 66(1), pp. 151-165.
Abstract: This paper describes the main activities and achievements of our research group on Machine Intelligence and Robotics (Grima) at the Computer Science Department, Pontificia Universidad Catolica de Chile (PUC). Since 2002, we have been developing an active research in the area of indoor autonomous social robots. Our main focus has been the cognitive side of Robotics, where we have developed algorithms for autonomous navigation using wheeled robots, scene recognition using vision and 3D range sensors, and social behaviors using Markov Decision Processes, among others. As a distinguishing feature, in our research we have followed a probabilistic approach, deeply rooted in machine learning and Bayesian statistical techniques. Among our main achievements are an increasing list of publications in main Robotics conference and journals, and the consolidation of a research group with more than 25 people among full-time professors, visiting researchers, and graduate students.
BibTeX:
@article{Caro2012,
  author = {Caro, Luis and Correa, Javier and Espinace, Pablo and Langdon, Daniel and Maturana, Daniel and Mitnik, Ruben and Montabone, Sebastian and Pszczolkowski, Stefan and Araneda, Anita and Mery, Domingo and Torres, Miguel and Soto, Alvaro},
  title = {Indoor mobile robotics at Grima, PUC},
  journal = {Journal of Intelligent & Robotic Systems},
  year = {2012},
  volume = {66},
  number = {1},
  pages = {151--165},
  url = {https://doi.org/10.1007/s10846-011-9604-2},
  doi = {10.1007/s10846-011-9604-2}
}
Oberli C, Torres-Torriti M and Landau D (2010), "Performance evaluation of UHF RFID technologies for real-time passenger recognition in intelligent public transportation systems", IEEE Transactions on Intelligent Transportation Systems., September, 2010. Vol. 11(3), pp. 748-753.
Abstract: Automated passenger tracking in public transportation systems can be used to estimate the short-term demand and, thereby, to optimize the fleet schedule in real time. It can also be used to determine the origin-destination matrix and to maintain statistics of each passenger's transportation habits over time, thus enabling enhancements in long-term planning. However, ubiquitously tracking passengers throughout a network requires the ability to recognize them at single locations in the network. In this paper, we study the merits of realizing this task by means of radio-frequency identification (RFID) technologies. Forty volunteers carried RFID tags of the norm EPC Gen2 in their backpacks, wallets, pockets, and hands through a mockup of a bus door equipped with four reading antennas. Setups with one and two rows of persons walking through the portal were evaluated. The RFID tags were embedded in laminated plastic cards. Single-tag cards embedded with a single EPC Gen2 tag and dual-tag cards that also contained a traditional Mifare tag were used. Recognition statistics of passengers for all the combinations of one, two, three, and four antennas are presented. The recognition percentages are mainly influenced by the antenna position and radiation pattern and by the line-of-sight conditions between the tag and the antennas.
BibTeX:
@article{Oberli2010,
  author = {C. Oberli and M. Torres-Torriti and D. Landau},
  title = {Performance evaluation of UHF RFID technologies for real-time passenger recognition in intelligent public transportation systems},
  journal = {IEEE Transactions on Intelligent Transportation Systems},
  year = {2010},
  volume = {11},
  number = {3},
  pages = {748--753},
  doi = {10.1109/TITS.2010.2048429}
}
Peralta-Cabezas JL, Torres-Torriti M and Guarini-Hermann M (2008), "A comparison of Bayesian prediction techniques for mobile robot trajectory tracking", Robotica. Vol. 26(5), pp. 571-585. Cambridge University Press.
BibTeX:
@article{Peralta-Cabezas2008,
  author = {Peralta-Cabezas, J. L. and Torres-Torriti, M. and Guarini-Hermann, M.},
  title = {A comparison of Bayesian prediction techniques for mobile robot trajectory tracking},
  journal = {Robotica},
  publisher = {Cambridge University Press},
  year = {2008},
  volume = {26},
  number = {5},
  pages = {571--585},
  doi = {10.1017/S0263574708004153}
}
Donoso-Aguirre F, Bustos-Salas J-P, Torres-Torriti M and Guesalaga A (2008), "Mobile robot localization using the Hausdorff distance", Robotica. Vol. 26(2), pp. 129-141. Cambridge University Press.
BibTeX:
@article{DonosoAguirre2008,
  author = {Donoso-Aguirre, F. and Bustos-Salas, J.-P. and Torres-Torriti, M. and Guesalaga, A.},
  title = {Mobile robot localization using the Hausdorff distance},
  journal = {Robotica},
  publisher = {Cambridge University Press},
  year = {2008},
  volume = {26},
  number = {2},
  pages = {129--141},
  doi = {10.1017/S0263574707003657}
}
Bustos JP, Donoso F, Guesalaga A and Torres M (2007), "Matching radar and satellite images for ship trajectory estimation using the Hausdorff distance", IET Radar, Sonar Navigation., February, 2007. Vol. 1(1), pp. 50-58.
Abstract: A novel technique to obtain position, velocity and radar biases estimates of a ship is described by matching ship-borne radar images to geo-referenced satellite images. The matching is performed through the minimisation of the averaged partial Hausdorff distances between data points in each image. The minimisation rapidly yields robust geographical latitude and longitude position measurements, as well as ship heading and radar biases. The accuracy of the measurements is improved by feeding them into a Kalman filter that also allows estimates of the ship's velocity to be obtained. The method provides an alternative effective position sensor for GPS denied environments, which may also be employed for automatic radar calibration of bearing and range biases or for indoor autonomous mobile robot navigation
BibTeX:
@article{Bustos2007,
  author = {J. P. Bustos and F. Donoso and A. Guesalaga and M. Torres},
  title = {Matching radar and satellite images for ship trajectory estimation using the Hausdorff distance},
  journal = {IET Radar, Sonar Navigation},
  year = {2007},
  volume = {1},
  number = {1},
  pages = {50--58},
  doi = {10.1049/iet-rsn:20060025}
}
Torres-Torriti M and Michalska H (2005), "A software package for Lie algebraic computations", SIAM Review. Vol. 47(4), pp. 722-745. Society for Industrial and Applied Mathematics.
Abstract: The paper presents a computer algebra package that facilitates Lie algebraic symbolic computations required in the solution of a variety of problems, such as the solution of right-invariant differential equations evolving on Lie groups. Lie theory is a powerful tool, helpful in the analysis and design of modern nonlinear control laws, nonlinear filters, and the study of particle dynamics. The practical application of Lie theory often results in highly complex symbolic expressions that are difficult to handle efficiently without the aid of a computer software tool. The aim of the package is to facilitate and encourage further research relying on Lie algebraic computations.
BibTeX:
@article{Torres-Torriti2005,
  author = {Miguel Torres-Torriti and Hannah Michalska},
  title = {A software package for Lie algebraic computations},
  journal = {SIAM Review},
  publisher = {Society for Industrial and Applied Mathematics},
  year = {2005},
  volume = {47},
  number = {4},
  pages = {722--745},
  url = {https://doi.org/10.1137/S0036144502410427},
  doi = {10.1137/S0036144502410427}
}
Michalska H and Torres-Torriti M (2004), "Feedback stabilization of strongly non-linear systems using the CBH formula", International Journal of Control. Vol. 77(6), pp. 562-571. Taylor & Francis.
Abstract: This paper presents an approach to the construction of stabilizing feedback for strongly non-linear systems. The class of systems of interest includes systems with drift which are affine in the controls and which cannot be stabilized by continuous state feedback. The approach is independent of the selection of a Lyapunov function, but requires the on-line solution of a non-linear programming satisficing problem stated in terms of expressions resulting from the composition of flows via the Campbell-Baker-Hausdorff formula.
BibTeX:
@article{Michalska2004,
  author = {H. Michalska and M. Torres-Torriti},
  title = {Feedback stabilization of strongly non-linear systems using the CBH formula},
  journal = {International Journal of Control},
  publisher = {Taylor & Francis},
  year = {2004},
  volume = {77},
  number = {6},
  pages = {562--571},
  url = {https://doi.org/10.1080/00207170410001663516},
  doi = {10.1080/00207170410001663516}
}
Michalska H and Torres-Torriti M (2003), "A geometric approach to feedback stabilization of nonlinear systems with drift", Systems & Control Letters. Vol. 50(4), pp. 303-318.
Abstract: The paper presents an approach to the construction of stabilizing feedback for strongly nonlinear systems. The class of systems of interest includes systems with drift which are affine in control and which cannot be stabilized by continuous state feedback. The approach is independent of the selection of a Lyapunov type function, but requires the solution of a nonlinear programming satisficing problem stated in terms of the logarithmic coordinates of flows. As opposed to other approaches, point-to-point steering is not required to achieve asymptotic stability. Instead, the flow of the controlled system is required to intersect periodically a certain reachable set in the space of the logarithmic coordinates.
BibTeX:
@article{Michalska2003,
  author = {Hannah Michalska and Miguel Torres-Torriti},
  title = {A geometric approach to feedback stabilization of nonlinear systems with drift},
  journal = {Systems & Control Letters},
  year = {2003},
  volume = {50},
  number = {4},
  pages = {303--318},
  url = {http://www.sciencedirect.com/science/article/pii/S0167691103001695},
  doi = {10.1016/S0167-6911(03)00169-5}
}