Publications

[Journal] R. Gonzalez, S. Chandler, D. Apostolopoulos; Characterization of Machine Learning Algorithms for Slippage Estimation in Planetary Exploration Rovers; Journal of Terramechanics [In Press]

[Conference] J. Kruger, A. Rogg, R. Gonzalez; Estimating wheel slip of a planetary exploration rover via unsupervised machine learning; IEEE Aerospace Conference, 2019. [Accepted]

[Journal] R. Gonzalez and K. Iagnemma; DeepTerramechanics: Terrain Classification and Slip Estimation for Ground Robots via Deep Learning; arXiv, June 2018.

[Online access]

[Journal] R. Gonzalez and K. Iagnemma; Slippage Estimation and Compensation for Planetary Exploration Rovers. State of the Art and Future Challenges; Journal of Field Robotics, Vol. 35, Pages: 564-577, June 2018. DOI: 10.1002/rob.21761

[Abstract]   [Online access]

Future lunar/planetary exploration missions will demand mobile robots with the capability of reaching more challenging science targets and driving farther per day than the current Mars rovers. Among other improvements, reliable slippage estimation and compensation strategies will play a key role in enabling a safer and more efficient navigation. This paper reviews and discusses this body of research in the context of planetary exploration rovers. Previously published state-ofthe- art methods that have been validated through field testing are included as exemplary results. Limitations of the current techniques and recommendations for future developments and planetary missions close the survey.

[Journal] R. Gonzalez, M. Fiacchini, and K. Iagnemma; Slippage Prediction for Off-Road Mobile Robots via Machine Learning Regression and Proprioceptive Sensing; Robotics and Autonomous Systems, Vol. 105, Pages 85–93, July 2018.

[Online access]

[Journal] R. Gonzalez, D. Apostolopoulos, K. Iagnemma; Slippage and Immobilization Detection for Planetary Exploration Rovers via Machine Learning and Proprioceptive Sensing; Journal of Field Robotics, Vol. 35. No. 2. Pages 231-247. March 2018.

[Online access]

[Journal] R. Gonzalez, D. Apostolopoulos, K. Iagnemma; Improving rover mobility through traction control. Simulating rovers on the Moon; Autonomous Robots, 2018. [Under review]

[Top]

[Journal] M.R. Bouguelia, R. Gonzalez, K. Iagnemma, S. Byttner; Unsupervised Detection of Soil Embedding Events for Planetary Exploration Rovers; Journal of Terramechanics, Volume 73, October 2017, Pages 95-106. DOI: 110.1016/j.jterra.2017.09.001.

[Abstract]   [Online access]

This paper introduces an unsupervised method for the classification of discrete rovers’ slip events based on proprioceptive signals. In particular, the method is able to automatically discover and track various degrees of slip (i.e. low slip, moderate slip, high slip). The proposed method is based on aggregating the data over time, since high level concepts, such as high and low slip, are concepts that are dependent on longer time perspectives. Different features and subsets of the data have been identified leading to a proper clustering, interpreting those clusters as initial models of the prospective concepts. Bayesian tracking has been used in order to continuously improve the parameters of these models, based on the new data. Two real datasets are used to validate the proposed approach in comparison to other known unsupervised and supervised machine learning methods. The first dataset is collected by a single-wheel testbed available at MIT. The second dataset was collected by means of a planetary exploration rover in real off-road conditions. Experiments prove that the proposed method is more accurate (up to 86% of accuracy vs. 80% for K-means) in discovering various levels of slip while being fully unsupervised (no need for hand-labeled data for training).

[Journal] R. Gonzalez, A. Lopez, K. Iagnemma; Thermal Vision, Moisture Content, and Vegetation in the Context of Off-Road Mobile Robots; Journal of Terramechanics, Volume 70, April 2017. Pp. 35-48. DOI: 10.1016/j.jterra.2017.01.001.

[Abstract]   [Online access]

This paper describes an initial investigation that shows the major impact that moisture and vegetation produce on a soil and how that effect may be measured using a thermal camera. In particular, those two variables influence how the soil compacts and, hence, the traversability of a vehicle. A broad set of experiments, under different weather conditions and with different soils, demonstrate that thermal properties derived from the thermal camera (i.e. thermal inertia) increase when moisture content of sandy soils increases. In addition to that, a relation is observed between thermal inertia and traversability (lower thermal inertia, worse traction; and vice versa). Another key behavior is noticed for vegetated soils, where a similar thermal inertia to wet sand is obtained but with only a third of moisture content. These results may be considered for maximizing traversability over sandy soils with higher thermal inertias, what eventually means higher compaction and safer routes. To the authors’ knowledge, this is the first work addressing the correlation between moisture content and vegetation, and the thermal properties of a soil using a light-weight thermal camera that can be mounted on a mobile robot.

[Journal] R. Gonzalez, P. Jayakumar, K. Iagnemma; Generation of Stochastic Mobility Maps for Large-Scale Route Planning of Ground Vehicles. A Case Study; Journal of Terramechanics, Volume 69, February 2017, Pp. 1-11. DOI: 10.1016/j.jterra.2016.10.001

[Abstract]   [Online access]

This paper describes a simple and efficient methodology to generate a mobility map accounting for two sources of uncertainty, namely measurement errors (RMSE of a Digital Elevation Model) and interpolation error (kriging method). The proposed methodology means a general-purpose solution since it works with standard and publicly-available Digital Elevation Models (DEMs). The different regions in the map are classified according to the geometry of the surface (i.e. slope) and the soil type. A real USGS DEM demonstrates the suitability of the proposed methodology: (1) interpolation of a 26×40-km2 DEM to a finer resolution (30-m to 20-m); (2) analysis of the number of random realizations to account for the variability of the data; (3) efficient computation time (4-million-point DEM requires less than 30 min to complete the whole process); (4) route planning using the stochastic mobility map (constraints in slope and soil properties).

[Journal] R. Gonzalez, P. Jayakumar, K. Iagnemma; Stochastic Mobility Prediction of Ground Vehicles over Large Spatial Regions. A Geostatistical Approach; Autonomous Robots, Volume 41(2), January 2017, Pp. 313-331. DOI: 10.1007/s10514-015-9527-z

[Abstract]   [Online access]

This paper describes a stochastic approach to vehicle mobility prediction over large spatial regions (> 5x5 [Km2]). The main source of uncertainty considered in this work derives from uncertainty in terrain elevation, which arises from sampling (at a finer resolution) a Digital Elevation Model (DEM). In order to account for such uncertainty, Monte Carlo simulation is employed, leading to a stochastic analysis of vehicle mobility properties. Experiments performed on two real data sets (namely, the Death Valley region and Sahara desert) demonstrate the advantage of stochastic analysis compared to classical deterministic mobility prediction. These results show the computational efficiency of the proposed methodology. The robotic simulator ANVEL has also been used to validate the proposed methodology.

[Conference] R. Gonzalez, C. Mahulea, M. Kloetzer; Comparative Study of Trajectories Resulted from Cell Decomposition Path Planning Approaches; IEEE International Conference on System Theory, Control and Computing (ICSTCC) [Online]

[Popular science book in Spanish] R. Gonzalez; Innovar o Morir? Esa es la cuestion (Innovate or Die? That's the question); Editorial Circulo Rojo. October 2017 (Third Edition). [Website]

[Top]

[Popular science book in Spanish] R. Gonzalez; Innovar o Morir? Esa es la cuestion (Innovate or Die? That's the question); Editorial Circulo Rojo. December 2016. [Website]

[Journal] R. Gonzalez, P. Jayakumar, K. Iagnemma; An Efficient Method for Increasing the Accuracy of Mobility Maps for Ground Vehicles; Journal of Terramechanics, Volume 68, December 2016, Pp. 23–35. DOI: 10.1016/j.jterra.2016.09.002

[Abstract]   [Online access]

This paper presents an efficient method for increasing the accuracy of one key step regarding the process of determining a mobility map. That is, the interpolation of the original Digital Elevation Model (DEM) to a finer resolution before running multi-body-dynamics simulations. Specifically, this paper explores the use of fractal dimension and elevation range metrics for increasing the accuracy and reducing the computation time associated with the spatial interpolation ordinary kriging method. The first goal is to ensure the stationary variogram requirement. The second goal is to reduce kriging error or variance in the new predicted values. A novel segmentation-based approach has been proposed to divide the regions of interest into segments where stationarity is ensured. Empirical investigation based on real DEMs indicates the generality of the segmentation approach when natural and man-made terrains are considered. The proposed method leads to a more efficient computation burden and to more accurate results than the traditional approach.

[Journal] R. Gonzalez, A. Rituerto, J.J. Guerrero; Improving Robot Mobility by Combining Downward-Looking and Frontal Cameras; Robotics, Volume 5(25), November 2016, Pp. 1-19. DOI: 10.3390/robotics5040025

[Abstract]   [Online access]

This paper presents a novel attempt to combine a downward-looking camera and a forward-looking camera for terrain classification in the field of off-road mobile robots. The first camera is employed to identify the terrain beneath the robot. This information is then used to improve the classification of the forthcoming terrain acquired from the frontal camera. This research also shows the usefulness of the Gist descriptor for terrain classification purposes. Physical experiments conducted in different terrains (quasi-planar terrains) and different lighting conditions, confirm the satisfactory performance of this approach in comparison with a simple color-based classifier based only on frontal images. Our proposal substantially reduces the misclassification rate of the color-based classifier (∼10% versus ∼20%).

[Conference] R. Gonzalez, S. Byttner, K. Iagnemma; Comparison of Machine Learning Approaches for Soil Embedding Detection of Planetary Exploration Rovers; International Conference of the ISTVS (International Society for Terrain-Vehicle Systems), 12-14 September 2016.

[Abstract]   [Conference]

This paper analyzes the advantages and limitations of known machine learning approaches to cope with the problem of incipient rover embedding detection based on propioceptive signals. In particular, two supervised learning approaches (Support Vector Machines and Feed-forward Neural Networks) are compared to two unsupervised learning approaches (K-means and Self-Organizing Maps) in order to identify various degrees of slip (e.g. low slip, moderate slip, high slip). A real dataset collected by a single-wheel testbed available at MIT has been used to validate each strategy. The SVM algorithm achieves the best performance (accuracy >95 %). However, the SOM algorithm represents a better solution in terms of accuracy and the need of hand-labeled data for training the classifier (accuracy >84 %).

[Conference] R. Gonzalez and K. Iagnemma; Soil Embedding Avoidance for Planetary Exploration Rovers; International Conference of the ISTVS (International Society for Terrain-Vehicle Systems), 12-14 September 2016.

[Abstract]   [Conference]

This paper contributes a new and novel layer, embedding avoidance, to the traditional navigation control architecture of a planetary exploration rover. In particular, the aim of this new layer is to both maximize traction and and minimize risk of entrapment. This layer is composed of a soil embedding detection algorithm (described in another paper published in this conference) and a traction control strategy. Simulation results demonstrate the suitability of the proposed embedding avoidance layer in realistic challenging conditions. Additionally, several traction control algorithms show the importance of considering both the slip compensation and the kinematic incompatibility problems within the same control strategy. After those experiments the following conclusions are drawn: (i) the proposed traction controllers mean simpler approaches than traditional torque-based optimal controllers, and they demonstrate a proper balance between slip-compensation (lowest mean slip) and reduction of wheels fighting effect (less aggressive control actions); (iii) when no traction control is considered (current solution in NASA’s rovers), simulation results show the rover becomes stuck in one of the proposed scenarios.

[Conference] S.U. Lee , R. Gonzalez, K. Iagnemma; Robust Sampling-based Motion Planning for Autonomous Tracked Vehicles in Deformable High Slip Terrain; IEEE International Conference on Robotics and Automation (ICRA), Pp. 2569 - 2574, 16-21 May 2016. Stockholm (Sweden). DOI: 978-1-4673-8026-3/16

[Abstract]   [Conference]

This paper presents an optimal global planner for autonomous tracked vehicles navigating in off-road terrain with uncertain slip, which affects the vehicle as a process noise. This paper incorporates two fields of study: slip estimation and motion planning. For slip estimation, an experimental result from [9] is used to model the effect of the slip on the vehicle in various soil types. For motion planning, a robust incremental sampling based motion planning algorithm (CC-RRT*) is combined with the LQG-MP algorithm. CC-RRT* yields the optimal and probabilistically feasible trajectory by using a chance constrained approach under the RRT* framework. LQG-MP provides the capability of considering the role of compensator in the motion planning phase and bounds the degree of uncertainty to appropriate size. In simulation, the planner successfully finds the optimal and robust solution. In addition, the planner is compared with an RRT* algorithm with dilated obstacles to show that it avoids being overly conservative.

[Tech. Report] J. Dasch and P. Jayakumar, editors; ET-148 Next-Generation NATO Reference Mobility Model (NRMM). Ch. 8: Stochastics. K. Iagnemma and R. Gonzalez; NATO/OTAN, August, 2016.

[Pre-released]

[Top]

[Journal] R. Gonzalez, F. Rodriguez, J.L. Guzman; Autonomous Tracked Robots. History, Modelling, Localization, and Motion Control (Robots Móviles con Orugas. Historia, Modelado, Localización y Control); Revista Iberoamericana de Automática e Informática Industrial, Vol. 12(1), Pp. 3-12. 2015. DOI: 10.1016/j.riai.2014.11.001

[Abstract]   [Journal]     [Online access]

One of the most significant research field in mobile robotics deals with robots operating in off-road conditions (planetary rovers, agriculture robots, search and rescue operations, military robots, etc.). However, obtaining a successful result is not an easy task. One primary point is the locomotion system. In this case, tracks constitute a well-known approach and since the beginning of the 20th century this locomotion system has demonstrated remarkable results in manned vehicles. This article motivates and shows through physical experiments the goodness of tracked mobile robots in off-road conditions. Firstly, a historical perspective of tracked vehicles and tracked robots is addressed. Then, the main modelling aspects are introduced, in particular, the slip phenomenon. After that, several localization techniques are discussed with especial mention to visual odometry. The motion control aspect is also of primal importance. In this regard, several slip-compensation control strategies are analysed. Finally, the authors background obtained in this field is expounded.

[Journal] M. Berenguel, F. Rodriguez, J.C. Moreno, J.L. Guzman, R. Gonzalez; Tools and Methodologies for Teaching Robotics in Computer Science & Engineering Studies; Computer Applications in Engineering Education, 2015, DOI: 10.1002/cae.21698

[Abstract]   [Journal]     [Online access]

This work presents a teaching experience of Robotic Systems in Computer Science & Engineering studies at the University of Almeria (Spain). The teaching methodology is mainly based on the use of ICT. In particular, interactive software tools, virtual and remote laboratories, and an e-learning content manage- ment are used. Such technologies have significantly helped to improve the learning capacity of the students. A discussion and feedback from students are presented to show the result of this approach.

[Conference] R. Gonzalez, C. Mahulea, M. Kloetzer; A Matlab-based Interactive Simulator for Teaching Mobile Robotics; IEEE International Conference on Automation Science and Engineering (CASE), Pp. 310 - 315, 24-28 August 2015. Gothenburg (Sweden). DOI: 10.1109/CoASE.2015.7294097

[Abstract]   [Conference]   [Online access]

This paper presents an open-source Matlab-based interactive software tool for teaching mobile robotics in introductory courses. In particular, it deals with the subjects: modeling, path planning, and motion control. This simulator offers the advantage of testing different aspects related to these fundamental topics and instantly seeing the result in a Graphical User Interface (GUI). This fact leads to a high realism in interactivity, while no previous knowledge in Matlab or programming is required. Additionally, it constitutes an easily scalable tool, the GUI has been properly designed with just one single window with straightforward and intuitive buttons, icons, and figures. Some illustrative examples demonstrate the benefits of the proposed simulator.

[Conference] M. Kloetzer, C. Mahulea, R. Gonzalez; Optimizing Cell Decomposition Path Planning for Mobile Robots using Different Metrics; IEEE International Conference on System Theory, Control and Computing (ICSTCC), 14-16 October 2015. Cheile Gradistei (Romania). DOI: 10.1109/ICSTCC.2015.7321353

[Abstract]   [Conference]   [Online access]

Many robot planning approaches use cell decomposition methods for finding a sequence of regions that the robot should traverse. When a fully-actuated robot is used, the robot reference trajectory is simply constructed by linking through line segments the middle points of common facets of successive traversed cells. This paper improves this approach by proposing three different optimizations that yield the waypoints through which the robot piecewise linear route is passing. The optimizations use different metrics defined as sums of norms for the linear segments that compose the route. The norms L-1, L-2 squared and L-infinity are used and standard optimization problems result in each case. Examples are included for showing the usefulness of these optimizations, since shorter routes can be obtained under a negligible computational overhead.

[Top]

[Book] R. Gonzalez, F. Rodriguez, J.L. Guzman; Autonomous Tracked Robots in Planar Off-Road Conditions. Modelling, Localization, and Motion Control. Springer, 2014. [Online access] More than 3000 chapter downloads (since April 2014)!

[Journal] R. Gonzalez, L. Roca, F. Rodriguez; Economic Optimal Control applied to a Solar Seawater Desalination Plant; Computers and Chemical Engineering, Vol. 71, Pp. 554-562. 2014.

[Abstract] [Online access]

This paper discusses the formulation of an optimal control strategy taking into account economic objectives in fresh water production process through a solar seawater desalination plant. It contributes both a linearised model of the solar-field dynamics and a simplified model of the produced distillate as a function of the outlet solar field water temperature. Then such linear models are used to design an economic receding horizon optimal controller. In particular, it comprises incomes related to the production of fresh water and the costs dealing with the electricity. Several simulations validate the proposed models and show the performance of the proposed economic optimal control strategy. In both cases, actual disturbances from former physical experiments have been included in the simulations. Notice that the AQUASOL facility available at the Plataforma Solar de Almeria (Spain) has been considered in this work as a testbed.

[Journal] J.L. Torres, R. Gonzalez, A. Gimenez, J. Lopez; Energy Management Strategy for Plug-in Hybrid Electric Vehicles. A Comparative Study; Applied Energy, Vol. 113, Pp. 816–824. 2014.

[Abstract]   [Journal]     [Online access]

This paper presents the development of an energy management strategy of a Plug-in Hybrid Electric Vehicle (PHEV). In this case, a rule-based optimal controller selects the appropriate operation mode. Furthermore, advantages and drawbacks of such vehicles are compared with respect to other vehicles powered by the most popular powertrain architectures. Simulations are carried out for three predefined drive cycles repeated over different geographic regions with varying CO2 intensities. The results reveal that the proposed controller is able to switch the vehicle's operating mode according to previous established criteria.

[Patent] Guiding system for autonomous vehicles in greenhouses

Applicants: University of Almeria (Spain), F. Rodriguez, J.G. Donaire, R. Gonzalez, A. Pawlowski, J. Sanchez-Hermosilla, J.L. Guzman, M. Berenguel, J.C. Lopez, E. Baeza, J.C. Gazquez, V. Plaza

International Classification: G05D1/00 (2006.01)

Publication number: ES2401509

Grant Date: February 26, 2014

[Online Information]

[Conference] J.G. Donaire, E. Gonzalez, R. Gonzalez, J.C. Moreno, F. Rodriguez; Development of a stereovision-based navigation strategy for mobile robots working in greenhouses, Ageng (International Conference on Agricultural Engineering), 2014, Zurich, Switzerland.

[Conference]

[National conference] D. Rodríguez-Gracía, J.C. Moreno, F. Rodríguez, R. González, J.G. Donaire; Comparación de algoritmos de visión para la generación de trayectorías de robots móviles en el interior de invernaderos (Comparison of vision-based algorithms for generating trajectories for mobile robots working in greenhouses); I Symposium Nacional de Ingeniería Hortícola, 20-22 Febrero 2014, Orihuela, Spain.

[Abstract]   [Conference]

En este trabajo se presenta un sistema de adquisición y procesamiento de imágenes que ayuda a la navegación autónoma de robots móviles en invernaderos del sudeste español. Las técnicas basadas en métodos reactivos no funcionan correctamente cuando existen condiciones de poca vegetación o cuando se realizan prácticas como la poda o la recolección, que disminuyen la masa vegetal. Es en estas situaciones cuando las técnicas de visión artificial resultan adecuadas. En este trabajo se evalúan distintas estrategias para determinar el centro del pasillo y así poder generar la ruta que debe seguir el robot. Estos algoritmos permiten implementar un sistema no supervisado de navegación basado en visión. El sistema propuesto se ha validado en distintos tipos de suelos, en presencia de irregularidades y para distintos valores de luminosidad. Además es invariante a imágenes descentradas o próximas al final del pasillo, a diferentes condiciones de frondosidad de la vegetación y para diferentes estados del plástico del invernadero (nivel de blanco).

[Top]

[Journal] R. Gonzalez, F. Rodriguez, J.L. Guzman, C. Pradalier, R. Siegwart; Control of Off-road Mobile Robots using Visual Odometry and Slip Compensation; Advanced Robotics, Vol. 27(11), 2013.

[Abstract]   [Journal]   [Pdf]

This manuscript evaluates through physical experiments a navigation architecture for off-road mobile robots. It has been implemented taking into account low-cost components and computational requirements while still being able to robustly address the required tasks. The visual odometry approach uses two consumer-grade cameras for estimating robot displacement and orientation (visual compass). One of these cameras is also used for slip estimation. The control scheme updates online the feedback gains taking into account the current slip. Furthermore, the setpoints are sent to two low-level controllers, PI controllers with anti-windup, properly tuned. In order to validate the proposed architecture we have employed a tracked mobile robot in off-road conditions, gravel terrains, with a slip around 5 [\%]. The selected physical experiments show the right integration of the localization layer (visual odometry with visual compass) and the control layer with the slip compensation controller and the appropriate comn time (lesser than 0.2 [s] are employed at each sampling instant).

[Journal] J. Sanchez-Hermosilla, R. Gonzalez, F. Rodriguez, J.G. Donaire; Mechatronic Description of a Laser Autoguided Vehicle for Greenhouse Operations; Sensors, Vol. 13, Pp. 769-784, 2013.

[Abstract]   [Online access]

This paper presents a novel approach for guiding mobile robots inside greenhouses demonstrated by promising preliminary physical experiments. It represents a comprehensive attempt to use the successful principles of AGVs (auto-guided vehicles) inside greenhouses, but avoiding the necessity of modifying the crop layout, and avoiding having to bury metallic pipes in the greenhouse floor. The designed vehicle can operate different tools, e.g., a spray system for applying plant-protection product, a lifting platform to reach the top part of the plants to perform pruning and harvesting tasks, and a trailer to transport fruits, plants, and crop waste. Regarding autonomous navigation, it follows the idea of AGVs, but now laser emitters are used to mark the desired route. The vehicle development is analyzed from a mechatronic standpoint (mechanics, electronics, and autonomous control).

[Journal] R. Gonzalez, F. Rodriguez, J.L. Guzman, and M. Berenguel; Robust Constrained Economic Receding Horizon Control applied to the Two-time-scale Dynamics Problem of a Greenhouse; Optimal Control, Applications and Methods, 2013. DOI: 10.1002/oca.2080

[Abstract]   [Online access]

This paper discusses the formulation of an optimal control framework for a two-time-scale system modelled in terms of Singular Perturbation Theory. The fast-dynamics subsystem is controlled online by means of a robust receding horizon control approach considering economic objectives in the performance function, and fulfilling state and input constraints. The formulation is addressed in general terms, so it can be adapted to different applications. A practical example is given, greenhouse crop growth control. Simulations comparing the proposed controller with another two-time-scale control strategy demonstrate constraints fulfillment and a proper performance, assuming uncertainty in the weather conditions during the predictions.

[National conference] M. Godoy, R. Gonzalez, F. Rodriguez; Diseño Mecatrónico de un Robot Submarino de Bajo Coste para uso Docente (Mechatronic design of a low-cost submarine robot for teaching purposes); Jornadas de Automática, Septiembre 2013, Tarrasa, Spain.

[Abstract]   [Conference]

Este artículo se enmarca en el contexto de la enseñanza de materias relacionadas con la robótica. En particular, siguiendo un enfoque mecatrónico se ha diseñado, ensamblado y programado un robot submarino para explicar a los alumnos la cinemática, la dinámica, los grados de libertad, y la programación de este tipo de robots. Nótese que este tipo de robots no son nada habituales en los cursos de robótica actuales, pero en cambio cada vez son más utilizados en aplicaciones reales.

[National magazine] El reto de la movilidad limpia (The challenge of clean mobility)

Revista Novaciencia: Actualidad Universitaria y Divulgación Científica

Número 8. Octubre 2013

[Download]

[Top]

[Journal] R. Gonzalez, A. Pawlowski, C. Rodriguez, J.L. Guzman, J. Sanchez-Hermosilla; Design and Implementation of an Automatic Pressure-Control System for a Mobile Sprayer for Greenhouse Applications; Spanish Journal of Agricultural Research, Vol. 10(4), 2012.

[Abstract]   [Journal]     [Pdf]

This article presents the design and development of an embedded automatic pressure-control system for a mobile sprayer working in greenhouses. The hardware developed is based on an embedded microprocessor and provides a low-cost and robust solution. The resulting embedded system has been tested on a spraying system mounted on a manned vehicle. Furthermore, an easy-tuning non-linear PI (Proportional Integral) controller to achieve the desired pressure profile is designed and implemented in the embedded system. Many physical experiments show the best performance of such controller compared with a typical PI controller.

[Journal] R. Gonzalez, F. Rodriguez, J.L. Guzman, C. Pradalier, R. Siegwart; Combined Visual Odometry and Visual Compass for Off-Road Mobile Robots Localization; Robotica, Vol. 30(6), 2012.

[Abstract]   [Journal]   [Pdf]

In this paper, we present the work related to the application of a visual odometry approach to estimate the location of mobile robots operating in off-road conditions. The visual odometry approach is based on template matching, which deals with estimating the robot displacement through a matching process between two consecutive images. Standard visual odometry has been improved using visual compass method for orientation estimation. For that purpose, two consumer-grade monocular cameras have been employed. One camera is pointing at the ground under the robot, and another camera is looking at the surrounding environment. Comparisons with popular localization approaches, through physical experiments in off-road conditions, have shown the satisfactory behavior of the proposed strategy.

[Conference] R. Gonzalez, J.G. Donaire, F. Rodriguez, A. Pawlowski; Guiding Strategy based on Laser and Template Matching for Autonomous Vehicles in Greenhouses, Ageng (International Conference on Agricultural Engineering), July 2012, Valencia, Spain.

[Abstract]   [Pdf]   [Conference]

This paper presents a guiding strategy for autonomous vehicles working in greenhouses based on laser and vision. It follows the idea of auto-guided vehicles but despite of establishing the desired route on the ground (like auto-guided vehicles), here a mesh of laser emitters are managed to establish the route. In particular, a vision-based algorithm (template matching) is employed to detect the position of such laser points which hit a set of dartboards installed on the front and lateral parts of a autonomous vehicle. Several physical experiments show the performance of the proposed vision approach which will permit to carry out physical experiments using the whole proposed navigation strategy.

[Conference] V. Plaza, F. Rodriguez, R. Gonzalez; Vision System based on RGB Filter to Guide Autonomous Vehicles in Greenhouses, First RHEA International Conference on Robotics and Associated High-Technologies and Equipment for Agriculture, September 2012, Pisa, Italy.

[Abstract]   [Pdf]   [Conference]

This paper is related to the navigation problem of mobile robots operating in greenhouses. It constitutes an attractive research, but a whole successful answer has not been found yet. Although there are some projects with good results (Gonzalez et al., 2009; Mandow et al., 1996; Sammons et al., 2005; van Henten et al., 2002), they present some drawbacks mainly related to the localization strategy (error growth effect of odometry based solutions, poor accuracy of beacons solutions, etc.). The main contribution of this work comes from a practical point of view rather than from a theoretical one. We demonstrate an appropriate solution to a particular problem.

[Top]

[Journal] R. Gonzalez, M. Fiacchini, T. Alamo, J.L. Guzman, F. Rodriguez; Online Robust Tube-based MPC for Time-Varying Systems: A Practical Approach; International Journal of Control, Vol. 86(6), 2011.

[Abstract]   [Journal]   [Pdf]

This paper focuses on the design of a robust model predictive control law for constrained discrete-time time-varying systems with additive uncertainties. The proposed solution to the control problem is a tube-based MPC ensuring robustness and constraints fulfillment. Reachable sets are calculated online taking into account the system dynamics by means of an adaptive local control law and additive uncertainties. The proposed method represents a trade-off between small conservativeness and efficient realtime execution. This approach is applied to solve the trajectory tracking problem of a mobile robot. Simulation results provide a comparison between the tube-based MPC scheme and established motion control algorithms, showing the efficient execution and satisfactory behavior of the proposed controller.

[Journal] R. Gonzalez, M. Fiacchini, J.L. Guzman, T. Alamo, F. Rodriguez; Robust Tube-based Predictive Control for Mobile Robots in Off-Road Conditions; Robotics and Autonomous Systems, Vol. 59(10), 2011.

[Abstract]   [Journal]   [Pdf]

This paper focuses on the design of a tube-based Model Predictive Control law for the control of constrained mobile robots in off-road conditions with longitudinal slip while ensuring robustness and stability. A time-varying trajectory tracking error model is used, where uncertainties are assumed to be bounded and additive. The robust tube-based MPC is compared with other motion control techniques through simulation and physical experiments. These tests show the satisfactory behavior of the presented control strategy.

[PhD Thesis] R. Gonzalez, Contributions to Modelling and Control of Mobile Robots in Off-Road Conditions, 2011, University of Almeria.

[Abstract]

Mobile robotics constitutes an attractive research field with a high potential for practical applications. These applications often require robots to travel across unprepared rough terrains. When a mobile robot operates in off-road conditions, many disturbances and inconveniences could lead to unsuccessful results. Some of these inconveniences deal with robot-terrain interaction, such as slip and sinkage phenomena, and inaccurate robot localization. In this context, a careful and precise design together with a strict testing process must be carried out to achieve a satisfactory and reliable result. To the successful application of mobile robots in off-road conditions, the following fundamental topics must be analyzed: path planning, motion control strategy, robot modelling, and robot localization. The former deals with the problem of generating a reference trajectory such that the robot moves from an initial point to a goal. Afterwards, motion controllers must steer the real mobile robot close to the refe ence trajectory. In this process, appropriate robot models are required for control design and simulation purposes. Furthermore, accurate localization techniques have to be considered in order to feedback to the motion controllers. This doctoral dissertation focuses on the three last fundamental issues. Thus, it is supposed that the desired trajectory has been obtained in a preliminary step. Particularly, the objectives are: the formulation of several models for the trajectory tracking problem of off-road mobile robots taking into account slip effects; to provide several robot localization strategies that accurately estimate the robot location in off-road conditions; and the design of advanced slip compensation motion controllers ensuring robot constraints fulfillment and efficient real-time execution. To validate these contributions, a whole navigation architecture is designed for a real mobile robot. In this case, a tracked mobile robot called Fitorobot and available at the University of Almeria, is employed. First, a kinematic model for the trajectory tracking problem is formulated. In this sense, an extended kinematic model taking into account slip effect has been suggested. This model avoids the estimation of complex variables usually related to dynamic models. Additionally, physical experiments show that this kinematic model is more accurate than the classic kinematic one when a mobile robot moves in off-road conditions. Regarding the localization issue, a visual-odometry-based technique is suggested. The most interesting point is that two cameras are combined, one for estimate the robot longitudinal displacement and another camera to estimate the robot orientation (visual compass). In this way, typical problems related to error growth of odometry-based solutions and false-matching phenomena of visual-odometry-based approaches are minimized. Furthermore, a technique based on indirect Kalman filter is proposed. The main advantage of this configuration is that the filter is out of the control loop, so if the filter fails, the navigation system can work, at least, in an emergency mode. Once the robot models and the localization techniques are developed and described, three motion control approaches are presented. The first one comes from a modification of a well-known linear feedback controller previously proposed in the literature. In this case, time-dependent feedback gains are updated online using the estimated slip. Furthermore, a slip compensation adaptive controller formulated using Linear Matrix Inequalities is proposed. The main advantages of this control strategy are: asymptotic stability, performance, input and state constraints fulfillment, and efficient real-time execution. A robust tube-based MPC controller is also suggested. The main advantages of this control strategy are: robustness (uncertainties are taken into account in the controller synthesis), performance, input and state constraints fulfillment, stability, and efficient real-time execution. All the contributions of this thesis are validated through simulations and physical experiments.

[Book chapter] R. Guirado, R. Gonzalez, F. Bienvenido, F. Rodriguez; Knowledge Modelling in Two-level Decision Making for Robot Navigation; Book: Advances in Robot Navigation, 2011, Intech Publisher.

[Download]

[National conference] F. Rodriguez, R. Gonzalez, J. Sanchez, A. Gimenez, E. Baeza; Experiencias en Robotica Aplicada a Invernaderos (Experiences in Robotics applied to Greenhouses); III Workshop de Robotica: Robotica Experimental, Noviembre 2011, Sevilla, Spain.

[Abstract]   [Pdf]   [Conference]

En este trabajo se comentan las principales experiencias adquiridas por miembros del grupo de investigación Automática, Electrónica y Robótica (TEP-197) de la Universidad de Almería en la robotización de tareas en invernaderos. En particular, en la aplicación de robots manipuladores en estaciones de trabajo capaces de realizar varias tareas y robots móviles aplicados principalmente a tareas de pulverización. Se presentan pruebas reales para mostrar el correcto funcionamiento de los sistemas desarrollados.

[National conference] R. Gonzalez, F. Rodriguez, J.L. Guzman, M. Berenguel; Aplicación del Filtro de Kalman Indirecto a la Localización de Robots Móviles (Applying the Indirect Kalman Filter to Mobile Robot Localization); CEA Jornadas de Automatica, Septiembre 2011, Sevilla, Spain.

[Abstract]   [Pdf]   [Conference]

Este artículo presenta una técnica basada en el Filtro de Kalman Indirecto (FKI) para la localización de robots móviles. El FKI utiliza la diferencia entre la posición obtenida usando odometría y el sistema radar-brújula para mejorar la estimación de la posición del vehículo. Esta estrategia se compara a través de pruebas reales utilizando un robot móvil con técnicas populares como la odometría. A fin de validar dichas pruebas se ha utilizado un DGPS y una brújula magnética como ground-truth.

[National magazine] Sistema de guiado para movimiento autonomo de vehiculos en entornos estructurados (Guiding system for autonomous vehicles working in structured environments)

Revista Nexus: Revista de Transferencia de Resultados de Investigación

Número 6. Noviembre 2011

[Pdf]

[National magazine] Los robots de la UAL se instalan en el Parque de las Ciencias de Granada (Robots of the University of Almeria in the Science Museum of Granada)

Revista Nexus: Revista de Transferencia de Resultados de Investigación

Número 6. Noviembre 2011

[Pdf]

[Top]

[Journal] R. Gonzalez, M. Fiacchini, T. Alamo, J.L. Guzman, F. Rodriguez; Adaptive Control for a Mobile Robot under Slip Conditions using an LMI-based Approach; European Journal of Control, Vol. 16(2), 2010.

[Abstract]   [Journal]   [Pdf]

This paper presents a control law for the trajectory tracking of mobile robots under slip conditions and subject to both system constraints and varying dynamics. First, a control law is obtained based on a Lyapunov function to guarantee closed-loop asymptotic stability, resulting in a set of feedback gains, one for each extreme model realization. On-line computation is devoted to determine an adaptive feedback control law for the current realization of the state as a convex combination of the gains previously obtained. Simulations comparing the proposed control law with other strategies under slip conditions are provided. They show the satisfactory behavior of the proposed control strategy.

[Book chapter] J. Sanchez-Hermosilla, F. Rodriguez, R. Gonzalez, J.L. Guzman, M. Berenguel; A Mechatronics Description of an Autonomous Mobile Robot for Agricultural Tasks in Greenhouses; Book: Mobile Robots Navigation, 2010, Intech Publisher.

[Abstract]   [Download]

This paper presents a project developed at the University of Almeria (Spain) aimed at designing, implementation, and testing a multi-use mobile robot with safe, efficient, and economic operation which moves autonomously through the crop lines of a greenhouse and which performs tasks that are tedious and/or hazardous for people, it is called Fitorobot. The developed mobile robot to operate in greenhouses involves a synergetic integration of mechanical engineering with electronics and automatic control.

[Patent] Multipurpose Autonomous Vehicle for Working in a Greenhouse

Applicants: University of Almeria (Spain), J. Sanchez-Hermosilla, F. Rodriguez, A. Sanchez, J.L. Guzman, R. Gonzalez, M. Berenguel

International Classification: G05D1/02 (2006.01)

Publication number: ES2329107

Grant Date: September 7, 2010

[Online Information]

[Conference] R. Gonzalez, F. Rodriguez, J.L. Guzman; Trajectory Tracking Control Algorithms and Localization Methods for Off-Road Mobile Robots, GeoFARMatics Workshop, November 2010, Cologne, Germany.

[Pdf]   [Conference]

[National conference] R. Gonzalez, F. Rodriguez, J.L. Guzman, C. Pradalier, R. Siegwart; Arquitectura de Navegacion para Robots Moviles en Entornos Exteriores usando Visual Odometry para la Localizacion (Navigation Architecture based on Visual Odometry for Off-Road Mobile Robots ); CEA Jornadas de Automatica, Septiembre 2010, Jaen, Spain.

[Abstract]   [Pdf]   [Conference]     Best Paper Award in Robotics

En este articulo se presenta una arquitectura de navegacion jerarquica para robots moviles usando como tecnica de localizacion visual odometry. El esquema de control de movimiento esta compuesto por un controlador principal, que asegura que el robot sigue la trajectoria de referencia. Este controlador genera las consignas de velocidad apropiadas a dos controladores de bajo nivel. Resultados reales, en condiciones exteriores, muestran el correcto funcionamiento de la arquitectura de control dentro de un tiempo de computación reducido.

[National conference] F.J. Martinez, R. Gonzalez, F. Rodriguez, J.L. Guzman; Laboratorio Virtual y Remoto para la Enseñanza de Robotica Paralela ( Virtual and Remote Lab for Teaching Parallel Robotics); CEA Jornadas de Enseñanza de la Ing. de Sistemas y Automatica, Junio 2010, Leon, Spain.

[Abstract]   [Pdf]   [Conference]

En este trabajo se presenta una herramienta software para la enseñanza de robotica paralela. Esta herramienta permite a los alumnos simular la cinematica directa e inversa de este tipo de robots. Ademas, en esta herramienta software se ha integrado la posibilidad de interactuar con un robot paralelo real (ensamblado mediante el kit Lego NXT) utilizando un joystick permitiendo acceso local y remoto. La herramienta software desarrollada se ejecuta de forma remota y no necesita la instalación de ningun software especifico, simplemente un navegador Web y una conexión a Internet..

[Top]

[Journal] R. Gonzalez, F. Rodriguez, J. Sanchez-Hermosilla, J.G. Donaire; Navigation Techniques for Mobile Robots in Greenhouses; Applied Engineering in Agriculture, Vol. 25(2), Pp. 153 - 165, 2009.

[Abstract]   [Journal]   [Pdf]

This article discusses navigation methods for mobile agricultural robots in greenhouses. Today, many dangers of repetitive and hazardous agricultural tasks for humans could be avoided by using robots. The problem of autonomous navigation in greenhouses has been solved using both deliberative and pseudo-reactive techniques. The first one utilizes a map-based algorithm to create a safe, obstacle-free path to circulate throughout the greenhouse. The second technique applies a sensor-feedback algorithm to move through the greenhouse corridors. Furthermore, along the trajectory a sensorial map is built. Both approaches have been implemented and tested in a real environment, with promising results.

[Conference] R. Gonzalez, M. Fiacchini, J.L. Guzman, T. Alamo; Robust Tube-based MPC for Constrained Mobile Robots under Slip Conditions, IEEE Conference on Decision and Control, December 2009, Shangahi, China.

[Abstract]   [Pdf]   [Conference]

This paper focuses on the design of a robust tube-based Model Predictive Control law for the control of constrained mobile robots. A time-varying trajectory tracking error model has been used, where uncertainties are assumed to be bounded and additive. The proposed solution to the control problem is a tube-based MPC ensuring robustness and stability. A comparative simulation example is presented showing the promising behavior of the robust MPC controller.

[Conference] R. Gonzalez, M. Fiacchini, T. Alamo, J.L. Guzman, F. Rodriguez; Adaptive Control for a Mobile Robot under Slip Conditions using an LMI-based Approach, European Control Conference, August 2009, Budapest, Hungary, Pages: 1251 - 1256.

[Abstract]   [Pdf]   [Conference]

This paper presents the synthesis of a control law which guarantees asymptotic stability for a wheeled mobile robot under slip conditions subject to both constraints and system dynamics. This control law is obtained using Linear Matrix Inequalities. The improvements provided by the proposed adaptive control are compared with other control laws, dealing with slip effect, through simulation.

[Conference] R. Gonzalez, F. Rodriguez, J.L. Guzman, M. Berenguel; Localization and Control of Tracked Mobile Robots under Slip Conditions, IEEE International Conference on Mechatronics, April 2009, Malaga, Spain.

[Abstract]   [Pdf]   [Conference]

This paper deals with the localization and trajectory tracking control problems of tracked mobile robots under slip conditions. The proposed control law consists of the modification of a well-known control algorithm based on the feedback linearization technique, in which additional parameters have been included in order to compensate for the slip effects. Furthermore, an Indirect Kalman Filter has been used to improve the localization of the robot. Real tests show promising results.

[Conference] R. Gonzalez, F. Rodriguez, J.L. Guzman, M. Berenguel; Comparative Study of Localization Techniques for Mobile Robots based on Indirect Kalman Filter, IFR International Symposium on Robotics, March 2009, Barcelona, Spain, Pages: 253 - 258.

[Abstract]   [Pdf]   [Conference]

This paper reviews some popular localization techniques used in mobile robotics. Furthermore, an adaptation of the classical formulation of the Indirect Kalman Filter (IKF) has been implemented by means of fusing different kinds of sensors (such as odometry and radar-compass system). Two different formulations of the IKF have been compared with popular localization techniques, through real tests using a tracked mobile robot available at the University of Almeria.

[Tech. report] R. Gonzalez; Results of my research stay at ASL, ETH Zurich. Supervisors: R. Siegwart, C. Pradalier and A. Krebs, 2009.

- Development of a Task Scheduler for the CRAB rover - Localization of the CRAB rover using Visual Odometry

[Pdf]   [ASL, ETH Zurich]   [CRAB rover]

[National conference] F. Parron, R. Gonzalez, F. Rodriguez, J.G. Donaire; Sistema de Localizacion para Robots Moviles basado en GPS. Aplicacion a Campos de Golf (GPS-based Localization of Mobile Robots. Application to Golf Courses); CEA Jornadas de Automatica, Septiembre 2009, Valladolid, Spain.

[Abstract]   [Pdf]   [Conference]

Este trabajo presenta una aplicacion del sistema de localizacion GPS, como un metodo para la localizacion de un robot movil en entornos abiertos, conocidos y estaticos, como es el caso de los campos de golf. Para ello, se han analizado y comparado varios sistemas de localizacion basados en GPS (DGPS y RTK-GPS). Ademas se comentan varias pruebas reales del sistema de navegacion implementado, para las cuales se ha usado un robot movil disponible en la Universidad de Almeria.

[Top]

[Conference] R. Gonzalez, F. Rodriguez, J.L. Guzman, M. Berenguel; Compensation of Sliding Effects in the Control of Tracked Mobile Robots, Portuguese Conference on Automatic Control (CONTROLO'08), July 2008, Vila Real, Portugal, Pages: 524 - 529.

[Abstract]   [Pdf]   [Conference]

A fuzzy-based approach for modeling and control of greenhouse temperature is presented. First, the model of a greenhouse is derived using Takagi-Sugeno fuzzy models. Then, applying the Parallel Distributed Compensation technique to this model, the stability analysis and control design problems are reduced to sufficient conditions expressed as linear matrix inequalities (LMIs). On-line experiments in a real greenhouse show that the proposed approach maintains successfully the temperature within the greenhouse around the desired set point.

[Conference] M. Nachidi, F. Rodriguez, F. Tadeo, J.L. Guzman, R. Gonzalez; Modeling and Control of Nocturnal Temperature inside a Greenhouse using Takagi-Sugeno Fuzzy Models, Portuguese Conference on Automatic Control (CONTROLO'08), July 2008, Vila Real, Portugal, Pages: 518 - 523.

[Abstract]   [Pdf]   [Conference]

This article discusses navigation methods for mobile agricultural robots in greenhouses. Today, many dangers of repetitive and hazardous agricultural tasks for humans could be avoided by using robots. The problem of autonomous navigation in greenhouses has been solved using both deliberative and pseudo-reactive techniques. The first one utilizes a map-based algorithm to create a safe, obstacle-free path to circulate throughout the greenhouse. The second technique applies a sensor-feedback algorithm to move through the greenhouse corridors. Furthermore, along the trajectory a sensorial map is built. Both approaches have been implemented and tested in a real environment, with promising results.

[National conference] F.J. Jimenez, J.C. Moreno, R. Gonzalez, J. Sanchez-Hermosilla; Sistema de Vision de Apoyo a la Navegacion de un Robot Movil en Internaderos (Vision-based System for Mobile Robots in Greenhouses); CEA Jornadas de Automatica, Septiembre 2008, Tarragona, Spain.

[Abstract]   [Pdf]   [Conference]

Este trabajo supone la mejora del algoritmo de navegación utilizado en un robot movil para la aplicacion de productos fitosanitarios en el interior de invernaderos. El algoritmo de navegacion reactiva utilizado anteriormente plantea algunos problemas. En este trabajo se proponen tecnicas de vision artificial que sirven de apoyo al sistema de navegacion y que consiguen solucionar el problema. Se utilizan para ello dos implementaciones diferentes del sistema de vision. Una de ellas se basa en una web-cam, donde el procesamiento lo llevara a cabo el sistema empotrado que esta integrado en el vehiculo movil. Y la otra utiliza una camara inteligente que realiza todo el procesamiento. En ambos casos, el problema es localizar el centro del pasillo del invernadero a partir de las imagenes capturadas.

[National magazine] Un robot de la Universidad de Almería acapara la atención de los participantes en la Semana de la Ciencia ( A Robot from the University of Almeria captures the attention of the Science Week)

Andalucía Investiga

17 de Noviembre de 2008

[Pdf]

[Top]

[Conference] R. Gonzalez, F. Rodriguez, J. Sanchez-Hermosilla, J.G. Donaire; Navigation Techniques for Mobile Robots in Greenhouses, AgriControl, September 2007, Osijek, Croatia, Pages: 159 - 164.

[Abstract]   [Pdf]   [Conference]

This paper discusses the problem of using navigation methods for agricultural mobile robots in greenhouses. Nowadays, many agricultural tasks are dangerous and repetitive for human beings and could be improved employing robots. The autonomous navigation in greenhouses has been solved using both deliberative and pseudo-reactive techniques. The first one utilizes a based-on map algorithm to create a safe and obstacle-free path to travel. The second technique applies a sensor feedback algorithm to cross the greenhouse corridors. Both strategies have been implemented and tested in real environment, obtaining quite appropriate results.

[National conference] R. Gonzalez, F. Rodriguez, J. Sanchez-Hermosilla, J.G. Donaire; Experiencias en Sistemas de Navegacion de Robots Moviles para Tareas en Invernadero ( Experiences of Navigation Systems for Mobile Robots working in Greenhouses); AgroIngenieria, Septiembre 2007, Albacete, Spain.

[Abstract]   [Pdf]   [Conference]

El trabajo en los invernaderos implica la realización de tareas peligrosas y repetitivas, las cuales necesitan desplazamientos de productos y maquinaria. Una solucion adecuada consiste en el empleo de vehiculos autonomos. La Universidad de Almeria (España) ha desarrollado un vehiculo capaz de realizar varías tareas dentro de un invernadero, llamado Fitorobot. En este trabajo se describen dos tecnicas que se emplean para el control de la navegacion de dicho robot movil. La primera tecnica se basa en el control del robot utilizando un mapa del invernadero. La segunda tecnica consiste en un algoritmo quasi-reactivo donde el robot toma decisiones basandose en la realimentacion del entorno proporcionada por el sistema sensorial. Finalmente ambas tecnicas se han probado en entornos reales y los resultados obtenidos se analizan en este trabajo.

[Top]

[National conference] R. Gonzalez, F. Rodriguez, J. Sanchez-Hermosilla, J.G. Donaire; Algoritmo de Navegacion Reactiva de Robots Moviles para Tareas Bajo Invernadero ( Reactive Navigation applied to Mobile Robots working in Greenhouses); CEA Jornadas de Automatica, Septiembre 2006, Almeria, Spain.

[Abstract]   [Pdf]   [Conference]     Best Paper Award in Robotics

Los cultivos bajo invernadero constituyen una de las principales fuentes de producción en el sudeste español. Una de las tareas mas arriesgadas para la salud en los invernaderos, como es la pulverización de los cultivos, se continua realizando de forma manual. Una alternativa adecuada la constituyen los robots moviles capaces de realizar tales tareas de forma autonoma, sin necesidad de un operario en el interior de los invernaderos. En este trabajo se presenta la implementacion y prueba de un algoritmo de navegacion sobre un robot movil, cuya caracteristica principal es que no necesita información previa del entorno de operación, construyendo ademas a lo largo de su recorrido un mapa sensorial que sera utilizado para analizar el recorrido seguido.

[Master thesis] R. Gonzalez; Desarrollo de algoritmos de navegacion reactivos de robots moviles para tareas bajo invernadero ( Development of Reactive Navigation Algorithms applied to Mobile Robots working in Greenhouses); University of Almeria, July 2006, Almeria, Spain.

[Abstract]

En este trabajo se ha implementado una arquitectura de navegación reactiva, es decir, el robot navegará de forma autónoma dentro de un invernadero sin información previa de tal entorno. Para que dicho objetivo sea llevado a cabo de forma exitosa el sistema de navegación esta realimentado por el sistema sensorial que posee la plataforma sobre la que se han realizado las pruebas.

[Top]

Presentation about Simultaneous Localization and Mapping [in Spanish]

R. Gonzalez

Year: 2007

[Download]

Presentation about Robonaut: A robot for the International Space Station [in Spanish]

R. Gonzalez

Year: 2005

[Download]

[Top]