List of my publications
2020
Acuna, Raul (TU Darmstadt); Willert, Volker (TU Darmstadt)
Verfahren zur Bestimmung von Kalibrierungsparametern einer Kamera Patent
, 2020.
@patent{Acuna2020,
title = {Verfahren zur Bestimmung von Kalibrierungsparametern einer Kamera},
author = {Raul (TU Darmstadt) Acuna and Volker (TU Darmstadt) Willert},
editor = {Deutsches Patent- und Markenamt},
url = {https://www.racuna.me/wp-content/uploads/2021/08/Acuna-Willert-2020-Verfahren-zur-Bestimmung-von-Kalibrierungsparametern-einer-Kamera.pdf},
year = {2020},
date = {2020-05-28},
urldate = {2020-05-28},
volume = {DE10201812},
pages = {1--6},
publisher = {Deutsches Patent- und Markenamt},
institution = {TU Darmstadt},
abstract = {Zusammenfassung: Die Erfindung betrifft ein Verfahren zur Bestimmung von Kalibrierungsparametern einer Kamera. In einem Darstellungsschritt (1) wird ein vorgegebenes Kalibriermuster durch matrixf\"{o}rmig angeordnete Kalibrierbildpunkte auf einer vorgegebenen und sich dreidimensional erstreckenden zusammenh\"{a}ngenden Oberfl\"{a}che dargestellt, sodass Abmessungen von Kalibriermusterbereichen des vorgegebenen Kalibriermusters auf der vorgegebenen Oberfl\"{a}che bekannt sind. Eine Helligkeit und ein Farbe jedes Kalibrierbildpunkts wird elektronisch vorgegeben. In einem auf den Darstellungschritt (1) folgenden Erfassungsschritt (2) wird eine Aufnahme des Kalibriermusters mit der Kamera erstellt. In einem sich anschlie\ssenden Bestimmungsvorgang werden die Kalibrierparameter auf Grundlage der Aufnahme bestimmt.},
howpublished = {Deutsches Patent- und Markenamt},
keywords = {},
pubstate = {published},
tppubtype = {patent}
}
Zusammenfassung: Die Erfindung betrifft ein Verfahren zur Bestimmung von Kalibrierungsparametern einer Kamera. In einem Darstellungsschritt (1) wird ein vorgegebenes Kalibriermuster durch matrixförmig angeordnete Kalibrierbildpunkte auf einer vorgegebenen und sich dreidimensional erstreckenden zusammenhängenden Oberfläche dargestellt, sodass Abmessungen von Kalibriermusterbereichen des vorgegebenen Kalibriermusters auf der vorgegebenen Oberfläche bekannt sind. Eine Helligkeit und ein Farbe jedes Kalibrierbildpunkts wird elektronisch vorgegeben. In einem auf den Darstellungschritt (1) folgenden Erfassungsschritt (2) wird eine Aufnahme des Kalibriermusters mit der Kamera erstellt. In einem sich anschließenden Bestimmungsvorgang werden die Kalibrierparameter auf Grundlage der Aufnahme bestimmt.
2019
Mihailescu-Stoica, Dinu; Acuna, Raul; Adamy, Jürgen
High Performance Adaptive Attitude Control of a Quadrotor Conference
18th European Control Conference (ECC), IEEE, Naples, Italy, Italy, 2019, ISBN: 978-3-907144-00-8.
@conference{dinu2019,
title = {High Performance Adaptive Attitude Control of a Quadrotor},
author = {Dinu Mihailescu-Stoica and Raul Acuna and J\"{u}rgen Adamy},
url = {https://www.racuna.me/wp-content/uploads/2019/12/High_Performance_Adaptive_Attitude_Control_of_a_Quadrotor.pdf},
doi = {10.23919/ECC.2019.8796203},
isbn = {978-3-907144-00-8},
year = {2019},
date = {2019-08-15},
booktitle = {18th European Control Conference (ECC)},
publisher = {IEEE},
address = {Naples, Italy, Italy},
abstract = {This paper introduces a quaternion based attitude controller, by augmenting a novel baseline controller with model reference adaptive control techniques (MRAC). In contrast to existing designs, the baseline controller makes use of the quaternion logarithm and the standard bi-invariant distance on SO(3). The adaptation restores the behavior of a time dependent reference model in case of model discrepancies. Moreover, we make use of the fact that the parameters, characterizing the gyroscopic coupling term of a rigid tumbling body, are naturally bounded to some predefined manifold and incorporate this information in our adaptive design. Altogether, the proposed design enables aggressive, high bandwidth acrobatic flight maneuvers over the whole attitude range without singularities, even in the presence of parametric uncertainties. Experimental results on our custom quadrotor platform validate the performance and robustness of the proposed attitude controller.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
This paper introduces a quaternion based attitude controller, by augmenting a novel baseline controller with model reference adaptive control techniques (MRAC). In contrast to existing designs, the baseline controller makes use of the quaternion logarithm and the standard bi-invariant distance on SO(3). The adaptation restores the behavior of a time dependent reference model in case of model discrepancies. Moreover, we make use of the fact that the parameters, characterizing the gyroscopic coupling term of a rigid tumbling body, are naturally bounded to some predefined manifold and incorporate this information in our adaptive design. Altogether, the proposed design enables aggressive, high bandwidth acrobatic flight maneuvers over the whole attitude range without singularities, even in the presence of parametric uncertainties. Experimental results on our custom quadrotor platform validate the performance and robustness of the proposed attitude controller.
2018
Li, Z; Acuna, R; Willert, V
Cooperative Localization by Fusing Pose Estimates from Static Environmental and Mobile Fiducial Features Inproceedings
In: Proc. of IEEE Latin American Robotics Symposium, pp. 65–70, IEEE, 2018.
@inproceedings{Acuna2018d,
title = {Cooperative Localization by Fusing Pose Estimates from Static Environmental and Mobile Fiducial Features},
author = {Z Li and R Acuna and V Willert},
url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8588528&isnumber=8588507},
doi = {10.1109/LARS/SBR/WRE.2018.00021},
year = {2018},
date = {2018-11-01},
booktitle = {Proc. of IEEE Latin American Robotics Symposium},
pages = {65--70},
publisher = {IEEE},
abstract = {In this paper, we propose a novel, purely vision-based cooperative localization approach for the multi-robot system to collaboratively improve the localization robustness and accuracy by fusing absolute pose estimates from static environment features with relative pose estimates from known mobile fiducial features. The fusion algorithm is formulated as an optimization problem combining two different objectives for two different feature sources based on the same error measure, namely the reprojection error. The optimization is solved at an on-line frame-by-frame rate to produce optimal positioning results during the robots' movement. The fiducial markers are attached to the mobile robots, thus no marker intervention is needed to add into the environment. A comparison between our cooperative localization approach and state-of-the-art localization algorithms for different configurations concerning various testing environments is given validating the improvements on both robustness and accuracy.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we propose a novel, purely vision-based cooperative localization approach for the multi-robot system to collaboratively improve the localization robustness and accuracy by fusing absolute pose estimates from static environment features with relative pose estimates from known mobile fiducial features. The fusion algorithm is formulated as an optimization problem combining two different objectives for two different feature sources based on the same error measure, namely the reprojection error. The optimization is solved at an on-line frame-by-frame rate to produce optimal positioning results during the robots' movement. The fiducial markers are attached to the mobile robots, thus no marker intervention is needed to add into the environment. A comparison between our cooperative localization approach and state-of-the-art localization algorithms for different configurations concerning various testing environments is given validating the improvements on both robustness and accuracy.
Acuna, Raul; Willert, Volker
Dynamic Markers: UAV landing proof of concept Inproceedings
In: Proc. of IEEE Latin American Robotics Symposium, pp. 496–502, IEEE, Joao Pessoa, 2018.
@inproceedings{Acuna2018a,
title = {Dynamic Markers: UAV landing proof of concept},
author = {Raul Acuna and Volker Willert},
url = {http://www.racuna.de/wp-content/uploads/2019/01/Dynamic-Markers-UAV-landing-proof-of-concept.pdf
https://ieeexplore.ieee.org/abstract/document/8588599},
doi = {10.1109/LARS/SBR/WRE.2018.00093},
year = {2018},
date = {2018-01-01},
booktitle = {Proc. of IEEE Latin American Robotics Symposium},
pages = {496--502},
publisher = {IEEE},
address = {Joao Pessoa},
abstract = {In this paper, we introduce a dynamic fiducial marker which can change its appearance according to the spatio-temporal requirements of the visual perception task of a mobile robot using a camera as sensor. We present a control scheme to dynamically change the appearance of the marker such that the pose of the robot can be optimally estimated from the camera image. The appearance control takes into account the dependency of the estimation quality on the current pose of the camera in relation to the marker.Hence, we realize a tight coupling between the visual pose control of the mobile robot and the appearance control of the dynamic fiducial marker. Further on, we discuss the implications of time delays because of processing time and communication delays between the robot and the marker. Finally, we propose a real time dynamic marker visual servoing control scheme for quadcopter landing and evaluate the performance on a real world example.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we introduce a dynamic fiducial marker which can change its appearance according to the spatio-temporal requirements of the visual perception task of a mobile robot using a camera as sensor. We present a control scheme to dynamically change the appearance of the marker such that the pose of the robot can be optimally estimated from the camera image. The appearance control takes into account the dependency of the estimation quality on the current pose of the camera in relation to the marker.Hence, we realize a tight coupling between the visual pose control of the mobile robot and the appearance control of the dynamic fiducial marker. Further on, we discuss the implications of time delays because of processing time and communication delays between the robot and the marker. Finally, we propose a real time dynamic marker visual servoing control scheme for quadcopter landing and evaluate the performance on a real world example.
Acuna, Raul; Li, Zaijuan; Willert, Volker
MOMA: Visual Mobile Marker Odometry Inproceedings
In: IEEE Int. Conf. on Indoor Positioning and Indoor Navigation (IPIN), pp. 206–212, Nantes, 2018.
@inproceedings{Acuna2018b,
title = {MOMA: Visual Mobile Marker Odometry},
author = {Raul Acuna and Zaijuan Li and Volker Willert},
url = {http://www.racuna.de/wp-content/uploads/2019/01/MOMA_visual_mobile_marker_odometry.pdf
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8533685&isnumber=8533678},
doi = {10.1109/IPIN.2018.8533685},
year = {2018},
date = {2018-01-01},
booktitle = {IEEE Int. Conf. on Indoor Positioning and Indoor Navigation (IPIN)},
pages = {206--212},
address = {Nantes},
abstract = {In this paper, we present a cooperative visual odometry system based on the detection of mobile markers. To this end, we introduce a simple scheme that realizes visual mobile marker odometry via accurate fixed marker-based camera positioning and we discuss the characteristics of errors inherent to the method compared to classical fixed marker-based navigation and visual odometry. The proposed cooperative scheme has the advantage of not needing any feature or fiducial marker in the environment, which can be used for indoor and underwater applications where it can be harder to extract reliable features. We provide specific configurations of UAV and UGV robots including one that allows continuous movements of the UAV, and a minimal caterpillar-like configuration that works with one UGV alone. Finally, we present a real-world implementation and an evaluation of the proposed configurations.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we present a cooperative visual odometry system based on the detection of mobile markers. To this end, we introduce a simple scheme that realizes visual mobile marker odometry via accurate fixed marker-based camera positioning and we discuss the characteristics of errors inherent to the method compared to classical fixed marker-based navigation and visual odometry. The proposed cooperative scheme has the advantage of not needing any feature or fiducial marker in the environment, which can be used for indoor and underwater applications where it can be harder to extract reliable features. We provide specific configurations of UAV and UGV robots including one that allows continuous movements of the UAV, and a minimal caterpillar-like configuration that works with one UGV alone. Finally, we present a real-world implementation and an evaluation of the proposed configurations.
Acuna, Raul; Zhang, Ding; Willert, Volker
Vision-based UAV landing on a moving platform in GPS denied environments using motion prediction Inproceedings
In: Proc. of IEEE Latin American Robotics Symposium, pp. 515–521, IEEE, João Pessoa, Brazil, 2018.
@inproceedings{Acuna2018c,
title = {Vision-based UAV landing on a moving platform in GPS denied environments using motion prediction},
author = {Raul Acuna and Ding Zhang and Volker Willert},
url = {http://www.racuna.de/wp-content/uploads/2019/01/UAV_landing_on_moving_platform.pdf
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8588602&isnumber=8588507},
year = {2018},
date = {2018-01-01},
booktitle = {Proc. of IEEE Latin American Robotics Symposium},
pages = {515--521},
publisher = {IEEE},
address = {Jo\~{a}o Pessoa, Brazil},
abstract = {In this paper, we propose a vision-based control system which enables a multi-rotor unmanned aerial vehicle (UAV) to track an unmanned ground vehicle (UGV) and land on it by using mainly the input of an integrated vision sensor without external localization systems. Our solution is able to generate and follow agile approaching maneuvers in which the target vehicle may leave the field of view of the UAV's vision sensor. This is particularly relevant in scenarios where external localization systems such as GPS are not available or not reliable. In our approach, the UAV observes the movement of the UGV, predicts its motion and generates a smooth approach trajectory to the predicted position. A 6-DOF controller in cascade form is used to track the trajectory, which can lead to movements were the UGV is lost from the field of view (FOV), and then once the UGV is back on the FOV a normal visual servoing tracking is used for landing. The UAV states required for the control law were obtained from an Extended Kalman Filter in combination with a Mahony complementary filter using only internal sensors. The control law and the landing state machine were implemented in ROS and the simulations were developed on Gazebo based on the Rotors simulator.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we propose a vision-based control system which enables a multi-rotor unmanned aerial vehicle (UAV) to track an unmanned ground vehicle (UGV) and land on it by using mainly the input of an integrated vision sensor without external localization systems. Our solution is able to generate and follow agile approaching maneuvers in which the target vehicle may leave the field of view of the UAV's vision sensor. This is particularly relevant in scenarios where external localization systems such as GPS are not available or not reliable. In our approach, the UAV observes the movement of the UGV, predicts its motion and generates a smooth approach trajectory to the predicted position. A 6-DOF controller in cascade form is used to track the trajectory, which can lead to movements were the UGV is lost from the field of view (FOV), and then once the UGV is back on the FOV a normal visual servoing tracking is used for landing. The UAV states required for the control law were obtained from an Extended Kalman Filter in combination with a Mahony complementary filter using only internal sensors. The control law and the landing state machine were implemented in ROS and the simulations were developed on Gazebo based on the Rotors simulator.
Acuna, Raul; Ziegler, Robin; Willert, Volker
Single pose camera calibration using a curved display screen Inproceedings
In: Forum Bildverarbeitung, pp. 25–36, KIT Scientific Publishing, Karlsruhe, 2018.
@inproceedings{Acuna2018e,
title = {Single pose camera calibration using a curved display screen},
author = {Raul Acuna and Robin Ziegler and Volker Willert},
url = {http://www.racuna.de/wp-content/uploads/2019/01/single_pose_camera_calibration_curved_screen.pdf
https://books.google.de/books?hl=en&lr=&id=CK19DwAAQBAJ&oi=fnd&pg=PA25&ots=XUJmnwts96&sig=18DuYoRsTxxtkd0DPheU1ZUn6tQ#v=onepage&q&f=false http://dx.doi.org/10.5445/KSP/1000085290 https://publikationen.bibliothek.kit.edu/1000085290},
doi = {10.5445/KSP/1000085290},
year = {2018},
date = {2018-01-01},
booktitle = {Forum Bildverarbeitung},
pages = {25--36},
publisher = {KIT Scientific Publishing},
address = {Karlsruhe},
abstract = {In this paper a method for single pose camera calibration is presented. Dense point correspondences are obtained by displaying structured light in a non-flat display screen (i.e. a curved display screen) which then are used as an input in common calibration algorithms. Experimental results demonstrate that the depth information present in a common commercial curved monitor with a radius of curvature of 1800 millimeters is sufficient in order to obtain calibration results comparable to the standard checkerboard method. In contrast with the commonly used checkerboard based calibration methods, the proposed method does not require to move the camera and it is a cheaper and easier to implement that other methods based on expensive 3D calibration rigs.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper a method for single pose camera calibration is presented. Dense point correspondences are obtained by displaying structured light in a non-flat display screen (i.e. a curved display screen) which then are used as an input in common calibration algorithms. Experimental results demonstrate that the depth information present in a common commercial curved monitor with a radius of curvature of 1800 millimeters is sufficient in order to obtain calibration results comparable to the standard checkerboard method. In contrast with the commonly used checkerboard based calibration methods, the proposed method does not require to move the camera and it is a cheaper and easier to implement that other methods based on expensive 3D calibration rigs.
Acuna, Raul; Willert, Volker
Insights into the robustness of control point configurations for homography and planar pose estimation Journal Article
In: CoRR, abs/1803.0 , 2018.
@article{DBLP:journals/corr/abs-1803-03025,
title = {Insights into the robustness of control point configurations for homography and planar pose estimation},
author = {Raul Acuna and Volker Willert},
url = {http://www.racuna.de/wp-content/uploads/2019/01/optimal_control_points_homography_pose_estimation.pdf
http://arxiv.org/abs/1803.03025},
year = {2018},
date = {2018-01-01},
journal = {CoRR},
volume = {abs/1803.0},
abstract = {In this paper, we investigate the influence of the spatial configuration of a number of $n backslashgeq 4$ control points on the accuracy and robustness of space resection methods, e.g. used by a fiducial marker for pose estimation. We find robust configurations of control points by minimizing the first order perturbed solution of the DLT algorithm which is equivalent to minimizing the condition number of the data matrix. An empirical statistical evaluation is presented verifying that these optimized control point configurations not only increase the performance of the DLT homography estimation but also improve the performance of planar pose estimation methods like IPPE and EPnP, including the iterative minimization of the reprojection error which is the most accurate algorithm. We provide the characteristics of stable control point configurations for real-world noisy camera data that are practically independent on the camera pose and form certain symmetric patterns dependent on the number of points. Finally, we present a comparison of optimized configuration versus the number of control points.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In this paper, we investigate the influence of the spatial configuration of a number of $n backslashgeq 4$ control points on the accuracy and robustness of space resection methods, e.g. used by a fiducial marker for pose estimation. We find robust configurations of control points by minimizing the first order perturbed solution of the DLT algorithm which is equivalent to minimizing the condition number of the data matrix. An empirical statistical evaluation is presented verifying that these optimized control point configurations not only increase the performance of the DLT homography estimation but also improve the performance of planar pose estimation methods like IPPE and EPnP, including the iterative minimization of the reprojection error which is the most accurate algorithm. We provide the characteristics of stable control point configurations for real-world noisy camera data that are practically independent on the camera pose and form certain symmetric patterns dependent on the number of points. Finally, we present a comparison of optimized configuration versus the number of control points.
2016
Ruiz, Elvis; Acuña, Raul
Safe Navigation of Mobile Robots Using a Hybrid Navigation Framework with a Fuzzy Logic Decision Process Book Chapter
In: Santos Os'orio, Fernando; Sales Gonçalves, Rog'erio (Ed.): Robotics: 12th Latin American Robotics Symposium and Third Brazilian Symposium on Robotics, LARS 2015/SBR 2015, Uberl^andia, Brazil, October 28 - November 1, 2015, Revised Selected Papers, pp. 39–56, Springer International Publishing, Cham, 2016, ISBN: 978-3-319-47247-8.
@inbook{Ruiz2016,
title = {Safe Navigation of Mobile Robots Using a Hybrid Navigation Framework with a Fuzzy Logic Decision Process},
author = {Ruiz, Elvis
and Acu\~{n}a, Raul},
editor = {Santos Os'orio, Fernando
and Sales Gon\c{c}alves, Rog'erio},
url = {http://dx.doi.org/10.1007/978-3-319-47247-8_3},
doi = {10.1007/978-3-319-47247-8_3},
isbn = {978-3-319-47247-8},
year = {2016},
date = {2016-01-01},
booktitle = {Robotics: 12th Latin American Robotics Symposium and Third Brazilian Symposium on Robotics, LARS 2015/SBR 2015, Uberl^andia, Brazil, October 28 - November 1, 2015, Revised Selected Papers},
pages = {39--56},
publisher = {Springer International Publishing},
address = {Cham},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
2015
Ruiz, Elvis; Acuña, Raul; Vélez, Pedro; Fernández-López, Gerardo
Hybrid deliberative reactive navigation system for mobile robots using ROS and Fuzzy Logic Control Inproceedings
In: 2015 12th Latin American Robotics Symposium and 2015 Third Brazilian Symposium on Robotics, pp. 67–72, IEEE Comput. Soc, 2015, ISBN: 9781467371292.
@inproceedings{ElvisRuiz2015,
title = {Hybrid deliberative reactive navigation system for mobile robots using ROS and Fuzzy Logic Control},
author = {Elvis Ruiz and Acu\~{n}a, Raul and V\'{e}lez, Pedro and Fern\'{a}ndez-L\'{o}pez, Gerardo},
url = {http://www.rag.com.ve/wp-content/uploads/2016/02/Elvis-Ruiz-et-al.-2015-Hybrid-deliberative-reactive-navigation-system-for-mobile-robots-using-ROS-and-Fuzzy-Logic-Control.pdf},
doi = {10.1109/LARS-SBR.2015.24},
isbn = {9781467371292},
year = {2015},
date = {2015-01-01},
booktitle = {2015 12th Latin American Robotics Symposium and 2015 Third Brazilian Symposium on Robotics},
pages = {67--72},
publisher = {IEEE Comput. Soc},
abstract = {Autonomous navigation involves solving problems of perception, localization, planning and control. Based on how these problems can be solved it is possible to have a deliberative, reactive or deliberative-reactive (hybrid) navigation. Additionally, navigation must meet security requirements for both the robot and humans operating in the same workspace. Thus, a navigation system for differential hybrid mobile robots in structured environments was designed, which integrates the advantages of a high level deliberative planner with a reactive low-level control and easing some of its weaknesses. For this, a fuzzy logic controller was implemented. The proposed system was tested with a simulated robot Amigobot with a Kinect sensor using V-REP and ROS.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Autonomous navigation involves solving problems of perception, localization, planning and control. Based on how these problems can be solved it is possible to have a deliberative, reactive or deliberative-reactive (hybrid) navigation. Additionally, navigation must meet security requirements for both the robot and humans operating in the same workspace. Thus, a navigation system for differential hybrid mobile robots in structured environments was designed, which integrates the advantages of a high level deliberative planner with a reactive low-level control and easing some of its weaknesses. For this, a fuzzy logic controller was implemented. The proposed system was tested with a simulated robot Amigobot with a Kinect sensor using V-REP and ROS.
2013
Ruiz, Elvis; Acuña, Raúl; Certad-H, Novel; Terrones, Angel; Cabrera, María Eugenia
Development of a control platform for the mobile robot Roomba using ROS and a Kinect sensor Inproceedings
In: IEEE Lars 2013, pp. –, 2013.
@inproceedings{Ruiz2013,
title = {Development of a control platform for the mobile robot Roomba using ROS and a Kinect sensor},
author = {Ruiz, Elvis and Acu\~{n}a, Ra\'{u}l and Certad-H, Novel and Terrones, Angel and Cabrera, Mar\'{i}a Eugenia},
url = {http://www.rag.com.ve/wp-content/uploads/2013/09/Development-of-a-control-platform-for-the-mobile-robot-Roomba-using-ROS-and-a-Kinect-sensor.pdf},
year = {2013},
date = {2013-01-01},
booktitle = {IEEE Lars 2013},
pages = {--},
abstract = {A control scheme for the mobile robot Roomba was developed using ROS (robot operating system), which allowed the control of the robot using velocity vector references. A Kinect sensor was incorporated into the system and also a framework for communication which provided communication with processes in other instances, monitoring and remote control. The system is flexible enough to be replicated in the future in other Roomba robots. With this framework it is possible to control the movement of the robot using vector references generated from the spatial references extracted from de environment using the Kinect sensor.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
A control scheme for the mobile robot Roomba was developed using ROS (robot operating system), which allowed the control of the robot using velocity vector references. A Kinect sensor was incorporated into the system and also a framework for communication which provided communication with processes in other instances, monitoring and remote control. The system is flexible enough to be replicated in the future in other Roomba robots. With this framework it is possible to control the movement of the robot using vector references generated from the spatial references extracted from de environment using the Kinect sensor.
2012
Mastalli, Carlos; Cappelletto, José; Acuña, Raúl; Terrones, Angel; Fernández-López, Gerardo
An Imitation Learning Approach For Truck Loading Operations in Backhoe Machines Incollection
In: Azad, A K M; Cowan, N J; Tokhi, M O; Virk, G S; Eastman, R D (Ed.): Adaptive Mobile Robotics, pp. 827–830, World Scientific, Baltimore, 2012, ISBN: 978-981-4415-94-1.
@incollection{Mastalli2012,
title = {An Imitation Learning Approach For Truck Loading Operations in Backhoe Machines},
author = {Mastalli, Carlos and Cappelletto, Jos\'{e} and Acu\~{n}a, Ra\'{u}l and Terrones, Angel and Fern\'{a}ndez-L\'{o}pez, Gerardo},
editor = {A K M Azad and N J Cowan and M O Tokhi and G S Virk and R D Eastman},
url = {http://www.rag.com.ve/wp-content/uploads/2013/09/An-imitation-learning-approach-for-truck-loading-operations-in-backhoe-machines.pdf
http://www.worldscientific.com/doi/abs/10.1142/9789814415958_0104},
isbn = {978-981-4415-94-1},
year = {2012},
date = {2012-01-01},
booktitle = {Adaptive Mobile Robotics},
pages = {827--830},
publisher = {World Scientific},
address = {Baltimore},
abstract = {This paper presents a motion planning and control system architecture development for autonomous earthmoving operations in excavating machines such as loading a dump truck. The motion planning system is imitation learning based, which is a general approach for learning motor skills from human demonstration. This scheme of supervised learning is based on a dynamical movement primitives (DMP) as control policies (CP). The DMP is a non-linear differential equation that encode movements, which are used to learn tasks in backhoe machines. A general architecture to achieve autonomous truck loading operations is described. Also, the effectiveness of our approach for truck loading task is demonstrated, where the machine can adapt to different operating scenarios. Read More: http://www.worldscientific.com/doi/abs/10.1142/9789814415958_0104},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
This paper presents a motion planning and control system architecture development for autonomous earthmoving operations in excavating machines such as loading a dump truck. The motion planning system is imitation learning based, which is a general approach for learning motor skills from human demonstration. This scheme of supervised learning is based on a dynamical movement primitives (DMP) as control policies (CP). The DMP is a non-linear differential equation that encode movements, which are used to learn tasks in backhoe machines. A general architecture to achieve autonomous truck loading operations is described. Also, the effectiveness of our approach for truck loading task is demonstrated, where the machine can adapt to different operating scenarios. Read More: http://www.worldscientific.com/doi/abs/10.1142/9789814415958_0104
Certad-H, Novel; Acuña, Raúl; Terrones, Angel; Ralev, Dimitar; Cappelletto, José; Grieco, J
Study and Improvements in Landmarks Extraction in 2D Range Images Based on an Adaptive Curvature Estimation Inproceedings
In: Andean Region International Conference (ANDESCON), 2012 VI, pp. 95–98, Cuenca, 2012.
@inproceedings{Certad-H,
title = {Study and Improvements in Landmarks Extraction in 2D Range Images Based on an Adaptive Curvature Estimation},
author = {Certad-H, Novel and Acu\~{n}a, Ra\'{u}l and Terrones, Angel and Ralev, Dimitar and Cappelletto, Jos\'{e} and Grieco, J},
url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6424128&isnumber=6424102
http://www.rag.com.ve/wp-content/uploads/2013/09/Study-and-improvements-in-landmarks-extraction-in-2D-range-images-based-on-an-adaptive-curvature-estimation.pdf},
year = {2012},
date = {2012-01-01},
booktitle = {Andean Region International Conference (ANDESCON), 2012 VI},
pages = {95--98},
address = {Cuenca},
abstract = {In this work we present an analysis of the natural reference extraction method (corners, intersections, hallways) using the estimated curvature function for 2D images provided by a laser range finder. Some of the problems from the original method introduced in 2007 are considered and possible solutions to this problems are proposed. Finally, the original and modified methods are submitted to various simulated benchmarks in order to compare their performance as a function of uncertainty, correctness, execution time and other parameters.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this work we present an analysis of the natural reference extraction method (corners, intersections, hallways) using the estimated curvature function for 2D images provided by a laser range finder. Some of the problems from the original method introduced in 2007 are considered and possible solutions to this problems are proposed. Finally, the original and modified methods are submitted to various simulated benchmarks in order to compare their performance as a function of uncertainty, correctness, execution time and other parameters.
Acuña, Raúl; Terrones, Angel; Certad-H, Novel; Fermín-León, Leonardo; Fernández-Lópezs, Gerardo
Dynamic Potential Field Generation Using Movement Prediction Incollection
In: Azad, A K M; Cowan, N J; Tokhi, M O; Virk, G S; Eastman, R D (Ed.): Adaptive Mobile Robotics, pp. 773–780, World Scientific, Baltimore, 2012, ISBN: 10.1142/9789814415958_0098.
@incollection{Acuna2012,
title = {Dynamic Potential Field Generation Using Movement Prediction},
author = {Acu\~{n}a, Ra\'{u}l and Terrones, Angel and Certad-H, Novel and Ferm\'{i}n-Le\'{o}n, Leonardo and Fern\'{a}ndez-L\'{o}pezs, Gerardo},
editor = {A K M Azad and N J Cowan and M O Tokhi and G S Virk and R D Eastman},
url = {http://www.worldscientific.com/doi/abs/10.1142/9789814415958_0098
http://www.rag.com.ve/wp-content/uploads/2013/09/Dynamic-Potential-field-Generation-using-movement-prediction.pdf},
isbn = {10.1142/9789814415958_0098},
year = {2012},
date = {2012-01-01},
booktitle = {Adaptive Mobile Robotics},
pages = {773--780},
publisher = {World Scientific},
address = {Baltimore},
abstract = {Path-planning in dynamic environments while meeting safety requirements for robots and humans is an open problem in robotics. The successful navigation in this kind of environments requires a certain level of anticipation to the future behavior of moving objects. In this paper we propose the use of movement prediction in the generation of dynamic artificial potential fields (DAPF), which will allow the robot to navigate in highly dynamic environments with a major degree of safety and effectiveness, especially in cases where the obstacles and objectives move at higher velocities than the controlled robots. Our approach is based on previous works on potential and velocity fields with additional considerations to avoid the well known local minimum problem and to anticipate the predicted path of objects, our solution tries to maintain the reactive characteristics of the artificial potential fields. The proposed method was tested in a holonomic simulation with 100% better results for the same scenarios than the original fields without prediction. Read More: http://www.worldscientific.com/doi/abs/10.1142/9789814415958_0098},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Path-planning in dynamic environments while meeting safety requirements for robots and humans is an open problem in robotics. The successful navigation in this kind of environments requires a certain level of anticipation to the future behavior of moving objects. In this paper we propose the use of movement prediction in the generation of dynamic artificial potential fields (DAPF), which will allow the robot to navigate in highly dynamic environments with a major degree of safety and effectiveness, especially in cases where the obstacles and objectives move at higher velocities than the controlled robots. Our approach is based on previous works on potential and velocity fields with additional considerations to avoid the well known local minimum problem and to anticipate the predicted path of objects, our solution tries to maintain the reactive characteristics of the artificial potential fields. The proposed method was tested in a holonomic simulation with 100% better results for the same scenarios than the original fields without prediction. Read More: http://www.worldscientific.com/doi/abs/10.1142/9789814415958_0098
Cabrera, María Eugenia; Bogado, Juan Manuel; Acuña, Raúl; Fermín, Leonardo; Ralev, Dimitar
Glove-Based Gesture Recognition System Incollection
In: Azad, A K M; Cowan, N J; Tokhi, M O; Virk, G S; Eastman, R D (Ed.): Adaptive Mobile Robotics, pp. 747–753, World Scientific, Baltimore, 2012, ISBN: 978-981-4415-94-1.
@incollection{Cabrera2012,
title = {Glove-Based Gesture Recognition System},
author = {Cabrera, Mar\'{i}a Eugenia and Bogado, Juan Manuel and Acu\~{n}a, Ra\'{u}l and Ferm\'{i}n, Leonardo and Ralev, Dimitar},
editor = {A K M Azad and N J Cowan and M O Tokhi and G S Virk and R D Eastman},
url = {http://www.worldscientific.com/doi/abs/10.1142/9789814415958_0095
http://www.rag.com.ve/wp-content/uploads/2013/09/Glove-based-gesture-recognition-system.pdf},
isbn = {978-981-4415-94-1},
year = {2012},
date = {2012-01-01},
booktitle = {Adaptive Mobile Robotics},
pages = {747--753},
publisher = {World Scientific},
address = {Baltimore},
abstract = {Among the research topics developing within the Mechatronics Group at Simon Bolivar University, there’s a field corresponding to Human-Computer Interaction (HCI), which is the center of this paper, regarding the design and implementation of a hand gesture recognition system, based on the information gathered with a data glove. The data glove sensors convey the degree of flexion in each finger of the hand. Additionally, an accelerometer sensor was placed on top of the glove to acquire the orientation of the hand in three axes. With this information, the system would begin a decision making process based on artificial intelligence tools, like neural networks, to recognize the American Sign Language (ASL) signs for fingerspelling. The whole system is executed by interfacing with a user, to collect the data and display the result of its classification. Read More: http://www.worldscientific.com/doi/abs/10.1142/9789814415958_0095},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Among the research topics developing within the Mechatronics Group at Simon Bolivar University, there’s a field corresponding to Human-Computer Interaction (HCI), which is the center of this paper, regarding the design and implementation of a hand gesture recognition system, based on the information gathered with a data glove. The data glove sensors convey the degree of flexion in each finger of the hand. Additionally, an accelerometer sensor was placed on top of the glove to acquire the orientation of the hand in three axes. With this information, the system would begin a decision making process based on artificial intelligence tools, like neural networks, to recognize the American Sign Language (ASL) signs for fingerspelling. The whole system is executed by interfacing with a user, to collect the data and display the result of its classification. Read More: http://www.worldscientific.com/doi/abs/10.1142/9789814415958_0095
Terrones, Angel; Acuña, Raúl; Certad-H, Novel; Fermín-León, Leonardo; Fernández-López, Gerardo
Local Distributed Control For Multi-Robot Navigation Incollection
In: Azad, A K M; Cowan, N J; Tokhi, M O; Virk, G S; Eastman, R D (Ed.): Adaptive Mobible Robotics, pp. 797–804, World Scientific, Baltimore, 2012, ISBN: 978-981-4415-94-1.
@incollection{Terrones,
title = {Local Distributed Control For Multi-Robot Navigation},
author = {Terrones, Angel and Acu\~{n}a, Ra\'{u}l and Certad-H, Novel and Ferm\'{i}n-Le\'{o}n, Leonardo and Fern\'{a}ndez-L\'{o}pez, Gerardo},
editor = {A K M Azad and N J Cowan and M O Tokhi and G S Virk and R D Eastman},
url = {http://www.worldscientific.com/doi/abs/10.1142/9789814415958_0101
http://www.rag.com.ve/wp-content/uploads/2013/09/Local-Distributed-Control-for-Multi-robot-navigation.pdf},
isbn = {978-981-4415-94-1},
year = {2012},
date = {2012-01-01},
booktitle = {Adaptive Mobible Robotics},
pages = {797--804},
publisher = {World Scientific},
address = {Baltimore},
abstract = {In this work a distributed navigation control strategy for multi-robot systems based only in the local information provided by the robots is presented. Each robot calculates the vector forces required for navigation towards a goal avoiding possible obstacles on the workspace and traveling in formation with other members of the swarm. A control architecture was implemented for the generation of the vector force used for navigation, based on three basic behavior agents responsible of calculating individual force components needed for navigation to the target, obstacle avoidance and swarm navigation. Also, an event driven control system is in charge of assigning a priority level to each force component generated by the agents of basic behaviors. Results obtained in simulations show the effectiveness of the control system in the navigation of a system of multiple robots under different obstacle configuration.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
In this work a distributed navigation control strategy for multi-robot systems based only in the local information provided by the robots is presented. Each robot calculates the vector forces required for navigation towards a goal avoiding possible obstacles on the workspace and traveling in formation with other members of the swarm. A control architecture was implemented for the generation of the vector force used for navigation, based on three basic behavior agents responsible of calculating individual force components needed for navigation to the target, obstacle avoidance and swarm navigation. Also, an event driven control system is in charge of assigning a priority level to each force component generated by the agents of basic behaviors. Results obtained in simulations show the effectiveness of the control system in the navigation of a system of multiple robots under different obstacle configuration.
2009
Estévez, Pablo; Cappelletto, José; Alvarez, Fernando; Acuña, Raúl; Fernández, G.; Grieco, J.; Armada, Manuel
Navegación Coordinada de un sistema multirobot usando campos de velocidades dinámicos. Incollection
In: RoboCity 2030. "5º Workshop, Cooperación en Robótica", pp. 79–103, 2009.
@incollection{Estevez2009a,
title = {Navegaci\'{o}n Coordinada de un sistema multirobot usando campos de velocidades din\'{a}micos.},
author = {Est\'{e}vez, Pablo and Cappelletto, Jos\'{e} and Alvarez, Fernando and Acu\~{n}a, Ra\'{u}l and Fern\'{a}ndez, G. and Grieco, J. and Armada, Manuel},
year = {2009},
date = {2009-01-01},
booktitle = {RoboCity 2030. "5º Workshop, Cooperaci\'{o}n en Rob\'{o}tica"},
pages = {79--103},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
2007
Estévez, P; Cappelletto, J; Acuña, R; Alvarez, F; Fernandez-López, G
Coordinated Navigation Using Dynamically Varying Velocity Fields Inproceedings
In: 9-th International Conference Artificial Intelligence and Soft Computing, Zakopane, 2007.
@inproceedings{Estevez2007b,
title = {Coordinated Navigation Using Dynamically Varying Velocity Fields},
author = {Est\'{e}vez, P and Cappelletto, J and Acu\~{n}a, R and Alvarez, F and Fernandez-L\'{o}pez, G},
url = {http://www.rag.com.ve/wp-content/uploads/2016/02/Coordinated-Navigation-Using-Dynamically-Varying-Velocity-Fields.pdf},
year = {2007},
date = {2007-01-01},
booktitle = {9-th International Conference Artificial Intelligence and Soft Computing},
address = {Zakopane},
abstract = {Abstract. This paper describes a framework for dynamically generated and temporary evolving fields for coordinated robot navigation. The ap- proach based on static fields usually faces the problem of saddle points and local minima preventing the achievement of the goals. This approach overcomes the aforementioned drawbacks by dynamically changing the field definitions through an insistence schema where unfulfilled goals in- crease their effect on robots movements. These algorithm and schema are described and tested to evaluate and compare this idea against classical field approaches. The results show an improvement on the capabilities of the systemto deal with the proposed tasks, thus validating this approach.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Abstract. This paper describes a framework for dynamically generated and temporary evolving fields for coordinated robot navigation. The ap- proach based on static fields usually faces the problem of saddle points and local minima preventing the achievement of the goals. This approach overcomes the aforementioned drawbacks by dynamically changing the field definitions through an insistence schema where unfulfilled goals in- crease their effect on robots movements. These algorithm and schema are described and tested to evaluate and compare this idea against classical field approaches. The results show an improvement on the capabilities of the systemto deal with the proposed tasks, thus validating this approach.