Skip to main content

TECNICAS DE INTELIGENCIA ARTIFICIAL Y AYUDA A LA NAVEGACION AUTONOMA

DPI2017-86915-C3-3-R

•
Funding agency name Agencia Estatal de Investigación
Funding agency acronym AEI
Program Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Call Proyectos I+D+i Retos de Investigación
Call year 2017
State Plan 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Beneficiary centre UNIVERSIDAD POLITECNICA DE MADRID

Resultados relacionados

Resultados totales (Incluyendo duplicados): 11
Encontrada(s) 1 página(s)

DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

Transient response comparison of feedback and feed-forward compensation methods in systems with zero steady state error

  • Matía, Fernando
Proportional–Integral–Derivative (PID) controllers with integral action are conventionally used as feedback controllers. They are used to obtain zero steady‐state error when the reference input or the disturbance are steps and where zero‐type systems (i.e. with no poles at the origin) are controlled. The controller meets its objective when the controlled system is non linear, but usually introduces undesirable changes in the dynamics that must be compensated by readjusting the proportional gain. In this paper, we compare PID with two alternative techniques based on the use of a feed‐forward system and a multiple feedback system, respectively. A detailed comparison of the transient response obtained with these methods is presented and validated with some simulation examples., This research is in receipt of funding from the Spanish Ministry of Science, Innovation and Universities (COG-DRIVE project: Artificial Intelligence Techniques and Assistance to Autonomous Navigation, reference DPI2017-86915-C3-3-R). It has also received funding from the RoboCity2030-DIH-CM Madrid Robotics Digital Innova-tion Hub project (Robótica aplicada a la mejora de la cali-dad de vida de los ciudadanos. fase IV; S2018/NMT-4331),funded by Programas de Actividades I+D en la Comunidad de Madrid and cofunded through EU Structural Funds, Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

Grasping Objects From the Floor in Assistive Robotics: Real World Implications and Lessons Learned

  • Puente, Paloma de la
  • Fischinger, David
  • Bajones, Markus
  • Wolf, Daniel
  • Vincze, Markus
This paper presents a system enabling a mobile robot to autonomously pick-up objects a human is pointing at from the oor. The system does not require object models and is designed to grasp unknown objects. The robot decides by itself if an object is suitable for grasping by considering measures of size, position and the environment suitability. The implementation is built on the second prototype of the home care robot Hobbit, thereby verifying that complex robotic manipulation tasks can be performed with economical hardware. The presented system was already tested in real apartments with elderly people. We highlight this by discussing the additional complexity for complete autonomous behavior in apartments compared with tests in labs., This work was supported in part by the European Community's Seventh Framework Programme (FP7/2007-2013) under Grant 288146, HOBBIT, in part by the Spanish Ministry of Science, Innovation and Universities through the project COGDRIVE - Arti cial Intelligence Techniques and Assistance to Autonomous Navigation under Grant DPI2017-86915-C3-3-R, in part by the RoboCity2030-DIH-CM, Madrid Robotics Digital Innovation Hub, under Grant S2018/NMT-4331, in part by the Programas de Actividades ICD en la Comunidad de Madrid, and in part by the Structural Funds of the EU., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

Control of multivariable delayed systems with colored noise using incremental state formulation

  • Al-Hadithi, Basil Mohammed
  • Adánez, José Miguel
  • Jiménez, Agustín
In this work, a novel approach based on incremental state models is proposed for the modeling and control of multivariable delayed systems with colored noise. One of the key features of the new approach is that the proposed incremental state model compared with the non-incremental one, solves the problem of computing the target state in a natural way, since for a desired output, a zero incremental state can be taken as an objective. Moreover, the control action in an incremental form is equivalent to introduce an integral action, thereby cancelling the steady state errors, even in presence of disturbances. An optimal Linear Quadratic Regulator (LQR) control, based on the incremental model, is proposed and a Kalman filter is used to obtain the estimated state. Thus, another advantage of the proposed method is minimizing the output variance. Illustrative examples are chosen to evaluate the effectiveness of the proposed method., This work is funded by Spanish Ministry of Economy and Competitiveness through the projects: Assisted Navigation through Natural Language (NAVEGASE) project (DPI2014-53525-C3-1-R) and Cognition Inspired Navigation for Autonomous Driving (COGDRIVE) project (DPI2017-86915-C3-3-R)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

A new branch-and-bound algorithm for the maximum edge-weighted clique problem

  • San Segundo, Pablo
  • Coniglio, Stefano
  • Furini, Fabio
  • Ljubić, Ivana
We study the maximum edge-weighted clique problem, a problem related to the maximum (vertex-weighted) clique problem which asks for finding a complete subgraph (i.e., a clique) of maximum total weight on its edges. The problem appears in a wide range of applications, including bioinformatics, material science, computer vision, robotics, and many more. In this work, we propose a new combinatorial branch-and-bound algorithm for the problem which relies on a novel bounding procedure capable of pruning a very large amount of nodes of the branch-and-bound tree. Extensive computational experiments on random and structured graphs, encompassing standard benchmarks used in the literature as well as recently introduced real-world large-scale graphs, show that our new algorithm outperforms the state-of-the-art by several orders of magnitude on many instances., This work is partially funded by the Spanish Ministry of Science, Innovation and Universities through the project COGDRIVE (grant DPI2017-86915-C3-3-R). The authors would also like to thank S. Hosseinian for sharing the source code of the algorithm CBQ and for his collaboration when comparing our algorithm with CBQ., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

Discrete-time systems sliding mode switching hyper plane design: A survey

  • Luis‐Delgado, José Darío
  • Al‐Hadithi, Basil Mohammed
  • Jiménez, Agustín
As regards to variable structure control with sliding mode (VSC-SM), it is knownthat designing sliding surface is a critical task because sliding surfaces mustguarantee that the steady state of the controlled system achieves some desiredperformance including global (or global asymptotic) stability. This problem hasbeen extensively analyzed for a wide class of systems: scalar, multivariable, lin-ear, nonlinear, time-variant, discrete-time system, etc. The main purpose of thispaper is to present a thorough survey about the main approaches related to thedesign of discrete-time switching surfaces applied to VSC-SM. Research workscovering the design of sliding surfaces for the aforementioned systems are con-sidered and some illustrative examples are also included to explain some of thedesign methodologies., This work has been funded by the Spanish Ministry of Science, Innovation and Universities through the (COGDRIVEproject: Artificial Intelligence Techniques and Assistance to Autonomous Navigation) (DPI2017-86915-C3-3-R)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

The fuzzy Kalman filter: Improving its implementation by reformulating uncertainty representation

  • Matía, Fernando
  • Jiménez, Víctor
  • Alvarado, Biel P.
  • Haber Guerra, Rodolfo E.
The fuzzy Kalman filter (FKF), introduced some years ago, is revisited. In the initial version, trapezoidal possibility distributions functions instead of gaussian probability distributions were proposed, and trapezius were modeled by four representative points. Nevertheless, and although the algorithm works properly, an implementation problem occurs when propagating uncertainty through a non-linear function in multi-variable systems, something that was solved by linearization. In this work we propose an alternative method to represent uncertainty, still using trapezoidal distributions, which avoids the previous inconvenience and eases the Kalman filter steps computation. We reformulate the FKF algorithm, presenting a new theoretical approach as well as validation tests in both simulation and a real mobile robot., This work has been funded by Spanish Ministry of Science, Innovation and Universities (Artificial Intelligence Techniques and Assistance to Autonomous Navigation, reference DPI 2017-86915-C3-3-R). It has also received funding from the RoboCity2030-DIH-CM Madrid Robotics Digital Innovation Hub “Robótica aplicada a la mejora de la calidad de vida de los ciudadanos, fase IV”; S2018/NMT-4331), funded by “Programas de Actividades I+D en la Comunidad de Madrid” and cofunded by Structural Funds of the EU., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

Motion Planning Approach Considering Localization Uncertainty

  • Artuñedo, Antonio
  • Villagrá, Jorge
  • Godoy, Jorge
  • Castillo-Sobrino, M. Dolores del
Localization plays an important role in autonomous driving since a high level of accuracy in vehicle localization is indispensable for a safe navigation. Most of the motion planning approaches in the literature assume negligible uncertainty in vehicle localization. However, the accuracy of localization systems can be low by design or even can drop depending on the environment in some cases. In these situations, the localization uncertainty can be taken into consideration in motion planning to increase the system reliability. Accordingly, this work presents two main contributions: (i) a probabilistic occupancy grid-based approach for localization uncertainty propagation, and (ii) a motion planning strategy that relies on such occupancy grid. Thus, the proposed motion planning solution for automated driving is able to generate safe human-like trajectories in real time while considering the localization uncertainty, ego-vehicle constrains and obstacles. In order to validate the proposed algorithms, several experiments have been conducted in a real environment., This work has been partially funded by the Spanish Ministry of Science, Innovation and Universities with National Project COGDRIVE (DPI2017-86915-C3-1-R), the Community of Madrid through SEGVAUTO 4.0-CM (S2018-EMT4362) Programme, and by the European Commission through the Projects PRYSTINE (ECSEL-783190-2) and SECREDAS (ECSEL-783119-2)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

A tour-guide robot: Moving towards interaction with humans

  • Alvarado Vásquez, Biel Piero E.
  • Matía, Fernando
The aim of this research project is to develop a smart social robot showing sufficient intelligence to work as atour-guide in different environments. In doing so, both a software and a hardware architecture are proposed,the different modules of which, such as a laser, cameras, platform, face, and voice, among others, controlthe different components of the robot. Those components are in turn used by other modules designed fornavigation and interaction. A sensor fusion for the purposes of localization is implemented by means of anExtended Kalman Filter, which is one of the navigation module components, together with the proposed fuzzycontrollers needed for path following. A fuzzy emotion system that controls the face and the voice modulesalso forms part of this architecture for assisting interaction. Finally, all the modules are controlled with acustomized programming language that is a mixture of C, Pascal, and JavaScript. The modules are optimizedfor immediate execution to achieve realistic human–machine interaction., The results in this paper report the research supported by the Spanish Ministry of Science, Innovation and Universities, Spain under DPI2017-86915-C3-3-R: Técnicas de Inteligencia Artificial y Ayuda a la Navegación Autónoma, and by Programas de Actividades I+D en la Comunidad de Madrid, cofunded with EU Structural Funds , through the EURoboCity2030-IV-CM project (Robótica aplicada a la mejora de la calidad de vida de los ciudadanos. fase IV; S2018/NMT-4331)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

VPS-SLAM: Visual Planar Semantic SLAM for Aerial Robotic Systems

  • Bavle, H.
  • De La Puente, P.
  • How, J. P.
  • Campoy, P.
Indoor environments have abundant presence of high-level semantic information which can provide a better understanding of the environment for robots to improve the uncertainty in their pose estimate. Although semantic information has proved to be useful, there are several challenges faced by the research community to accurately perceive, extract and utilize such semantic information from the environment. In order to address these challenges, in this paper we present a lightweight and real-time visual semantic SLAM framework running on board aerial robotic platforms. This novel method combines low-level visual/visual-inertial odometry (VO/VIO) along with geometrical information corresponding to planar surfaces extracted from detected semantic objects. Extracting the planar surfaces from selected semantic objects provides enhanced robustness and makes it possible to precisely improve the metric estimates rapidly, simultaneously generalizing to several object instances irrespective of their shape and size. Our graph-based approach can integrate several state of the art VO/VIO algorithms along with the state of the art object detectors in order to estimate the complete 6DoF pose of the robot while simultaneously creating a sparse semantic map of the environment. No prior knowledge of the objects is required, which is a significant advantage over other works. We test our approach on a standard RGB-D dataset comparing its performance with the state of the art SLAM algorithms. We also perform several challenging indoor experiments validating our approach in presence of distinct environmental conditions and furthermore test it on board an aerial robot., This work was supported by the MISTI-Spain for the financial support in the project entitled Drone Autonomy and the Spanish Ministry of Economy and Competitivity for its funding Project (Complex Coordinated Inspection and Security missions by UAVs in cooperation with UGV) under Grant RTI2018-100847-B-C21. The work of Paloma de la Puente was supported in part by the Spanish Ministry of Economics and Competitivity under Grant DPI2017-86915-C3-3-R COGDRIVE., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

A new combinatorial branch-and-bound algorithm for the Knapsack Problem with Conflicts

  • Coniglio, Stefano
  • Furini, Fabio
  • San Segundo, Pablo
We study the Knapsack Problem with Conflicts, a generalization of the Knapsack Problem in which a set of conflicts specifies pairs of items which cannot be simultaneously selected. In this work, we propose a novel combinatorial branch-and-bound algorithm for this problem based on an n-ary branching scheme. Our algorithm effectively combines different procedures for pruning the branch-and-bound nodes based on different relaxations of the Knapsack Problem with Conflicts. Its main elements of novelty are: (i) the adoption of the branching-and-pruned set branching scheme which, while extensively used in the maximum-clique literature, was never successfully employed for solving the Knapsack Problem with Conflicts; (ii) the adoption of the Multiple-Choice Knapsack Problem for the derivation of upper bounds used for pruning the branch-and-bound tree nodes; and (iii) the design of a new upper bound for the latter problem which can be computed very efficiently. Key to our algorithm is its high pruning potential and the low computational effort that it requires to process each branch-and-bound node. An extensive set of experiments carried out on the benchmark instances typically used in the literature shows that, for edge densities ranging from 0.1 to 0.9, our algorithm is faster by up to two orders of magnitude than the state-of-the-art method and by up to several orders of magnitude than a state-of-the-art mixed-integer linear programming solver., This work has been partially funded by the Spanish Ministry of Science, Innovation and Universities through the project COGDRIVE (DPI2017-86915-C3-3-R)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

A set of practical experiments to validate the fuzzy Kalman filter

  • Jiménez Bermejo, Víctor
  • Alvarado, Biel Piero
  • Matía, Fernando
The Fuzzy Kalman Filter (FKF) was recently reformulated, with a number of basic examples included in order to demonstrate its applicability. We now look ahead to its practical implementation, introducing deep analysis which includes very detailed simulations and complete real applications. This will allow us to not only validate the FKF but also to draw important conclusions which will help users in the adjustment of the fuzzy filter parameters and the choosing of possibilistic distributions., This paper was funded by the Spanish Ministry of Science, Innovation and Universities (Artificial Intelligence Techniques and Assistance to Autonomous Navigation, reference DPI 2017-86915-C3-3-R). It also received funding from the RoboCity2030-DIH-CM, Madrid Robotics Digital Innovation Hub, S2018/NMT-4331, funded by Programas de Actividades I+D en la Comunidad de Madrid and co-funded by Structural Funds of the EU., Peer reviewed