Skip to main content

INTERACCION, APRENDIZAJE Y COOPERACION ROBOT – HUMANO EN AREAS URBANAS

DPI2013-42458-P

•
Funding agency name Ministerio de Economía y Competitividad
Funding agency acronym MINECO
Program Programa Estatal de Fomento de la Investigación Científica y Técnica de Excelencia
Subprogram Subprograma Estatal de Generación de Conocimiento
Call Proyectos de I+D (Excelencia / Generación de Conocimiento)
Call year 2013
State Plan 2013-2016 Plan Estatal de Investigación Científica y Técnica y de Innovación
Management unit Secretaría de Estado de Educación, Formación Profesional y Universidades
Beneficiary centre UNIVERSITAT POLITECNICA DE CATALUNYA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 17
Encontrada(s) 1 página(s)

DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

Continuous real time POMCP to find-and-follow people by a humanoid service robot

  • Goldhoorn, Alex
  • Garrell, Anaís
  • Alquézar Mancho, Renato
  • Sanfeliu, Alberto
Trabajo presentado al 14th IEEE-RAS International Conference on Humanoid Robots: Humanoids 2014 "Humans and Robots Face-to-Face", celebrado en Madrid (España) del 18 al 20 de noviembre de 2014., This study describes and evaluates two new methods for finding and following people in urban settings using a humanoid service robot: the Continuous Real-time POMCP method, and its improved extension called Adaptive Highest Belief Continuous Real-time POMCP follower. They are able to run in real-time, in large continuous environments. These methods make use of the online search algorithm Partially Observable Monte-Carlo Planning (POMCP), which in contrast to other previous approaches, can plan under uncertainty on large state spaces. We compare our new methods with a heuristic person follower and demonstrate that they obtain better results by testing them extensively in both simulated and real-life experiments. More than two hours, over 3 km, of autonomous navigation during real-life experiments have been done with a mobile humanoid robot in urban environments., This work has been partially funded by the DPI2013-42458-P., Peer Reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

Efficient monocular pose estimation for complex 3D models

  • Rubio Romano, Antonio
  • Villamizar, Michael
  • Ferraz, Luis
  • Peñate-Sánchez, Adrián
  • Ramisa, Arnau
  • Simo-Serra, Edgar
  • Sanfeliu, Alberto
  • Moreno-Noguer, Francesc
Trabajo presentado al ICRA celebrado en Seattle (US) del 26 al 30 de mayo de 2015., We propose a robust and efficient method to estimate the pose of a camera with respect to complex 3D textured models of the environment that can potentially contain more than 100, 000 points. To tackle this problem we follow a top down approach where we combine high-level deep network classifiers with low level geometric approaches to come up with a solution that is fast, robust and accurate. Given an input image, we initially use a pre-trained deep network to compute a rough estimation of the camera pose. This initial estimate constrains the number of 3D model points that can be seen from the camera viewpoint. We then establish 3D-to-2D correspondences between these potentially visible points of the model and the 2D detected image features. Accurate pose estimation is finally obtained from the 2D-to-3D correspondences using a novel PnP algorithm that rejects outliers without the need to use a RANSAC strategy, and which is between 10 and 100 times faster than other methods that use it. Two real experimentsdealing with very large and complex 3D models demonstrate the effectiveness of the approach., This work has been partially funded by the Spanish Ministry of Economy and Competitiveness under projects ERANet Chistera project ViSen PCIN-2013-047, PAU+ DPI2011-27510 and ROBOT-INT-COOP DPI2013-42458-P, and by the EU project ARCAS FP7-ICT-2011-28761., Peer Reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

Modeling robot's world with minimal effort

  • Villamizar, Michael
  • Garrell, Anaís
  • Sanfeliu, Alberto
  • Sanfeliu, Alberto
  • Moreno-Noguer, Francesc
Trabajo presentado al ICRA celebrado en Seattle (US) del 26 al 30 de mayo de 2015., We propose an efficient Human Robot Interaction approach to efficiently model the appearance of all relevant objects in robot's environment. Given an input video stream recorded while the robot is navigating, the user just needs to annotate a very small number of frames to build specific classifiers for each of the objects of interest. At the core of the method, there are several random ferns classifiers that share the same features and are updated online. The resulting methodology is fast (runs at 8 fps), versatile (it can be applied to unconstrained scenarios), scalable (real experiments show we can model up to 30 different object classes), and minimizes the amount of human intervention by leveraging the uncertainty measures associated to each classifier. We thoroughly validate the approach on synthetic data and on real sequences acquired with a mobile platform in outdoor and challenging scenarios containing a multitude of different objects. We show that the human can, with minimal effort, provide the robot with a detailed model of the objects in the scene., Work partially supported by the Spanish Ministry of Science and Innovation under project DPI2013-42458-P, ERA-Net Chistera project ViSen PCIN-2013-047, and by the EU project ARCAS FP7-ICT-2011-28761., Peer Reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

Multimodal object recognition using random clustering trees

  • Villamizar, Michael
  • Garrell, Anaís
  • Sanfeliu, Alberto
  • Moreno-Noguer, Francesc
Trabajo presentado a la 7th Iberian Conference (IbPRIA) celebrada en Santiago de Compostela (España) del 17 al 19 de junio de 2015., In this paper, we present an object recognition approach that in addition allows to discover intra-class modalities exhibiting highcorrelated visual information. Unlike to more conventional approaches based on computing multiple specialized classifiers, the proposed approach combines a single classifier, Boosted Random Ferns (BRFs), with probabilistic Latent Semantic Analysis (pLSA) in order to recognize an object class and to find automatically the most prominent intra-class appearance modalities (clusters) through tree-structured visual words. The proposed approach has been validated in synthetic and real experiments where we show that the method is able to recognize objects with multiple appearances., Work partially supported by the Spanish ministry of Science and Innovation under project DPI2013-42458-P, ERA-Net Chistera project ViSen PCIN-2013-047, and by the EU project ARCAS FP7-ICT-2011-28761., Peer Reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

Multi-objective cost-to-go functions on robot navigation in dynamic environments

  • Ferrer, Gonzalo
  • Sanfeliu, Alberto
Trabajo presentado a la International Conference on Intelligent Robots and Systems, celebrada en Hamburgo (Alemania) del 28 de septiembre al 2 de octubre de 2015., In our previous work we introduced the Anticipative Kinodynamic Planning (AKP): a robot navigation algorithm in dynamic urban environments that seeks to minimize its disruption to nearby pedestrians. In the present paper, we maintain all the advantages of the AKP, and we overcome the previous limitations by presenting novel contributions to our approach. Firstly, we present a multi-objective cost function to consider different and independent criteria and a well-posed procedure to build a joint cost function in order to select the best path. Then, we improve the construction of the planner tree by introducing a cost-to-go function that will be shown to outperform a classical Euclidean distance approach. In order to achieve real time calculations, we have used a steering heuristic that dramatically speeds up the process. Plenty of simulations and real experiments have been carried out to demonstrate the success of the AKP., This work was supported by the Spanish Ministry of Science and Innovation project DPI2013-42458-P, Peer Reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

Real time people detection combining appearance and depth image spaces using boosted random ferns

  • Vaquero, Victor
  • Villamizar, Michael
  • Sanfeliu, Alberto
Trabajo presentado a la 2nd Iberian Robotics Conference (ROBOT-2015)., This paper presents a robust and real-time method for people detection in urban and crowed environments. Unlike other conventional methods which either focus on single features or compute multiple and independent classifiers specialized in a particular feature space, the proposed approach creates a synergic combination of appearance and depth cues in a unique classifier. The core of our method is a Boosted Random Ferns classifier that selects automatically the most discriminative local binary features for both the appearance and depth image spaces. Based on this classifier, a fast and robust people detector which maintains high detection rates in spite of environmental changes is created. The proposed method has been validated in a challenging RGB-D database of people in urban scenarios and has shown that outperforms state-of-the-art approaches in spite of the difficult environment conditions. As a result, this method is of special interest for real-time robotic applications where people detection is a key matter, such as human-robot interaction or safe navigation of mobile robots for example., This work has been partially funded by the EU project CargoANTs FP7-SST-2013-605598 and the Spanish CICYT project DPI2013-42458-P., Peer Reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

Low cost, robust and real time system for detecting and tracking moving objects to automate cargo handling in port terminals

  • Vaquero, Victor
  • Repiso, Ely
  • Sanfeliu, Alberto
  • Vissers, John
  • Kwakkernaat, Maurice
Trabajo presentado a la 2nd Iberian Robotics Conference (ROBOT-2015)., The presented paper addresses the problem of detecting and tracking moving objects for autonomous cargo handling in port terminals using a perception system which input data is a single layer laser scanner. A computationally low cost and robust Detection and Tracking Moving Objects (DATMO) algorithm is presented to be used in autonomous guided vehicles and autonomous trucks for efficient transportation of cargo in ports. The method first detects moving objects and then tracks them, taking into account that in port terminals the structure of the environment is formed by containers and that the moving objects can be trucks, AGV, cars, straddle carriers and people among others. Two approaches of the DATMO system have been tested, the first one is oriented to detect moving obstacles and focused on tracking and filtering those detections; and the second one is focused on keepking targets when no detections are provided. The system has been evaluated with real data obtained in the CTT port terminal in Hengelo, the Netherlands. Both methods have been tested in the dataset with good results in tracking moving objects., This work has been partially funded by the EU project CargoANTs FP7-SST-2013-605598 and the Spanish CICYT project DPI2013-42458-P., Peer Reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

Distance-based kernels for dynamical movement primitives

  • Escudero-Rodrigo, Diego
  • Alquézar Mancho, Renato
Trabajo presentado a la 18th Catalan Conference on Artificial Intelligence (CCIA-2015)., In the Anchoring Problem actions and objects must be anchored to symbols; and movement primitives as DMPs seems a good option to describe actions. In the bottom-up approach to anchoring, the recognition of an action is done applying learning techniques as clustering. Although most work done about movement recognition with DMPs is focus on weights, we propose to use the shape-attractor function as feature vector. As several DMPs formulations exist, we have analyzed the two most known to check if using the shape-attractor instead of weights is feasible for both formulations. In addition, we propose to use distance-based kernels, as RBF and TrE, to classify DMPs in some predefined actions. Our experiments based on an existing dataset and using 1-NN and SVM techniques confirm that shape-attractor function is a better choice for movement recognition with DMPs., This work was partially funded by Spanish research project DPI2013-42458-P., Peer Reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

Learning the hidden human knowledge of UAV pilots when navigating in a cluttered environament for improving Path Plannig

  • Alzugaray, Ignacio
  • Sanfeliu, Alberto
  • Sanfeliu, Alberto
Trabajo presentado a la IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), celebrada en Daejeon (Korea) del 9 al 14 de octubre de 2016., We propose in this work a new model of how the hidden human knowledge (HHK) of UAV pilots can be incorporated in the UAVs path planning generation. We intuitively know that human's pilots barely manage or even attempt to drive the UAV through a path that is optimal attending to some criteria as an optimal planner would suggest. Although human pilots might get close but not reach the optimal path proposed by some planner that optimizes over time or distance, the final effect of this differentiation could be not only surprisingly better, but also desirable. In the best scenario for optimality, the path that human pilots generate would deviate from the optimal path as much as the hidden knowledge that its perceives is injected into the path. The aim of our work is to use real human pilot paths to learn the hidden knowledge using repulsion fields and to incorporate this knowledge afterwards in the environment obstacles as cause of the deviation from optimality. We present a strategy of learning this knowledge based on attractor and repulsors, the learning method and a modified RRT* that can use this knowledge for path planning. Finally we do real-life tests and we compare the resulting paths with and without this knowledge., This work was supported by the Spanish Ministry of Science and Innovation, project Rob-Int-Coop DPI2013-42458-P and AEROARMS European project H2020-ICT-2014-1-644271., Peer Reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

PL-SLAM: Real-time monocular visual SLAM with points and lines

  • Pumarola, Albert
  • Vakhitov, Alexander
  • Agudo Martínez, Antonio
  • Sanfeliu, Alberto
  • Moreno-Noguer, Francesc
Trabajo presentado a la IEEE International Conference on Robotics and Automation (ICRA), celebrada en Singapur del 29 de mayo al 3 de junio de 2017., Low textured scenes are well known to be one of the main Achilles heels of geometric computer vision algorithms relying on point correspondences, and in particular for visual SLAM. Yet, there are many environments in which, despite being low textured, one can still reliably estimate line-based geometric primitives, for instance in city and indoor scenes, or in the so-called ``Manhattan worlds'', where structured edges are predominant. In this paper we propose a solution to handle these situations. Specifically, we build upon ORB-SLAM, presumably the current state-of-the-art solution both in terms of accuracy as efficiency, and extend its formulation to simultaneously handle both point and line correspondences. We propose a solution that can even work when most of the points are vanished out from the input images, and, interestingly it can be initialized from solely the detection of line correspondences in three consecutive frames. We thoroughly evaluate our approach and the new initialization strategy on the TUM RGB-D benchmark and demonstrate that the use of lines does not only improve the performance of the original ORB-SLAM solution in poorly textured frames, but also systematically improves it in sequence frames combining points and lines, without compromising the efficiency., This work has been partially supported by the EU project AEROARMS H2020-ICT-2014-1-644271, by the MINECO projects RobInstruct TIN2014-58178-R and Rob-Int-Coop DPI2013-42458-P, by the ERA-Net Chistera project IDRESS PCIN-2015-147 and by the Russian MES grant RFMEFI61516X0003., Peer Reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

On-line adaptive side-by-side human robot companion in dynamic urban environments

  • Repiso, Ely
  • Ferrer, Gonzalo
  • Sanfeliu, Alberto
Trabajo presentado a la IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), celebrada en Vancouver (Canada) del 24 al 28 de septiembre de 2017., This paper presents an adaptive side-by-side human-robot companion approach for navigation in urban dynamic environments, based on the anticipative kinodynamic planning. The adaptive means that the robot is capable of adjusting its motion to the behavior of the person being accompanied. Our main objective is to optimize in real time the path performed by the pair human-robot, by modifying dynamically the angle and distance between both throughout different locations of the path. We have defined a new cost function for finding the best planned path that takes into account the cost of the geometrical configuration between the human and the robot. Moreover, we have modified the Extended Social Force Model (SFM) to include the required forces to maintain the angle and distance between the robot and human while the human-robot pair is moving towards the shared goal. The method has been validated throughout a large set of simulations and real-live experiments., Work supported by the Spanish Ministry of Science and Innovation under project ROBOT-INT-COOP(DPI2013-42458-P)., Peer Reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

Planar PØP: Feature-less pose estimation with applications in UAV localization

  • Amor-Martinez, Adrian
  • Santamaria-Navarro, Àngel
  • Herrero, Fernando
  • Ruiz Moreno, Alberto
  • Sanfeliu, Alberto
Trabajo presentado al IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), celebrado en Lausanne (Suiza) del 23 al 27 de octubre de 2016., We present a featureless pose estimation method that, in contrast to current Perspective-n-Point (PnP) approaches, it does not require n point correspondences to obtain the camera pose, allowing for pose estimation from natural shapes that do not necessarily have distinguished features like corners or intersecting edges. Instead of using n correspondences (e.g. extracted with a feature detector) we will use the raw polygonal representation of the observed shape and directly estimate the pose in the pose-space of the camera. This method compared with a general PnP method, does not require n point correspondences neither a priori knowledge of the object model (except the scale), which is registered with a picture taken from a known robot pose. Moreover, we achieve higher precision because all the information of the shape contour is used to minimize the area between the projected and the observed shape contours. To emphasize the non-use of n point correspondences between the projected template and observed contour shape, we call the method Planar PØP. The method is shown both in simulation and in a real application consisting on a UAV localization where comparisons with a precise ground-truth are provided., This work has been partially funded by the AEROARMS EU project H2020-ICT-2014-1-644271, the CICYT project DPI2013-42458-P, and by Spanish MINECO and EU FEDER grant TIN2015-66972-C5-3-R., Peer Reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

Study of the anchoring problem in generalist robots based on ROSPlan

  • Escudero-Rodrigo, Diego
  • Alquézar Mancho, Renato
Trabajo presentado a la 19th International Conference of the Catalan Association for Artificial Intelligence (CCIA), celebrada en Barcelona (España) del 19 al 21 de octubre de 2016., In real life environments where robots must deal with complex situations and humans, generalist robots that adapt to novel situations are needed. They are composed by two sub-systems: perception/actuation and knowledge representation, and they need that symbols in the high-level area are coupled to objects and actions of the low-level area. This is the so-called Anchoring Problem. In this paper we present the system we are using to study this problem. It is based on ROSPlan, a framework that provides a generic method for task planning in a ROS system. The high-level area is composed by a planner that uses PDDL files and a knowledge representation system, while the low-level area is defined as a set of robot services exported using ROS actions, services and topics. We plan to contribute to this problem by applying human-robot interaction and learning techniques, and our main objectives are: (1) link an existing symbol with a learned action by interaction, and (2) automated code generation of ad-hoc ROS nodes that connect symbols to specific perceptions/actions., This work was partially funded by Spanish research project DPI2013-42458-P, Peer Reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

Solutions to reduce CO2 emissions for autonomous robotics

  • Grau Saldes, Antoni
  • Bolea, Yolanda
  • Sanfeliu, Alberto
Trabajo presentado a la 18th International Conference on Computer and Automation Technology (ICCAT), celebrada en Zurich (Suiza) del 15 al 16 de septiembre de 2016., Sewer inspections require many people to work in risky and unhealthy conditions. A European ECHORD++ project introduces a robotic solution in this process aiming to reduce the labour risks, improving the precision of sewer inspections and optimizing sewer cleaning resources of cities. This system should be able to determine the state of the sewer in order to identify sewer segments where its functionality has been reduced either by sediments or by structural defects. Other functionalities required are sewer monitoring and water, air and sediment sampling. To well carry out these tasks, some general functions are required like remote operation, video and images capture, scanning and map building, among others. The ECHORD++ innovative proposed solution is carried out in Barcelona as pilot city. The current need of the City of Barcelona is to mechanize sewer inspections in order to objectify sewer inspections and optimize sewer cleaning expenses of the city. The sewer network of Barcelona is 1,532 km long, from which approximately 50% is accessible, which means that the pipe is at least 1.5 m high and workers are allowed to go inside it. In order to determine the state of the network, visual inspections are done with different frequencies depending on the slope and other characteristics of the sewer. Workers walk all along the pipe, in some sections even four times a year, and decide where it is necessary to clean. Moreover, sewers are classified as confined spaces which require special health and safety measures, in addition to other risks like slippery sections, obstacles or biological risks from the eventual contact with wastewater. These features made the process of sewer inspection a risky and expensive process that requires improvements urgently. Sewer inspection is a service included in the public management of the sewers of Barcelona. Nowadays, sewer inspections are done by people performing visual inspections and collecting information about the state of the sewage like sediment level and type, pipe obstructions, etc. In this paper the technological proposed solution (a semi-autonomous green robotic solution) is explained. The requirements for the new technology are given by the inherent sewer characteristics, that is, different ranges of pipe sizes, possible high concentration of, not explosive, but toxic gases as hydrogen sulphide, slippery areas, obstacles, atmosphere with 100% humidity, water temperature at 16 °C, and no telecommunication coverage in the sewer. The ECHORD++ project seeks to facilitate real-time decision making, innovation that makes inspection devices more autonomous, to have more degrees of freedom to move around the network, and the possibility to intensify the checking of a zone where impairment has been detected. This technological solution will fulfill environmental legislation and policies., This research was funded by Spanish Science ministry project CICYT DPI2013-42458-P (Robot-Int-Coop)., Peer Reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

Collaborative-AI: Social robots accompanying and approaching people

  • Sanfeliu, Alberto
  • Repiso, Ely
  • Garrell, Anaís
Trabajo presentado en el International First International Workshop on New Foundations for Human-Centered AI (NeHuAI), celebrado en Santiago de Compostela (España), el 4 de septiembre de 2020, Collaborative AI to approach or to accompany people using social robots will be a fundamental robotics field in the near future. If we desire to share and to collaborate with social robots during the development of our daily task, social robots should be able to develop Collaborative AI task, such us accompanying or approaching people. In this article, we will present the robot-people accompaniment and approaching missions through the four levels of abstractions of Collaborative AI systems and describe the main Collaborative AI functionalities that are needed for these missions. We will also show the system that we have developed for accompany one or two pedestrians and approaching on person by a robot in an urban space, Work supported by the Spanish Ministry of Science project ROCOTRANSP (PID2019-106702RB-C21-RAEI/FEDER EU) by Ministerio de Ciencia e Innovacion , the EU AI4EU project (H2020-ICT-2018-2-825619), by the Spanish State Research Agency through the María de Maeztu Seal of Excellence to IRI (MDM-2016-0656). Ely Repiso is suported by the FPI-grant, BES-2014-067713.
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Efficient monocular pose estimation for complex 3D models

  • Rubio Romano, Antonio
  • Villamizar Vergel, Michael Alejandro
  • Ferraz Colomina, Luis
  • Peñate Sánchez, Adrián
  • Ramisa Ayats, Arnau
  • Simó Serra, Edgar
  • Sanfeliu Cortés, Alberto|||0000-0003-3868-9678
  • Moreno-Noguer, Francesc
We propose a robust and efficient method to estimate the pose of a camera with respect to complex 3D textured models of the environment that can potentially contain more than 100, 000 points. To tackle this problem we follow a top down approach where we combine high-level deep network classifiers with low level geometric approaches to come up with a solution that is fast, robust and accurate. Given an input image, we initially use a pre-trained deep network to compute a rough estimation of the camera pose. This initial estimate constrains the number of 3D model points that can be seen from the camera viewpoint. We then establish 3D-to-2D correspondences between these potentially visible points of the model and the 2D detected image features. Accurate pose estimation is finally obtained from the 2D-to-3D correspondences using a novel PnP algorithm that rejects outliers without the need to use a RANSAC strategy, and which is between 10 and 100 times faster than other methods that use it. Two real experimentsdealing with very large and complex 3D models demonstrate the effectiveness of the approach., Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Efficient monocular pose estimation for complex 3D models

  • Rubio Romano, Antonio
  • Villamizar Vergel, Michael Alejandro
  • Ferraz Colomina, Luis
  • Peñate Sánchez, Adrián
  • Ramisa Ayats, Arnau
  • Simó Serra, Edgar
  • Sanfeliu Cortés, Alberto
  • Moreno-Noguer, Francesc
We propose a robust and efficient method to estimate the pose of a camera with respect to complex 3D textured models of the environment that can potentially contain more than 100, 000 points. To tackle this problem we follow a top down approach where we combine high-level deep network classifiers with low level geometric approaches to come up with a solution that is fast, robust and accurate. Given an input image, we initially use a pre-trained deep network to compute a rough estimation of the camera pose. This initial estimate constrains the number of 3D model points that can be seen from the camera viewpoint. We then establish 3D-to-2D correspondences between these potentially visible points of the model and the 2D detected image features. Accurate pose estimation is finally obtained from the 2D-to-3D correspondences using a novel PnP algorithm that rejects outliers without the need to use a RANSAC strategy, and which is between 10 and 100 times faster than other methods that use it. Two real experimentsdealing with very large and complex 3D models demonstrate the effectiveness of the approach., Peer Reviewed, Postprint (author's final draft)