In this paper we present a new real-time hierarchical (topological/metric) Visual SLAM system foc... more In this paper we present a new real-time hierarchical (topological/metric) Visual SLAM system focusing on the localization of a vehicle in large-scale outdoor urban environments. It is exclusively based on the visual information provided by a cheap wide-angle stereo camera. Our approach divides the whole map into local sub-maps identified by the so-called fingerprints (vehicle poses). At the sub-map level (low level SLAM), 3D sequential mapping of natural landmarks and the robot location/orientation are obtained using a top-down Bayesian method to model the dynamic behavior. A higher topological level (high level SLAM) based on fingerprints has been added to reduce the global accumulated drift, keeping real-time constraints. Using this hierarchical strategy, we keep the local consistency of the metric submaps, by mean of the EKF, and global consistency by using the topological map and the MultiLevel Relaxation (MLR) algorithm. Some experimental results for different large-scale outdoor environments are presented, showing an almost constant processing time.
2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2007
... David Schleicher, Luis M. Bergasa, Member, IEEE, Rafael Barea, Elena López, Manuel Ocaña, Mem... more ... David Schleicher, Luis M. Bergasa, Member, IEEE, Rafael Barea, Elena López, Manuel Ocaña, Member, IEEE, Jesús Nuevo ... which will be explained later, it is needed to add two more variables to the camera state vector v X : the linear and angular speed: ( )T rob rob rob rob v v ...
This paper presents a complete vision sensor onboard a moving vehicle which collects the traffic ... more This paper presents a complete vision sensor onboard a moving vehicle which collects the traffic data in its local area in daytime conditions. The sensor comprises a rear looking and a forward looking camera. Thus, a representative description of the traffic conditions in the local area of the host vehicle can be computed. The proposed sensor detects the number of vehicles (traffic load), their relative positions and their relative velocities in a four-stage process: lane detection, candidates selection, vehicles classification and tracking. Absolute velocities (average road speed) and global positioning are obtained after combining the outputs provided by the vision sensor with the data supplied by the CAN Bus and a GPS sensor. The presented experiments are promising in terms of detection performance and accuracy in order to be validated for applications in the context of the automotive industry.
The framework of this paper is robot localization inside buildings by means of wireless localizat... more The framework of this paper is robot localization inside buildings by means of wireless localization systems. Such kind of systems make use of the Wireless Fidelity (WiFi) signal strength sensors which are becoming more and more useful in the localization stage of several robotic platforms. Robot localization is usually made up of two phases: training and estimation stages. In the former, WiFi signal strength of all visible Access Points (APs) are collected and stored in a database or WiFi map. In the latter, the signal strengths received from all APs at a certain position are compared with the WiFi map to estimate the robot location. Hence, WiFi localization systems exploit the well-known path loss propagation model due to large-scale variations of WiFi signal to determine how closer the robot is to a certain AP. Unfortunately, there is another kind of signal variations called small-scale variations that have to be considered. They appear when robots move under the wavelength λ. In consequence, a chaotic noise is added to the signal strength measure yielding a lot of uncertainty that should be handled by the localization model. While lateral and orientation errors in the robot positioning stage are well studied and they remain under control thanks to the use of robust low-level controllers, more studies are needed when dealing with small-scale variations. Moreover, if the robot can not use a robust low-level controller because, for example, the environment is not organized in perpendicular corridors, then lateral and orientation errors can be significantly increased yielding a bad global localization and navigation performance. The main goal of this work is to strengthen the localization stage of our previous WiFi Partially Observable Markov Decision Process (POMDP) Navigation System with the aim of dealing effectively with small-scale variations. In addition, looking for the applicability of our system to a wider variety of environments, we relax the necessity of having a robust low-level controller. To do that, this paper proposes the use of a Soft Computing based system to tackle with the uncertainty related to both the small-scale variations and the lack of a robust low-level controller. The proposed system is actually implemented in the form of a Fuzzy Rule-based System and it has been evaluated in two real test-beds and robotic platforms. Experimental results show how our system is easily adaptable to new environments where classical localization techniques can not be applied since the AP physical location is unknown.
The paper describes a robotic application in which some fuzzy techniques have been used to analyz... more The paper describes a robotic application in which some fuzzy techniques have been used to analyze motion problems in a mobile robot. The robot is equipped with ultrasound sensors used for obstacle detection, but, in some cases, small obstacles are out of the range of the sensors and can be dragged by the robot without being detected. By peer description of the system dynamics the effect of the external obstacle on the robot motion variables can be stablished by means of linguistic rules, making the use of fuzzy techniques convinient and feasible. Using other variables such as measured velocity, undershoots of that velocity, or the derivative of the battery voltage, a fuzzy system is able to diagnose on robot motion problems.
The framework of this paper is the robotics navigation inside buildings using WiFi signal strengt... more The framework of this paper is the robotics navigation inside buildings using WiFi signal strength measure. In most cases this navigation is achieved using a Partially Observable Markov Decission Process (POMDP). In the localization phase of this process the WiFi signal strength is used as observation. The localization system works in two stages: map construction and localization stage. In this paper we compare three different methods for obtaining the WiFi map in the construction stage. The methods have been tested in a real environment using two commercial robotic platforms. Some experimental results and the conclusions are presented.
The framework of this paper is the robotics navigation inside buildings using WiFi signal strengt... more The framework of this paper is the robotics navigation inside buildings using WiFi signal strength measure. This navigation is achieved using a Partially Observable Markov Decission Process (POMDP). In the localization phase we used WiFi signal strength and Ultrasound measures as observations. The localization system works in two stages: map construction and localization stage. The map construction stage usually requires a great effort, therefore in this paper we address the problem of minimizing this calibration effort using an automatic training method. We describe the method based on Simultaneous Localization And Mapping (SLAM) techniques and in a robust local navigation task. This automatic method is compared with a manual method to obtain a deterministic map. Also we demonstrate that using this one in a on-line training stage the system is able to adapt the WiFi map to the variations of the WiFi signal measure. Additionally, we analyze the optimal parameters for this automatic training system. The system has been tested in a real environment using two commercial robotic platforms. Some experimental results and the conclusions are presented.
The goal of this paper is to solve the problem of dynamic obstacle avoidance for a mobile platfor... more The goal of this paper is to solve the problem of dynamic obstacle avoidance for a mobile platform by using the stochastic optimal control framework to compute paths that are optimal in terms of safety and energy efficiency under constraints. We propose a three-dimensional extension of the Bayesian Occupancy Filter (BOF) (Coué et al. Int. J. Rob. Res. 2006, 25, 19-30) to deal with the noise in the sensor data, improving the perception stage. We reduce the computational cost of the perception stage by estimating the velocity of each obstacle using optical flow tracking and blob filtering. While several obstacle avoidance systems have been presented in the literature addressing safety and optimality of the robot motion separately, we have applied the approximate inference framework to this problem to combine multiple goals, constraints and priors in a structured way. It is important to remark that the problem involves obstacles that can be moving, therefore classical techniques based on reactive control are not optimal from the point of view of energy consumption. Some experimental results, including comparisons against classical algorithms that highlight the advantages are presented.
This paper presents an analytical study of the depth estimation error of a stereo vision-based pe... more This paper presents an analytical study of the depth estimation error of a stereo vision-based pedestrian detection sensor for automotive applications such as pedestrian collision avoidance and/or mitigation. The sensor comprises two synchronized and calibrated low-cost cameras. Pedestrians are detected by combining a 3D clustering method with Support Vector Machine-based (SVM) classification. The influence of the sensor parameters in the stereo quantization errors is analyzed in detail providing a point of reference for choosing the sensor setup according to the application requirements. The sensor is then validated in real experiments. Collision avoidance maneuvers by steering are carried out by manual driving. A real time kinematic differential global positioning system (RTK-DGPS) is used to provide ground truth data corresponding to both the pedestrian and the host vehicle locations. The performed field test provided encouraging results and proved the validity of the proposed sensor for being used in the automotive sector towards applications such as autonomous pedestrian collision avoidance.
2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2006
This paper presents a new method for real-time ego-motion calculation applied to the location/ori... more This paper presents a new method for real-time ego-motion calculation applied to the location/orientation of a cheap wide-angle stereo camera in a 3D environment. To achieve that, the goal is to solve the Simultaneous Localization and Mapping (SLAM) problem. Our approach consists in the 3D sequential mapping of natural land-marks by means of a stereo camera, which also provides means to obtain the camera location/orientation. The dynamic behavior is modeled using a top-down Bayesian method. The results show a comparison between our system and a monocular visual SLAM system using a hand-waved camera. Several improvements related to no priori environment knowledge requirements, lower processing time (real-time constrained) and higher robustness is presented.
The framework of this paper is robot localization inside buildings using WiFi signal strength mea... more The framework of this paper is robot localization inside buildings using WiFi signal strength measure. This localization is usually made up of two phases: training and estimation stages. In the former the WiFi signal strength of all visible Access Points (APs) are collected and stored in a database or Wifi map, while in the latter the signal strengths received from
In this paper we present a new real-time hierarchical (topological/metric) Visual SLAM system foc... more In this paper we present a new real-time hierarchical (topological/metric) Visual SLAM system focusing on the localization of a vehicle in large-scale outdoor urban environments. It is exclusively based on the visual information provided by both a low-cost wide-angle stereo camera and a low-cost GPS. Our approach divides the whole map into local sub-maps identified by the so-called fingerprint (reference poses). At the sub-map level (Low Level SLAM), 3D sequential mapping of natural landmarks and the vehicle location/orientation are obtained using a top-down Bayesian method to model the dynamic behavior. A higher topological level (High Level SLAM) based on references poses has been added to reduce the global accumulated drift, keeping real-time constraints. Using this hierarchical strategy, we keep local consistency of the metric sub-maps, by mean of the EKF, and global consistency by using the topological map and the MultiLevel Relaxation (MLR) algorithm. GPS measurements are integrated at both levels, improving global estimation. Some experimental results for different large-scale urban environments are presented, showing an almost constant processing time.
This paper describes a monocular vision-based Adaptive Cruise Control (ACC) System in the framewo... more This paper describes a monocular vision-based Adaptive Cruise Control (ACC) System in the framework of Intelligent Transportation Systems (ITS) technologies. The challenge is to use a single camera as input, in order to achieve a low cost final system that meets the requirements needed to undertake serial production.
This paper presents a new method for real-time environments. One of the main milestones is to ach... more This paper presents a new method for real-time environments. One of the main milestones is to achieve large SLAM calculation applied to autonomous robot navigation in closing loops in robot paths running in real-time. large-scale environments without restrictions. It is exclusively Several approaches can be found to solve the related issues based on the visual information provided by a cheap wide-angle by using metric methods, topological methods or hybrid ones. stereo camera. Our approach divide the global map into local One example of the last ones is described in [5]. This solution sub-maps identified by the so-called SIFT fingerprint. At the tries to build a topological map composed by several simple sub-map level (low level SLAM), 3D sequential mapping of metric maps. After that, as long as the robot explores new natural land-marks and the robot location/orientation are
2009 IEEE International Conference on Robotics and Automation, 2009
In this paper we present a new real-time hierarchical (topological/metric) Visual SLAM system foc... more In this paper we present a new real-time hierarchical (topological/metric) Visual SLAM system focusing on the localization of a vehicle in large-scale outdoor urban environments. It is exclusively based on the visual information provided by both a low-cost wide-angle stereo camera and a low-cost GPS. Our approach divides the whole map into local sub-maps identified by the so-called fingerprint (reference poses). At the sub-map level (Low Level SLAM), 3D sequential mapping of natural landmarks and the vehicle location/orientation are obtained using a top-down Bayesian method to model the dynamic behavior. A higher topological level (High Level SLAM) based on references poses has been added to reduce the global accumulated drift, keeping real-time constraints. Using this hierarchical strategy, we keep local consistency of the metric sub-maps, by mean of the EKF, and global consistency by using the topological map and the MultiLevel Relaxation (MLR) algorithm. GPS measurements are integrated at both levels, improving global estimation. Some experimental results for different large-scale urban environments are presented, showing an almost constant processing time.
In this paper we present a new real-time hierarchical (topological/metric) Visual SLAM system foc... more In this paper we present a new real-time hierarchical (topological/metric) Visual SLAM system focusing on the localization of a vehicle in large-scale outdoor urban environments. It is exclusively based on the visual information provided by a cheap wide-angle stereo camera. Our approach divides the whole map into local sub-maps identified by the so-called fingerprints (vehicle poses). At the sub-map level (low level SLAM), 3D sequential mapping of natural landmarks and the robot location/orientation are obtained using a top-down Bayesian method to model the dynamic behavior. A higher topological level (high level SLAM) based on fingerprints has been added to reduce the global accumulated drift, keeping real-time constraints. Using this hierarchical strategy, we keep the local consistency of the metric submaps, by mean of the EKF, and global consistency by using the topological map and the MultiLevel Relaxation (MLR) algorithm. Some experimental results for different large-scale outdoor environments are presented, showing an almost constant processing time.
2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2007
... David Schleicher, Luis M. Bergasa, Member, IEEE, Rafael Barea, Elena López, Manuel Ocaña, Mem... more ... David Schleicher, Luis M. Bergasa, Member, IEEE, Rafael Barea, Elena López, Manuel Ocaña, Member, IEEE, Jesús Nuevo ... which will be explained later, it is needed to add two more variables to the camera state vector v X : the linear and angular speed: ( )T rob rob rob rob v v ...
This paper presents a complete vision sensor onboard a moving vehicle which collects the traffic ... more This paper presents a complete vision sensor onboard a moving vehicle which collects the traffic data in its local area in daytime conditions. The sensor comprises a rear looking and a forward looking camera. Thus, a representative description of the traffic conditions in the local area of the host vehicle can be computed. The proposed sensor detects the number of vehicles (traffic load), their relative positions and their relative velocities in a four-stage process: lane detection, candidates selection, vehicles classification and tracking. Absolute velocities (average road speed) and global positioning are obtained after combining the outputs provided by the vision sensor with the data supplied by the CAN Bus and a GPS sensor. The presented experiments are promising in terms of detection performance and accuracy in order to be validated for applications in the context of the automotive industry.
The framework of this paper is robot localization inside buildings by means of wireless localizat... more The framework of this paper is robot localization inside buildings by means of wireless localization systems. Such kind of systems make use of the Wireless Fidelity (WiFi) signal strength sensors which are becoming more and more useful in the localization stage of several robotic platforms. Robot localization is usually made up of two phases: training and estimation stages. In the former, WiFi signal strength of all visible Access Points (APs) are collected and stored in a database or WiFi map. In the latter, the signal strengths received from all APs at a certain position are compared with the WiFi map to estimate the robot location. Hence, WiFi localization systems exploit the well-known path loss propagation model due to large-scale variations of WiFi signal to determine how closer the robot is to a certain AP. Unfortunately, there is another kind of signal variations called small-scale variations that have to be considered. They appear when robots move under the wavelength λ. In consequence, a chaotic noise is added to the signal strength measure yielding a lot of uncertainty that should be handled by the localization model. While lateral and orientation errors in the robot positioning stage are well studied and they remain under control thanks to the use of robust low-level controllers, more studies are needed when dealing with small-scale variations. Moreover, if the robot can not use a robust low-level controller because, for example, the environment is not organized in perpendicular corridors, then lateral and orientation errors can be significantly increased yielding a bad global localization and navigation performance. The main goal of this work is to strengthen the localization stage of our previous WiFi Partially Observable Markov Decision Process (POMDP) Navigation System with the aim of dealing effectively with small-scale variations. In addition, looking for the applicability of our system to a wider variety of environments, we relax the necessity of having a robust low-level controller. To do that, this paper proposes the use of a Soft Computing based system to tackle with the uncertainty related to both the small-scale variations and the lack of a robust low-level controller. The proposed system is actually implemented in the form of a Fuzzy Rule-based System and it has been evaluated in two real test-beds and robotic platforms. Experimental results show how our system is easily adaptable to new environments where classical localization techniques can not be applied since the AP physical location is unknown.
The paper describes a robotic application in which some fuzzy techniques have been used to analyz... more The paper describes a robotic application in which some fuzzy techniques have been used to analyze motion problems in a mobile robot. The robot is equipped with ultrasound sensors used for obstacle detection, but, in some cases, small obstacles are out of the range of the sensors and can be dragged by the robot without being detected. By peer description of the system dynamics the effect of the external obstacle on the robot motion variables can be stablished by means of linguistic rules, making the use of fuzzy techniques convinient and feasible. Using other variables such as measured velocity, undershoots of that velocity, or the derivative of the battery voltage, a fuzzy system is able to diagnose on robot motion problems.
The framework of this paper is the robotics navigation inside buildings using WiFi signal strengt... more The framework of this paper is the robotics navigation inside buildings using WiFi signal strength measure. In most cases this navigation is achieved using a Partially Observable Markov Decission Process (POMDP). In the localization phase of this process the WiFi signal strength is used as observation. The localization system works in two stages: map construction and localization stage. In this paper we compare three different methods for obtaining the WiFi map in the construction stage. The methods have been tested in a real environment using two commercial robotic platforms. Some experimental results and the conclusions are presented.
The framework of this paper is the robotics navigation inside buildings using WiFi signal strengt... more The framework of this paper is the robotics navigation inside buildings using WiFi signal strength measure. This navigation is achieved using a Partially Observable Markov Decission Process (POMDP). In the localization phase we used WiFi signal strength and Ultrasound measures as observations. The localization system works in two stages: map construction and localization stage. The map construction stage usually requires a great effort, therefore in this paper we address the problem of minimizing this calibration effort using an automatic training method. We describe the method based on Simultaneous Localization And Mapping (SLAM) techniques and in a robust local navigation task. This automatic method is compared with a manual method to obtain a deterministic map. Also we demonstrate that using this one in a on-line training stage the system is able to adapt the WiFi map to the variations of the WiFi signal measure. Additionally, we analyze the optimal parameters for this automatic training system. The system has been tested in a real environment using two commercial robotic platforms. Some experimental results and the conclusions are presented.
The goal of this paper is to solve the problem of dynamic obstacle avoidance for a mobile platfor... more The goal of this paper is to solve the problem of dynamic obstacle avoidance for a mobile platform by using the stochastic optimal control framework to compute paths that are optimal in terms of safety and energy efficiency under constraints. We propose a three-dimensional extension of the Bayesian Occupancy Filter (BOF) (Coué et al. Int. J. Rob. Res. 2006, 25, 19-30) to deal with the noise in the sensor data, improving the perception stage. We reduce the computational cost of the perception stage by estimating the velocity of each obstacle using optical flow tracking and blob filtering. While several obstacle avoidance systems have been presented in the literature addressing safety and optimality of the robot motion separately, we have applied the approximate inference framework to this problem to combine multiple goals, constraints and priors in a structured way. It is important to remark that the problem involves obstacles that can be moving, therefore classical techniques based on reactive control are not optimal from the point of view of energy consumption. Some experimental results, including comparisons against classical algorithms that highlight the advantages are presented.
This paper presents an analytical study of the depth estimation error of a stereo vision-based pe... more This paper presents an analytical study of the depth estimation error of a stereo vision-based pedestrian detection sensor for automotive applications such as pedestrian collision avoidance and/or mitigation. The sensor comprises two synchronized and calibrated low-cost cameras. Pedestrians are detected by combining a 3D clustering method with Support Vector Machine-based (SVM) classification. The influence of the sensor parameters in the stereo quantization errors is analyzed in detail providing a point of reference for choosing the sensor setup according to the application requirements. The sensor is then validated in real experiments. Collision avoidance maneuvers by steering are carried out by manual driving. A real time kinematic differential global positioning system (RTK-DGPS) is used to provide ground truth data corresponding to both the pedestrian and the host vehicle locations. The performed field test provided encouraging results and proved the validity of the proposed sensor for being used in the automotive sector towards applications such as autonomous pedestrian collision avoidance.
2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2006
This paper presents a new method for real-time ego-motion calculation applied to the location/ori... more This paper presents a new method for real-time ego-motion calculation applied to the location/orientation of a cheap wide-angle stereo camera in a 3D environment. To achieve that, the goal is to solve the Simultaneous Localization and Mapping (SLAM) problem. Our approach consists in the 3D sequential mapping of natural land-marks by means of a stereo camera, which also provides means to obtain the camera location/orientation. The dynamic behavior is modeled using a top-down Bayesian method. The results show a comparison between our system and a monocular visual SLAM system using a hand-waved camera. Several improvements related to no priori environment knowledge requirements, lower processing time (real-time constrained) and higher robustness is presented.
The framework of this paper is robot localization inside buildings using WiFi signal strength mea... more The framework of this paper is robot localization inside buildings using WiFi signal strength measure. This localization is usually made up of two phases: training and estimation stages. In the former the WiFi signal strength of all visible Access Points (APs) are collected and stored in a database or Wifi map, while in the latter the signal strengths received from
In this paper we present a new real-time hierarchical (topological/metric) Visual SLAM system foc... more In this paper we present a new real-time hierarchical (topological/metric) Visual SLAM system focusing on the localization of a vehicle in large-scale outdoor urban environments. It is exclusively based on the visual information provided by both a low-cost wide-angle stereo camera and a low-cost GPS. Our approach divides the whole map into local sub-maps identified by the so-called fingerprint (reference poses). At the sub-map level (Low Level SLAM), 3D sequential mapping of natural landmarks and the vehicle location/orientation are obtained using a top-down Bayesian method to model the dynamic behavior. A higher topological level (High Level SLAM) based on references poses has been added to reduce the global accumulated drift, keeping real-time constraints. Using this hierarchical strategy, we keep local consistency of the metric sub-maps, by mean of the EKF, and global consistency by using the topological map and the MultiLevel Relaxation (MLR) algorithm. GPS measurements are integrated at both levels, improving global estimation. Some experimental results for different large-scale urban environments are presented, showing an almost constant processing time.
This paper describes a monocular vision-based Adaptive Cruise Control (ACC) System in the framewo... more This paper describes a monocular vision-based Adaptive Cruise Control (ACC) System in the framework of Intelligent Transportation Systems (ITS) technologies. The challenge is to use a single camera as input, in order to achieve a low cost final system that meets the requirements needed to undertake serial production.
This paper presents a new method for real-time environments. One of the main milestones is to ach... more This paper presents a new method for real-time environments. One of the main milestones is to achieve large SLAM calculation applied to autonomous robot navigation in closing loops in robot paths running in real-time. large-scale environments without restrictions. It is exclusively Several approaches can be found to solve the related issues based on the visual information provided by a cheap wide-angle by using metric methods, topological methods or hybrid ones. stereo camera. Our approach divide the global map into local One example of the last ones is described in [5]. This solution sub-maps identified by the so-called SIFT fingerprint. At the tries to build a topological map composed by several simple sub-map level (low level SLAM), 3D sequential mapping of metric maps. After that, as long as the robot explores new natural land-marks and the robot location/orientation are
2009 IEEE International Conference on Robotics and Automation, 2009
In this paper we present a new real-time hierarchical (topological/metric) Visual SLAM system foc... more In this paper we present a new real-time hierarchical (topological/metric) Visual SLAM system focusing on the localization of a vehicle in large-scale outdoor urban environments. It is exclusively based on the visual information provided by both a low-cost wide-angle stereo camera and a low-cost GPS. Our approach divides the whole map into local sub-maps identified by the so-called fingerprint (reference poses). At the sub-map level (Low Level SLAM), 3D sequential mapping of natural landmarks and the vehicle location/orientation are obtained using a top-down Bayesian method to model the dynamic behavior. A higher topological level (High Level SLAM) based on references poses has been added to reduce the global accumulated drift, keeping real-time constraints. Using this hierarchical strategy, we keep local consistency of the metric sub-maps, by mean of the EKF, and global consistency by using the topological map and the MultiLevel Relaxation (MLR) algorithm. GPS measurements are integrated at both levels, improving global estimation. Some experimental results for different large-scale urban environments are presented, showing an almost constant processing time.
Uploads
Papers by Manuel Ocaña