— Autonomous robots conception has to face developing efficient localization and control algorith... more — Autonomous robots conception has to face developing efficient localization and control algorithms which could be implemented in a small electronic system, embedded on a robot. The WACIF project, supported by the French government, takes up this challenge. It aims to design algorithms and electronics for an autonomous surveillance robot at home. Thanks to an original image-based framework, the developed prototype is able to navigate autonomously into an indoor environment. All the navigation algorithms are running on a programmable on-board hardware system controlling a two wheeled nonholonomic mobile robot, which is equipped with an embedded monocular vision system. The proposed framework includes the concept of visual memory of the environment. In an unknown environment, this memory results from a supervised learning step. A reference path, to be performed later in an autonomous way, is recorded as a set of ordered key images of the environment, called visual path. The robot performs the learnt path thanks to recently developed approaches of vision-based localization and visual servoing for nonholonomic mobile robots.
2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2006
In this paper, we present a control design for the tele-operation of a miniature unmanned aerial ... more In this paper, we present a control design for the tele-operation of a miniature unmanned aerial vehicle known as an X4-flyer. A simple dynamic nonlinear model for the vehicle, valid for quasi-stationary flight conditions, is derived as a basis for the control design. An attitude control based on information issued from an Inertial Measurement Unit is designed. In order to control the vehicle altitude, an adaptive controller avoiding the ground effects and based on measurements issued from an ultrasonic low cost sensor is designed. In order to compute the altitude velocity, an estimator based on the proposed modelling is used. At the end of the paper, experimental results are presented.
2010 IEEE International Conference on Robotics and Automation, 2010
ABSTRACT Classic registration methods for model-based tracking try to align the projected edges o... more ABSTRACT Classic registration methods for model-based tracking try to align the projected edges of a 3D model with the edges of the image. However, wrong matches at low level can make these methods fail. This paper presents a new approach allowing to retrieve multiple hypothesis on the camera pose from multiple low-level hypothesis. These hypothesis are integrated into a particle filtering framework to guide the particle set toward the peaks of the distribution. Experiments on simulated and real video sequences show the improvement in robustness of the resulting tracker.
2009 IEEE International Conference on Robotics and Automation, 2009
ABSTRACT — Color-based tracking methods have proved to be efficient for their robustness qualitie... more ABSTRACT — Color-based tracking methods have proved to be efficient for their robustness qualities. The drawback of such global representation of an object is the lack of information on its spatial configuration, making difficult the tracking of more complex motions. This issue can be overcome by using several kernels weighting pixels locations. In this paper a multiple kernels configuration is proposed and developed in both probabilistic and deterministic frameworks. The advantages of both approaches are combined to design a robust tracker allowing to track location, size and orientation of the object. A target tracking scheme using visual servoing considering measurements provided by the presented approach validates the proposed method. I.
2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2011
ABSTRACT This paper proposes a vision-based algorithm to autonomously track and chase a moving ta... more ABSTRACT This paper proposes a vision-based algorithm to autonomously track and chase a moving target with a small-size flying UAV. The challenging constraints associated with the UAV flight led us to consider a density-based representation of the object to track. The proposed approach to estimate the target's position, orientation and scale, is built on a robust color-based tracker using a multi-part representation. This object tracker can handle large displacements, occlusions and account for some image noise due to partial loss of wireless video link, thanks to the use of a particle filter. The information obtained from the visual tracker is then used to control the position and yaw angle of the UAV in order to chase the target. A hierarchical control scheme is designed to achieve the tracking task. Experiments on a quad-rotor UAV following a small moving car are provided to validate the proposed approach.
This paper proposes a novel model-based tracking approach for 3-D localization. One main difficul... more This paper proposes a novel model-based tracking approach for 3-D localization. One main difficulty of standard model-based approach lies in the presence of low-level ambiguities between different edges. In this paper, given a 3-D model of the edges of the environment, we derive a multiple hypotheses tracker which retrieves the potential poses of the camera from the observations in the image. We also show how these candidate poses can be integrated into a particle filtering framework to guide the particle set toward the peaks of the distribution. Motivated by the UAV indoor localization problem where GPS signal is not available, we validate the algorithm on real image sequences from UAV flights.
2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2008
In this paper, we present a method to efficiently manage visual memory for autonomous vehicle nav... more In this paper, we present a method to efficiently manage visual memory for autonomous vehicle navigation in large scale environments. It relies on two crucial issues for real-time navigation: an efficient organisation of the memory and small computational cost. A software platform (SoViN) dedicated to visual memory management and navigation strategies (including vision-based memory building, localization and navigation) has been developed to fulfill these requirements. We show that using this software architecture makes possible realtime navigation in large-scale outdoor situation using a single camera and natural landmarks.
2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2010
... on the quad-rotor (X4-flyer) developped by the CEA LIST (Figure 3). The UAV sends the ... gro... more ... on the quad-rotor (X4-flyer) developped by the CEA LIST (Figure 3). The UAV sends the ... ground station and the desired orientation and thrust are sent back to the quad-rotor vehicle. Onboard, the exponential stability of the orientation toward the desired one is ensured by a 'high ...
2008 IEEE International Conference on Robotics and Automation, 2008
An efficient method for global robot localization in a memory of omnidirectional images is presen... more An efficient method for global robot localization in a memory of omnidirectional images is presented. This method is valid for indoor and outdoor environments and not restricted to mobile robots. The proposed strategy is purely vision-based and uses as reference a set of prerecorded images (visual memory). The localization consists on finding in the visual memory the image which best fits the current image. We propose a hierarchical process combining global descriptors computed onto cubic interpolation of triangular mesh and patches correlation around Harris corners. To evaluate this method, three large images data sets have been used. Results of the proposed method are compared with those obtained from state-of-the-art techniques by means of 1) accuracy, 2) amount of memorized data required per image and 3) computational cost. The proposed method shows the best compromise in term of those criteria.
2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2007
Omnidirectional cameras have a wide field of view and are thus used in many robotic vision tasks.... more Omnidirectional cameras have a wide field of view and are thus used in many robotic vision tasks. An omnidirectional view may be acquired by a fisheye camera which provides a full image compared to catadioptric visual sensors and do not increase the size and the weakness of the imaging system with respect to perspective cameras. We prove that the unified model for catadioptric systems can model fisheye cameras with distortions directly included in its parameters. This unified projection model consists on a projection onto a virtual unitary sphere, followed by a perspective projection onto an image plane. The validity of this assumption is discussed and compared with other existing models. Calibration and partial Euclidean reconstruction results help to confirm the validity of our approach. Finally, an application to the visual servoing of a mobile robot is presented and experimented.
2008 10th International Conference on Control, Automation, Robotics and Vision, 2008
In this paper, we present a complete framework for autonomous indoor robot navigation. We show th... more In this paper, we present a complete framework for autonomous indoor robot navigation. We show that autonomous navigation is possible in indoor situation using a single camera and natural landmarks. When navigating in an unknown environment for the first time, a natural behavior consists on memorizing some key views along the performed path, in order to use these references as checkpoints for a future navigation mission. The navigation framework for wheeled robots presented in this paper is based on this assumption. During a human-guided learning step, the robot performs paths which are sampled and stored as a set of ordered key images, acquired by an embedded camera. The set of these obtained visual paths is topologically organized and provides a visual memory of the environment. Given an image of one of the visual paths as a target, the robot navigation mission is defined as a concatenation of visual path subsets, called visual route. When running autonomously, the control guides the robot along the reference visual route without explicitly planning any trajectory. The control consists on a vision-based control law adapted to the nonholonomic constraint. The proposed framework has been designed for a generic class of cameras (including conventional, catadioptric and fish-eye cameras). Experiments with a AT3 Pioneer robot navigating in an indoor environment have been carried on with a fisheye camera. Results validate our approach.
In this paper, we investigate a range of image-based visual servo control algorithms for regulati... more In this paper, we investigate a range of image-based visual servo control algorithms for regulation of the position of a quadrotor aerial vehicle. The most promising control algorithms have been successfully implemented on an autonomous aerial vehicle and demonstrate excellent performance.
This paper focuses on a new torque detection technique for magnetorheological (MR) actuators. An ... more This paper focuses on a new torque detection technique for magnetorheological (MR) actuators. An MR fluid consists of a suspension of ferromagnetic micron-sized particles in a carrier fluid. Under the action of a magnetic field, these particles form chains-like structures which interact with the magnetic poles. The torque detection technique is based on the assumption that a relative displacement of the poles stretches the chains, altering the magnetic reluctance of the fluid gap. This hypothesis is analytically developed using an elementary group of ferromagnetic particles placed in a non-magnetic carrier liquid. A measure of the excitation coil impedance using a high precision demodulator, is used to verify this hypothesis. Experimental results show that when the poles are displaced before the rupture of the chains, the chains are stretched and the reluctance increases. A higher sensitivity system is subsequently proposed to detect the variation of an external torque. The experimental results demonstrate that the system is able to detect the application as well as the release of the torque and can successfully be employed to detect the chain rupture critical point.
This paper presents the design and the stability analysis of a hierarchical controller for unmann... more This paper presents the design and the stability analysis of a hierarchical controller for unmanned aerial vehicles (UAV), using singular perturbation theory. Position and attitude control laws are successively designed by considering a time-scale separation between the translational dynamics and the orientation dynamics of a six degrees of freedom vertical take-off and landing (VTOL) UAV model. For the design of the position controller, we consider the case where the linear velocity of the vehicle is not measured. A partial state feedback control law is proposed, based on the introduction of a virtual state into the translational dynamics of the system. Results from simulation and from experiments on a miniature quadrirotor UAV are provided to illustrate the performance of the proposed control scheme.
In this paper, we present a generic framework for urban vehicle navigation using a topological ma... more In this paper, we present a generic framework for urban vehicle navigation using a topological map. This map is built by taking into account the non-holonomic behaviour of the vehicle. After a localization step, a sensory route is extracted to reach a goal. This route is followed using a sensor-based control strategy, based on the vehicle model and computed from the state extracted from the current and the desired sensory images. In that aim, a generic model is proposed for visual sensors. Experiments with an urban electric vehicle navigating in an outdoor environment have been carried out with a fisheye camera using a single camera and natural landmarks. A navigation along a 1700-meter-long trajectory validates our approach.
Autonomous robots conception has to face developing efficient localization and control algorithms... more Autonomous robots conception has to face developing efficient localization and control algorithms which could be implemented in a small electronic system, embedded on a robot. The WACIF project, supported by the French government, takes up this challenge. It aims to design algorithms and electronics for an autonomous surveillance robot at home. Thanks to an original image-based framework, the developed prototype is able to navigate autonomously into an indoor environment. All the navigation algorithms are running on a programmable on-board hardware system controlling a two wheeled nonholonomic mobile robot, which is equipped with an embedded monocular vision system. The proposed framework includes the concept of visual memory of the environment. In an unknown environment, this memory results from a supervised learning step. A reference path, to be performed later in an autonomous way, is recorded as a set of ordered key images of the environment, called visual path. The robot performs the learnt path thanks to recently developed approaches of vision-based localization and visual servoing for nonholonomic mobile robots.
— Autonomous robots conception has to face developing efficient localization and control algorith... more — Autonomous robots conception has to face developing efficient localization and control algorithms which could be implemented in a small electronic system, embedded on a robot. The WACIF project, supported by the French government, takes up this challenge. It aims to design algorithms and electronics for an autonomous surveillance robot at home. Thanks to an original image-based framework, the developed prototype is able to navigate autonomously into an indoor environment. All the navigation algorithms are running on a programmable on-board hardware system controlling a two wheeled nonholonomic mobile robot, which is equipped with an embedded monocular vision system. The proposed framework includes the concept of visual memory of the environment. In an unknown environment, this memory results from a supervised learning step. A reference path, to be performed later in an autonomous way, is recorded as a set of ordered key images of the environment, called visual path. The robot performs the learnt path thanks to recently developed approaches of vision-based localization and visual servoing for nonholonomic mobile robots.
2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2006
In this paper, we present a control design for the tele-operation of a miniature unmanned aerial ... more In this paper, we present a control design for the tele-operation of a miniature unmanned aerial vehicle known as an X4-flyer. A simple dynamic nonlinear model for the vehicle, valid for quasi-stationary flight conditions, is derived as a basis for the control design. An attitude control based on information issued from an Inertial Measurement Unit is designed. In order to control the vehicle altitude, an adaptive controller avoiding the ground effects and based on measurements issued from an ultrasonic low cost sensor is designed. In order to compute the altitude velocity, an estimator based on the proposed modelling is used. At the end of the paper, experimental results are presented.
2010 IEEE International Conference on Robotics and Automation, 2010
ABSTRACT Classic registration methods for model-based tracking try to align the projected edges o... more ABSTRACT Classic registration methods for model-based tracking try to align the projected edges of a 3D model with the edges of the image. However, wrong matches at low level can make these methods fail. This paper presents a new approach allowing to retrieve multiple hypothesis on the camera pose from multiple low-level hypothesis. These hypothesis are integrated into a particle filtering framework to guide the particle set toward the peaks of the distribution. Experiments on simulated and real video sequences show the improvement in robustness of the resulting tracker.
2009 IEEE International Conference on Robotics and Automation, 2009
ABSTRACT — Color-based tracking methods have proved to be efficient for their robustness qualitie... more ABSTRACT — Color-based tracking methods have proved to be efficient for their robustness qualities. The drawback of such global representation of an object is the lack of information on its spatial configuration, making difficult the tracking of more complex motions. This issue can be overcome by using several kernels weighting pixels locations. In this paper a multiple kernels configuration is proposed and developed in both probabilistic and deterministic frameworks. The advantages of both approaches are combined to design a robust tracker allowing to track location, size and orientation of the object. A target tracking scheme using visual servoing considering measurements provided by the presented approach validates the proposed method. I.
2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2011
ABSTRACT This paper proposes a vision-based algorithm to autonomously track and chase a moving ta... more ABSTRACT This paper proposes a vision-based algorithm to autonomously track and chase a moving target with a small-size flying UAV. The challenging constraints associated with the UAV flight led us to consider a density-based representation of the object to track. The proposed approach to estimate the target's position, orientation and scale, is built on a robust color-based tracker using a multi-part representation. This object tracker can handle large displacements, occlusions and account for some image noise due to partial loss of wireless video link, thanks to the use of a particle filter. The information obtained from the visual tracker is then used to control the position and yaw angle of the UAV in order to chase the target. A hierarchical control scheme is designed to achieve the tracking task. Experiments on a quad-rotor UAV following a small moving car are provided to validate the proposed approach.
This paper proposes a novel model-based tracking approach for 3-D localization. One main difficul... more This paper proposes a novel model-based tracking approach for 3-D localization. One main difficulty of standard model-based approach lies in the presence of low-level ambiguities between different edges. In this paper, given a 3-D model of the edges of the environment, we derive a multiple hypotheses tracker which retrieves the potential poses of the camera from the observations in the image. We also show how these candidate poses can be integrated into a particle filtering framework to guide the particle set toward the peaks of the distribution. Motivated by the UAV indoor localization problem where GPS signal is not available, we validate the algorithm on real image sequences from UAV flights.
2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2008
In this paper, we present a method to efficiently manage visual memory for autonomous vehicle nav... more In this paper, we present a method to efficiently manage visual memory for autonomous vehicle navigation in large scale environments. It relies on two crucial issues for real-time navigation: an efficient organisation of the memory and small computational cost. A software platform (SoViN) dedicated to visual memory management and navigation strategies (including vision-based memory building, localization and navigation) has been developed to fulfill these requirements. We show that using this software architecture makes possible realtime navigation in large-scale outdoor situation using a single camera and natural landmarks.
2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2010
... on the quad-rotor (X4-flyer) developped by the CEA LIST (Figure 3). The UAV sends the ... gro... more ... on the quad-rotor (X4-flyer) developped by the CEA LIST (Figure 3). The UAV sends the ... ground station and the desired orientation and thrust are sent back to the quad-rotor vehicle. Onboard, the exponential stability of the orientation toward the desired one is ensured by a 'high ...
2008 IEEE International Conference on Robotics and Automation, 2008
An efficient method for global robot localization in a memory of omnidirectional images is presen... more An efficient method for global robot localization in a memory of omnidirectional images is presented. This method is valid for indoor and outdoor environments and not restricted to mobile robots. The proposed strategy is purely vision-based and uses as reference a set of prerecorded images (visual memory). The localization consists on finding in the visual memory the image which best fits the current image. We propose a hierarchical process combining global descriptors computed onto cubic interpolation of triangular mesh and patches correlation around Harris corners. To evaluate this method, three large images data sets have been used. Results of the proposed method are compared with those obtained from state-of-the-art techniques by means of 1) accuracy, 2) amount of memorized data required per image and 3) computational cost. The proposed method shows the best compromise in term of those criteria.
2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2007
Omnidirectional cameras have a wide field of view and are thus used in many robotic vision tasks.... more Omnidirectional cameras have a wide field of view and are thus used in many robotic vision tasks. An omnidirectional view may be acquired by a fisheye camera which provides a full image compared to catadioptric visual sensors and do not increase the size and the weakness of the imaging system with respect to perspective cameras. We prove that the unified model for catadioptric systems can model fisheye cameras with distortions directly included in its parameters. This unified projection model consists on a projection onto a virtual unitary sphere, followed by a perspective projection onto an image plane. The validity of this assumption is discussed and compared with other existing models. Calibration and partial Euclidean reconstruction results help to confirm the validity of our approach. Finally, an application to the visual servoing of a mobile robot is presented and experimented.
2008 10th International Conference on Control, Automation, Robotics and Vision, 2008
In this paper, we present a complete framework for autonomous indoor robot navigation. We show th... more In this paper, we present a complete framework for autonomous indoor robot navigation. We show that autonomous navigation is possible in indoor situation using a single camera and natural landmarks. When navigating in an unknown environment for the first time, a natural behavior consists on memorizing some key views along the performed path, in order to use these references as checkpoints for a future navigation mission. The navigation framework for wheeled robots presented in this paper is based on this assumption. During a human-guided learning step, the robot performs paths which are sampled and stored as a set of ordered key images, acquired by an embedded camera. The set of these obtained visual paths is topologically organized and provides a visual memory of the environment. Given an image of one of the visual paths as a target, the robot navigation mission is defined as a concatenation of visual path subsets, called visual route. When running autonomously, the control guides the robot along the reference visual route without explicitly planning any trajectory. The control consists on a vision-based control law adapted to the nonholonomic constraint. The proposed framework has been designed for a generic class of cameras (including conventional, catadioptric and fish-eye cameras). Experiments with a AT3 Pioneer robot navigating in an indoor environment have been carried on with a fisheye camera. Results validate our approach.
In this paper, we investigate a range of image-based visual servo control algorithms for regulati... more In this paper, we investigate a range of image-based visual servo control algorithms for regulation of the position of a quadrotor aerial vehicle. The most promising control algorithms have been successfully implemented on an autonomous aerial vehicle and demonstrate excellent performance.
This paper focuses on a new torque detection technique for magnetorheological (MR) actuators. An ... more This paper focuses on a new torque detection technique for magnetorheological (MR) actuators. An MR fluid consists of a suspension of ferromagnetic micron-sized particles in a carrier fluid. Under the action of a magnetic field, these particles form chains-like structures which interact with the magnetic poles. The torque detection technique is based on the assumption that a relative displacement of the poles stretches the chains, altering the magnetic reluctance of the fluid gap. This hypothesis is analytically developed using an elementary group of ferromagnetic particles placed in a non-magnetic carrier liquid. A measure of the excitation coil impedance using a high precision demodulator, is used to verify this hypothesis. Experimental results show that when the poles are displaced before the rupture of the chains, the chains are stretched and the reluctance increases. A higher sensitivity system is subsequently proposed to detect the variation of an external torque. The experimental results demonstrate that the system is able to detect the application as well as the release of the torque and can successfully be employed to detect the chain rupture critical point.
This paper presents the design and the stability analysis of a hierarchical controller for unmann... more This paper presents the design and the stability analysis of a hierarchical controller for unmanned aerial vehicles (UAV), using singular perturbation theory. Position and attitude control laws are successively designed by considering a time-scale separation between the translational dynamics and the orientation dynamics of a six degrees of freedom vertical take-off and landing (VTOL) UAV model. For the design of the position controller, we consider the case where the linear velocity of the vehicle is not measured. A partial state feedback control law is proposed, based on the introduction of a virtual state into the translational dynamics of the system. Results from simulation and from experiments on a miniature quadrirotor UAV are provided to illustrate the performance of the proposed control scheme.
In this paper, we present a generic framework for urban vehicle navigation using a topological ma... more In this paper, we present a generic framework for urban vehicle navigation using a topological map. This map is built by taking into account the non-holonomic behaviour of the vehicle. After a localization step, a sensory route is extracted to reach a goal. This route is followed using a sensor-based control strategy, based on the vehicle model and computed from the state extracted from the current and the desired sensory images. In that aim, a generic model is proposed for visual sensors. Experiments with an urban electric vehicle navigating in an outdoor environment have been carried out with a fisheye camera using a single camera and natural landmarks. A navigation along a 1700-meter-long trajectory validates our approach.
Autonomous robots conception has to face developing efficient localization and control algorithms... more Autonomous robots conception has to face developing efficient localization and control algorithms which could be implemented in a small electronic system, embedded on a robot. The WACIF project, supported by the French government, takes up this challenge. It aims to design algorithms and electronics for an autonomous surveillance robot at home. Thanks to an original image-based framework, the developed prototype is able to navigate autonomously into an indoor environment. All the navigation algorithms are running on a programmable on-board hardware system controlling a two wheeled nonholonomic mobile robot, which is equipped with an embedded monocular vision system. The proposed framework includes the concept of visual memory of the environment. In an unknown environment, this memory results from a supervised learning step. A reference path, to be performed later in an autonomous way, is recorded as a set of ordered key images of the environment, called visual path. The robot performs the learnt path thanks to recently developed approaches of vision-based localization and visual servoing for nonholonomic mobile robots.
Uploads
Papers by Laurent Eck