ALLIBERT , Guillaume

No description

Image-based visual servoing (IBVS) is now recognized to be an efficient and robust control strategy to guide robots using only visual data. Classical IBVS is commonly based on the Cartesian coordinates of points in the image. Although the convergence of the visual features to the desired ones is generally achieved, classical IBVS can lead to...

L'asservissement visuel 2D (AV2D) utilise très souvent comme information visuelle de retour, les coordonnées cartésiennes de points dans l'image. Cette approche classique permet généralement de satisfaire les objectifs de commande. Cependant, dans certaines configurations, des déplacements 3D inutiles peuvent être constatés. Ce désagrément peut...

The purpose of this paper is to show what image prediction can bring to Image-Based Visual Servoing. The visual feature prediction is obtained thanks to the interaction matrix. Based on a Model Predictive Control strategy, the visual servoing task is formulated into an optimization problem. The error between the reference features and the...

This paper revisits the problem of estimating the pose (i.e. position and attitude) of a robotic vehicle by combining landmark position measurements provided by a stereo camera with measurements of an Inertial Measurement Unit. The distinguished features with respect to similar works on the topic are two folds: First, the vehicle's linear...

Visual servoing control schemes, such as Image-Based (IBVS), Pose Based (PBVS) or Hybrid-Based (HBVS) have been extensively developed over the last decades making possible their uses in a large number of applications. It is well-known that the main problems to be handled concern the presence of local minima or singularities, the visibility...

This paper addresses the choice of the control horizon in a Nonlinear Model Predictive Control (NMPC) strat- egy for nonholonomic vehicles. The latter can be modeled by chained systems. We establish a relation between the degree of nonholonomy and the minimum length of the control horizon so as to make the full-state control possible. A...

Flight performance of aerial robotic vehicles is critically dependent on the quality of the state estimates provided by onboard sensor systems. The attitude estimation problem has been extensively studied over the last ten years and the development of low complexity, high performance, robust non-linear observers for attitude has been one of the...

Recently, Model Predictive Path Integral (MPPI) control algorithm has been extensively applied to autonomous navigation tasks, where the cost map is mostly assumed to be known and the 2D navigation tasks are only performed. In this paper, we propose a generic MPPI control framework that can be used for 2D or 3D autonomous navigation tasks in...

This paper deals with the image-based visual servoing (IBVS), subject to constraints. Robot workspace limitations, visibility constraints, and actuators limitations are addressed. These constraints are formu- lated into state, output, and input constraints, respectively. Based on the predictive-control strategy, the IBVS task is written into a...

In this chapter, image-based visual servoing is addressed via nonlinear model predictive control. The visual servoing task is formulated into a nonlinear optimization problem in the image plane. The proposed approach, named visual pre- dictive control, can easily and explicitly take into account 2D and 3D constraints. Furthermore, the image...

This paper deals with state feedback control of chained systems based on a Nonlinear Model Predictive Control (NMPC) strategy. Chained systems can model many common nonholonomic vehicles. We establish a relation between the degree of nonholonomy and the minimum length of the control horizon so as to make the NMPC feasible. A necessary condition...

Perception is crucial for drone obstacle avoidance in complex, static, and unstructured outdoor environments. However, most navigation solutions based on Deep Reinforcement Learning (DRL) use limited Field-Of-View (FOV) images as input. In this paper, we demonstrate that omnidirectional images improve these methods. Thus, we provide a...

Deep Reinforcement Learning (DRL) is highly efficient for solving complex tasks such as drone obstacle avoidance using cameras. However, these methods are often limited by the camera perception capabilities. In this paper, we demonstrate that point-goal navigation performances can be improved by using cameras with a wider Field-Of-View (FOV)....

Omnidirectional images have drawn great research attention recently thanks to their great potential and performance in various computer vision tasks. However, processing such a type of image requires an adaptation to take into account spherical distortions. Therefore, it is not trivial to directly extend the conventional convolutional neural...

— A key requirement for effective control of quadro-tor vehicles is estimation of both attitude and linear velocity. Recent work has demonstrated that it is possible to measure horizontal velocities of a quadrotor vehicle from strap-down ac-celerometers along with a system model. In this paper we extend this to full body-fixed-frame velocity...

Solving Direct Shooting Model Predictive Control (MPC) optimization problems online can be computationally expensive if a large horizon is used while also maintaining a dense time sampling. In these cases, it is accepted that tradeoffs between computational load and performances should be sought in order to meet real-time feasibility...

In this paper, we present a coupled inertial and body-fixed frame non-linear complementary velocity aided attitude filter and a linear velocity controller for quadrotors. The coupled observers provide estimates of attitude and the different velocities associated with quadrotor motion. With the estimated body-fixed frame velocity, we propose a...

Model Predictive Control (MPC) while being a very effective control technique can become computationally demanding when a large prediction horizon is selected. To make the problem more tractable, one technique that has been proposed in the literature makes use of control input parameterizations to decrease the numerical complexity of nonlinear...

Conventional 2D Convolutional Neural Networks (CNN) extract features from an input image by applying linear filters. These filters compute the spatial coherence by weighting the photometric information on a fixed neighborhood without taking into account the geometric information. We tackle the problem of improving the classical RGB CNN methods...

A nonlinear image-based visual servo control approach for pipeline following of fully-actuated Autonomous Underwater Vehicles (AUV) is proposed. It makes use of the binormalized Plücker coordinates of the pipeline borders detected in the image plane as feedback information while the system dynamics are exploited in a cascade manner in the...

This paper describes a nonlinear image-based visual servo control algorithm for the pipeline tracking problem of a fully-actuated underwater vehicle. The dynamic model of a generic autonomous underwater vehicle (AUV), incorporating all significant forces and torques is developed and a generic velocity control strategy is proposed. The desired...

This paper presents a new observer on the Special Linear group SL(3). The proposed solution is oriented towards online homography estimation from video sequences obtained from robotic vehicles equipped with a monocular camera. The originality of this paper relies on the extension of our prior works based on linear features to nonlinear features...

Spherical cameras and the latest image processing techniques open up new horizons. In particular, methods based on Convolutional Neural Networks (CNNs) now give excellent results for optical flow estimation on perspective images. However, these approaches are highly dependent on their architectures and training datasets. This paper proposes to...