Search results for "Robot"
showing 10 items of 1036 documents
Deep Reinforcement Learning with Omnidirectional Images: application to UAV Navigation in Forests
2022
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). To this end, we present a DRL solution based on equirectangular images and demonstrates its relevance, especially compared to its perspective version. Several visual modalities are compared: ground truth depth, RGB, and depth directly estimated from these 360°R GB images using Deep Learning methods. Next, we propose a spherical adaptation to take into …
On Keyframe Positioning for Pose Graphs Applied to Visual SLAM
2013
International audience; In this work, a new method is introduced for localization and keyframe identification to solve a Simultaneous Localization and Mapping (SLAM) problem. The proposed approach is based on a dense spherical acquisition system that synthesizes spherical intensity and depth images at arbitrary locations. The images are related by a graph of 6 degrees-of-freedom (DOF) poses which are estimated through spherical registration. A direct image-based method is provided to estimate pose by using both depth and color information simultaneously. A new keyframe identification method is proposed to build the map of the environment by using the covariance matrix between raletive 6 DOF…
Time to Contact Estimation on Paracatadioptric Cameras
2012
International audience; Time to contact or time to collision (TTC) is the time available to a robot before reaching an object. In this paper, we propose to estimate this time using a catadioptric camera embedded on th erobot. Indeed, whereas a lot of works have shown the utility of this kind of cameras in robotic applications (monitoring, locali- sation, motion,...), a few works deal with the problem of time to contact estimation on it. Thus, in this paper, we propose a new work which allows to define and to estimate the TTC on catadioptric camera. This method will be validated on simulated and real data.
Localisation Basée Vision : de l'hétérogénéité des approches et des données
2017
National audience; De nos jours, nous disposons d'une grande diversité de données sur les lieux qui nous entourent. Ces données peuvent être de natures très différentes : une collection d'images, un modèle 3D, un nuage de points colorisés, etc. Lorsque les GPS font défaut, ces informations peuvent être très utiles pour localiser un agent dans son environnement s'il peut lui-même acquérir des informations à partir d'un système de vision. On parle alors de Localisation Basée Vision (LBV). De par la grande hétérogénéité des données acquises et connues sur l'environnement, il existe de nombreux travaux traitant de ce problème. Cet article a pour objet de passer en revue les différentes méthodes…
Reconstruction 3D de scènes dynamiques par segmentation au sens du mouvement
2016
National audience; L'objectif de ce travail est de reconstruire les parties sta-tiques et dynamiques d'une scène 3D à l'aide d'un robot mobile équipé d'un capteur 3D. Cette reconstruction né-cessite la classification des points 3D acquis au cours du temps en point fixe et point mobile indépendamment du dé-placement du robot. Notre méthode de segmentation utilise directement les données 3D et étudie les mouvements des objets dans la scène sans hypothèse préalable. Nous déve-loppons un algorithme complet reconstruisant les parties fixes de la scène à chaque acquisition à l'aide d'un RAN-SAC qui ne requiert que 3 points pour recaler les nuages de points. La méthode a été expérimentée sur de la…
Stratified Autocalibration of Cameras with Euclidean Image Plane
2020
International audience; This paper tackles the problem of stratified autocalibration of a moving camera with Euclidean image plane (i.e. zero skew and unit aspect ratio) and constant intrinsic parameters. We show that with these assumptions, in addition to the polynomial derived from the so-called modulus constraint, each image pair provides a new quartic polynomial in the unknown plane at infinity. For three or more images, the plane at infinity estimation is stated as a constrained polynomial optimization problem that can efficiently be solved using Lasserre's hierarchy of semidefinite relaxations. The calibration parameters and thus a metric reconstruction are subsequently obtained by so…
Perspective-n-Learned-Point: Pose Estimation from Relative Depth
2019
International audience; In this paper we present an online camera pose estimation method that combines Content-Based Image Retrieval (CBIR) and pose refinement based on a learned representation of the scene geometry extracted from monocular images. Our pose estimation method is two-step, we first retrieve an initial 6 Degrees of Freedom (DoF) location of an unknown-pose query by retrieving the most similar candidate in a pool of geo-referenced images. In a second time, we refine the query pose with a Perspective-n-Point (PnP) algorithm where the 3D points are obtained thanks to a generated depth map from the retrieved image candidate. We make our method fast and lightweight by using a commo…
The Influence of the feedback control of the hexapod platform of the SAAM dynamic driving simulator on neuromuscular dynamics of the drivers
2012
Multi sensorial cues (visual, auditory, haptic, inertial, vestibular, neuromuscular) [Ang2] play important roles to represent a proper sensation (objectively) and so a perception (subjectively as cognition) in driving simulators. Driving simulator aims at giving the sensation of driving as in a real case. For a similar situation, the driver has to react in the same way as in reality in terms of ‘self motion’. To enable this behavior, the driving simulator must enhance the virtual immersion of the subject in the driving situation. The subject has to perceive the motion of his own body in the virtual scene of the virtual car as he will have in a real car. For that reason, restituting the iner…
Robot Personality Design for an Appropriate Response to the Human Partner
2012
International audience; This paper discusses the importance of modeling personality for social robots. While human-liked features (such as voice, gestures, and postures) are well-studied in social robotics, developing robots with personality traits is still very much in its infancy. In this paper, we show and argue the importance of embodying personality in the robot's behavior so as to provide a more natural interaction and a more appropriate feedback to the human partner.