A5041727589- Robotics and Sensor-Based Localization
- Indoor and Outdoor Localization Technologies
- Target Tracking and Data Fusion in Sensor Networks
- Advanced Image and Video Retrieval Techniques
- Video Surveillance and Tracking Methods
- Inertial Sensor and Navigation
- Advanced Vision and Imaging
- Advanced Neural Network Applications
- Astro and Planetary Science
- Planetary Science and Exploration
- Robotic Path Planning Algorithms
- Autonomous Vehicle Technology and Safety
- Anomaly Detection Techniques and Applications
- Underwater Vehicles and Communication Systems
- Remote Sensing and LiDAR Applications
- Video Analysis and Summarization
- Infrastructure Maintenance and Monitoring
- 3D Surveying and Cultural Heritage
- Advanced Optical Sensing Technologies
- Traffic Prediction and Management Techniques
- Gait Recognition and Analysis
- Human Pose and Action Recognition
- Image and Object Detection Techniques
- Space Satellite Systems and Control
- Maritime Navigation and Safety
Institut Superieur de l'Aeronautique et de l'Espace (ISAE-SUPAERO)
2012-2025
Université de Toulouse
2018-2025
Laboratoire d'Optique Appliquée
2017
Université d'Orléans
2015-2016
Laboratoire Pluridisciplinaire de Recherche en Ingénierie des Systèmes, Mécanique et Energétique
2014-2015
Institut National des Sciences Appliquées Centre Val de Loire
2015
Institut National des Sciences Appliquées Rouen Normandie
2013
Laboratoire d'Informatique, du Traitement de l'Information et des Systèmes
2013
Université de Rouen Normandie
2013
Centre National de la Recherche Scientifique
2010-2013
Abstract Planetary defense efforts rely on estimates of the mechanical properties asteroids, which are difficult to constrain accurately from Earth. The asteroid material also important in interpretation Double Asteroid Redirection Test (DART) impact. Here we perform a detailed morphological analysis surface boulders Dimorphos using images, primary data set available DART mission. We estimate bulk angle internal friction be 32.7 ± 2. 5° our measurements roundness 34 best-resolved ranging...
Abstract The bearing capacity - the ability of a surface to support applied loads is an important parameter for understanding and predicting response surface. Previous work has inferred trafficability specific regions Moon using orbital imagery measurements boulder tracks visible on its Here, we estimate asteroid first time DART/DRACO images suspected (65803) Didymos. Given extremely low gravity environment, special attention paid underlying assumptions geotechnical approach. detailed...
Rotating radar sensors are perception systems rarely used in mobile robotics. This paper is concerned with the use of a ground-based panoramic sensor which able to deliver both distance and velocity multiple targets its surrounding. The consequence using such high speed robotics appearance geometric Doppler distortions collected data. These effects are, majority studies, ignored or considered as noise then corrected based on proprioceptive localization systems. Our purpose study data...
Active visual SLAM finds a wide array of applications in GNSS-Denied sub-terrain environments and outdoor for ground robots. To achieve robust localization mapping accuracy, it is imperative to incorporate the perception considerations goal selection path planning towards during an exploration mission. Through this work, we propose FIT-SLAM (Fisher Information Traversability estimation-based SLAM), new method tailored unmanned vehicles (UGVs) explore 3D environments. This approach devised...
This paper is concerned with robotic applications using a ground-based radar sensor for simultaneous localization and mapping problems. In mobile robotics, technology interesting because of its long range the robustness waves to atmospheric conditions, making these sensors well-suited extended outdoor applications. Two approaches data obtained from 360° field view microwave are presented compared. The first method trajectory-oriented technique, which makes no landmark assumptions avoids...
Summary Standard state estimation techniques, ranging from the linear Kalman filter (KF) to nonlinear extended KF (EKF), sigma‐point or particle filters, assume a perfectly known system model, that is, process and measurement functions noise statistics (both distribution its parameters). This is strong assumption which may not hold in practice, reason why several approaches have been proposed for robust filtering, mainly because performance particularly sensitive different model mismatches....
The use of a rotating range sensor in high speed robotics creates distortions the collected data. Such an effect is, majority studies, ignored or considered as noise and then corrected, based on proprioceptive sensors localization systems. In this study we consider that distortion contains information about vehicle's displacement. We propose to extract from without any other than exteroceptive only used for work is panoramic Frequency Modulated Continuous Wave (FMCW) radar called K2Pi. No...
According to a new market research report, electronic access control system is expected be worth $16.3 billion by 2017. Vision‐based biometric authentication systems have received much attention with increasing demands for long distance surveillance applications and the security area. Such visual application mainly focused on face recognition. Nevertheless, small size or poor quality images varying poses, illumination, expressions, glasses hats so can perturb To deal such problems, fusing of...
The purpose of this paper is to develop a wrapper Random Forest-based feature selection method and study the performance on emotion recognition different selected sets. A large bank Gabor filters used extract face appearance. then applied wide set based importance score computed by Forest. multi-class SVM finally trained chosen features using widely database (CK+ database). Results show impact rate reveal that anger, sadness neutral expression increased selection.
The technological advancement of sensors and computational power has opened a new chapter in machine learning for robotics applications, especially image classification, segmentation, object detection, self-driving cars. One the challenges among these applications is improving systems perception reliability accuracy through fusion. Hence, focus on using Stereo-cameras LiDARs as complement to its accurate distance measurement. However, calibration process mandatory before deployment. Some may...
The detection and tracking of moving objects (DATMO) in an outdoor environment from a mobile robot are difficult tasks because the wide variety dynamic objects. A reliable discrimination static detections without any prior knowledge is often conditioned by good position estimation obtained using Global Positionning System/Differential Positioning System (GPS/DGPS), proprioceptive sensors, inertial sensors or even use Simultaneous Localization Mapping (SLAM) algorithms. In this article...
Active visual SLAM finds a wide array of applications in GNSS-Denied sub-terrain environments and outdoor for ground robots. To achieve robust localization mapping accuracy, it is imperative to incorporate the perception considerations goal selection path planning towards during an exploration mission. Through this work, we propose FIT-SLAM (Fisher Information Traversability estimation-based SLAM), new method tailored unmanned vehicles (UGVs) explore 3D environments. This approach devised...
Urban environments are undergoing significant transformations, with pedestrian areas emerging as complex hubs of diverse mobility modes. This shift demands a more nuanced approach to urban planning and navigation technologies, highlighting the limitations traditional, road-centric datasets in capturing detailed dynamics spaces. In response, we introduce DELTA dataset, designed improve analysis mapping zones, thereby filling critical need for sidewalk-centric multimodal datasets. The dataset...
This letter addresses the robust state estimation problem for mismatched nonlinear dynamic systems. In this context, we are interested in filters able to provide consistent estimates while mitigating impact of possible modeling errors. We focus on cubature Kalman filter (CKF) and its square-root form (SCKF), being most promising Gaussian filters, latter providing improved numerical stability. leverage recently introduced linearly constraint filter, derive sigma-point-based counterparts,...
Environmental context detection is a topic of interest for the navigation community since it enables to build context-adaptive solution. Indeed if type environment known then possible choose proper data processing algorithm or select sensors be used dynamically adapt solution design itself. This paper proposes supervised machine learning model which can robustly classify multiple contexts such as urban canyons, urban, trees and open-sky areas using GNSS only. A training test database have...
This paper is concerned with the Simultaneous Localization And Mapping (SLAM) application a mobile robot moving in structured environment using data obtained from rotating sensors such as radars or lasers. A line-based EKF-SLAM (EKF stands for Extended Kalman Filter) algorithm presented, which able to deal that cannot be considered instantaneous when compared dynamics of vehicle. When sensor motion fast relative measurement time, scans become locally distorted. mapping solution includes...