Search

Self-driving vehicle technology has become a popular topic for discussion and debate in the modern day. Although LiDAR is one of the primary sensors being used by most of the groups working towards autonomous driving, it is very costly, prone to mechanical failure, and its localization capability is not scalable due to its dependency on high-definition maps. Also, the perception related benefits of a LiDAR can be achieved by using a sensor fusion of cameras and RADAR. Considering the drawbacks of the LiDARs, the availability of an alternate solution, and the recent progress of computer vision techniques in the last few years, we are proposing an architecture for vision-based autonomous driving. In this thesis, we outline building blocks for the development of this vision-based architecture, describe the functionality of these blocks, and provide a brief overview of existing studies and research to implement these blocks, and thereby achieve a vision-based autonomous system. Furthermore, we discuss the design and implementation of a few of these blocks in the purview of the activities being undertaken at Autonomous Living Laboratory (AVL) at UC San Diego.

International audience; Testing perception functions for safety-critical autonomous systems is a crucial task. The reason is that accurate ML models applied in computer vision tasks still fail in scenarios where humans perform well. Out-of-distribution (OOD) images are usually a source of such failures. For this reason, literature usually applies data augmentation techniques or runtime monitors such as OOD detectors to increase robustness. Evaluating such solutions is usually performed by analyzing metrics based on positive and negative rates over a dataset containing several perturbations. However, using such metrics on such datasets can be misleading since not all OOD data lead to failures in the perception system. Hence, testing a perception system cannot be reduced to measuring Machine Learning (ML) performances on a dataset but rely on the images captured by the system at runtime. However, the amount of time spent to generate diverse test cases during a simulation of perception components can grow quickly since it is a combinatorial optimization problem. Aiming to provide a solution for this challenging task, we present SiMOOD, an evolutionary simulation testing of safety-critical perception systems, which comes integrated into the CARLA simulator. Unlike related works that simulate scenarios that raise failures for control or specific perception problems such as adversarial and novelty, we provide an approach that finds the most relevant OOD perturbations that can lead to hazards in safety-critical perception systems. Moreover, our approach can decrease, at least 10 times, the amount of time to find a set of hazards in safety-critical scenarios such as autonomous emergency braking system simulation. Besides, code is publicly available for use.

Human workers conducting inspection and maintenance (I&M) operations on high altitude infrastructures like power lines or industrial facilities face significant difficulties getting tools or devices once they are deployed on this kind of workspaces. In this sense, aerial manipulation robots can be employed to deliver quickly objects to the operator, considering long reach configurations to improve safety and the feeling of comfort for the operator during the handover. This paper presents a dual arm aerial manipulation robot in cable suspended configuration intended to conduct fast and safe aerial delivery, considering a human-centered approach relying on an on-board perception system in which the aerial robot accommodates its pose to the worker. Preliminary experimental results in an indoor testbed validate the proposed system design., This work was supported by the EU project H2020 AERIAL-CORE (871479). Partial funding was obtained from the Spanish Project ROBMIND (PDC2021-121524-I00) and the Plan Estatal de Investigación Científica y Técnica y de Innovación of the Ministerio de Universidades del Gobierno de España (FPU19/04692).

Monitoring the safe social distancing then conducting efficient sterilization in potentially crowded public places are necessary but challenging especially during the COVID-19 pandemic. This work presents the 3D human space-based surveillance system enabling selective cleaning framework. To this end, the proposed AI-assisted perception techniques is deployed on Toyota Human Support Robot (HSR) equipped with autonomous navigation, Lidar, and RGBD vision sensor. The human density mapping represented as heatmap was constructed to identify areas with the level being likely the risks for interactions. The surveillance framework adopts the 3D human joints tracking technique and the accumulated asymmetrical Gaussian distribution scheme modeling the human location, size, and direction to quantify human density. The HSR generates the human density map as a grid-based heatmap to perform the safe human distance monitoring task while navigating autonomously inside the pre-built map. Then, the cleaning robot uses the levels of the generated heatmap to sterilize by the selective scheme. The experiment was tested in public places, including food court and wet market. The proposed framework performance analyzed with standard performance metrics in various map sizes spares about 19 % of the disinfection time and 15 % of the disinfection liquid usage, respectively.

Autonomous Vehicles (AVs) have the potential to solve many traffic problems, such as accidents, congestion and pollution. However, there are still challenges to overcome, for instance, AVs need to accurately perceive their environment to safely navigate in busy urban scenarios. The aim of this paper is to review recent articles on computer vision techniques that can be used to build an AV perception system. AV perception systems need to accurately detect non-static objects and predict their behaviour, as well as to detect static objects and recognise the information they are providing. This paper, in particular, focuses on the computer vision techniques used to detect pedestrians and vehicles. There have been many papers and reviews on pedestrians and vehicles detection so far. However, most of the past papers only reviewed pedestrian or vehicle detection separately. This review aims to present an overview of the AV systems in general, and then review and investigate several detection computer vision techniques for pedestrians and vehicles. The review concludes that both traditional and Deep Learning (DL) techniques have been used for pedestrian and vehicle detection; however, DL techniques have shown the best results. Although good detection results have been achieved for pedestrians and vehicles, the current algorithms still struggle to detect small, occluded, and truncated objects. In addition, there is limited research on how to improve detection performance in difficult light and weather conditions. Most of the algorithms have been tested on well-recognised datasets such as Caltech and KITTI; however, these datasets have their own limitations. Therefore, this paper recommends that future works should be implemented on more new challenging datasets, such as PIE and BDD100K. EPSRC DTP PhD studentship

An autonomous vehicle navigates by perceiving the environment through the sensors and acting on the received data by making sense of the surroundings. In this paper, innovative holoscopic 3D scene classification based on the single aperture holoscopic 3D camera is proposed to recognise continuous 3D scene of environment. The deep learning network AlexNet is used to evaluate the proposed approach, and the outcome exhibits promising results compared to 2D images.

Surgical robots have been widely researched due to their features of accurate positioning, no jitter, high precision, and low error rate under certain tasks. However, it is generally relatively slow to the feedback generated by force, deformation, or sudden and arbitrary impact during operation. Besides, the feedback is always provided through a vision that cannot meet the actual operation requirements for doctors. The customized design and integration of force perception functions on different robots have become one of the research hotspots of surgical robotics-worldwide recently. A force perception sensor for surgical robots based on Fiber Bragg grating (FBG) is proposed in this paper. It can be used to measure three-dimensional force. The experimental parameters are utilized to calibrate the model through the least square method. A four DoFs experimental platform is constructed. The system errors of the sensor involved are evaluated. The effectiveness of the proposed algorithm can be proved by the experimental results

The aim of this work is to propose mechanisms for multirotor drones that allow, on the one hand, to tolerate faults on the drone, and on the other hand to take into account the effects of the wind outdoors. The faults targeted include fault in actuators, sensors, but also software faults on the data fusion algorithms. ln our work, we have developed a robust controller and an exterior disturbance observer capable of cooperating with th, contrai reconfiguration method, to simultaneously tolerate motor failures and exterior wind disturbances through active fault tolerance techniques… We have also proposed a new technique for tolerating actuator faults for a coaxial octorotor drone. This technique is based on a robust command law with reconfigurable "self tuning sliding mode control (STSMC)" gains, where the control gains are readjusted according to the detected error in order to maintain the stability of the system. lndoor experiments are conducted to show and compare our solution with two other fault tolerance techniques. The efficiency and behavior of each method are studied after successive fault injections into the actuators. The main advantages and disadvantages of each method are deduced by analyzing the results obtained. Additionally, we provide an approach for fault tolerance of drone data fusion sensors and software mechanisms. This approach is based on the redundancy of sensors and the diversification of software components.; Le but de ce travail est de proposer des mécanismes pour les drones multirotors qui permettent d'une part de tolérer des fautes sur le drone, et d'autre part de prendre en compte les effets du vent en extérieur. Les fautes visées comportent des fautes d'actionneurs, de capteurs, mais également des fautes logicielles sur les algorithmes de fusion de données. Dans nos travaux, nous avons développé un contrôleur robuste et un observateur des perturbations extérieures capables de coopérer avec la méthode de reconfiguration des commandes, pour tolérer de façon simultanée les défaillances de moteurs et les perturbations extérieures du vent par des techniques de tolérance aux fautes active. Egalement, nous avons proposé une nouvelle technique de tolérance aux fautes des actionneurs pour un drone octorotor coaxial. Cette technique est basée sur une loi de commande robuste avec des gains reconfigurables "self tuning sliding mode control (STSMC)", où les gains de contrôle sont réajustés en fonction de l'erreur détectée afin de maintenir la stabilité du système. Des expériences à l'intérieur ont été menées pour montrer et comparer notre solution avec deux autres techniques de tolérances aux fautes. L'efficacité et le comportement de chaque méthode ont été étudiés après des injections de fautes successives dans les actionneurs. Les principaux avantages et inconvénients de chaque méthode sont déduits en analysant les résultats obtenus. En outre, nous proposons une approche pour la tolérance aux fautes des capteurs et mécanismes logiciels de fusion de données du drone. Cette approche est basée sur la redondance des capteurs et la diversification des composants logiciels.

The aim of this work is to propose mechanisms for multirotor drones that allow, on the one hand, to tolerate faults on the drone, and on the other hand to take into account the effects of the wind outdoors. The faults targeted include fault in actuators, sensors, but also software faults on the data fusion algorithms. ln our work, we have developed a robust controller and an exterior disturbance observer capable of cooperating with th, contrai reconfiguration method, to simultaneously tolerate motor failures and exterior wind disturbances through active fault tolerance techniques… We have also proposed a new technique for tolerating actuator faults for a coaxial octorotor drone. This technique is based on a robust command law with reconfigurable "self tuning sliding mode control (STSMC)" gains, where the control gains are readjusted according to the detected error in order to maintain the stability of the system. lndoor experiments are conducted to show and compare our solution with two other fault tolerance techniques. The efficiency and behavior of each method are studied after successive fault injections into the actuators. The main advantages and disadvantages of each method are deduced by analyzing the results obtained. Additionally, we provide an approach for fault tolerance of drone data fusion sensors and software mechanisms. This approach is based on the redundancy of sensors and the diversification of software components., Le but de ce travail est de proposer des mécanismes pour les drones multirotors qui permettent d'une part de tolérer des fautes sur le drone, et d'autre part de prendre en compte les effets du vent en extérieur. Les fautes visées comportent des fautes d'actionneurs, de capteurs, mais également des fautes logicielles sur les algorithmes de fusion de données. Dans nos travaux, nous avons développé un contrôleur robuste et un observateur des perturbations extérieures capables de coopérer avec la méthode de reconfiguration des commandes, pour tolérer de façon simultanée les défaillances de moteurs et les perturbations extérieures du vent par des techniques de tolérance aux fautes active. Egalement, nous avons proposé une nouvelle technique de tolérance aux fautes des actionneurs pour un drone octorotor coaxial. Cette technique est basée sur une loi de commande robuste avec des gains reconfigurables "self tuning sliding mode control (STSMC)", où les gains de contrôle sont réajustés en fonction de l'erreur détectée afin de maintenir la stabilité du système. Des expériences à l'intérieur ont été menées pour montrer et comparer notre solution avec deux autres techniques de tolérances aux fautes. L'efficacité et le comportement de chaque méthode ont été étudiés après des injections de fautes successives dans les actionneurs. Les principaux avantages et inconvénients de chaque méthode sont déduits en analysant les résultats obtenus. En outre, nous proposons une approche pour la tolérance aux fautes des capteurs et mécanismes logiciels de fusion de données du drone. Cette approche est basée sur la redondance des capteurs et la diversification des composants logiciels.

The file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link This work presents a novel intelligent system designed using a multi-agent hardware platform to detect improvised explosive devices concealed in the ground. Each agent is equipped with a different sensor, (i.e. a ground-penetrating radar, a thermal sensor and three cameras each covering a different spectrum) and processes dedicated AI decision-making capabilities. The proposed system has a unique hardware structure, with a distributed design and effective selection of sensors, and a novel multi-phase and cooperative decision-making framework. Agents operate independently via a customised logic adjusting their sensor positions - to achieve optimal acquisition; performing a preliminary “local decision-making” - to classify buried objects; sharing information with the other agents. Once sufficient information is shared by the agents, a collaborative behaviour emerges in the so-called “cooperative decision-making” process, which performs the final detection. In this paper, 120 variations of the proposed system, obtained by combining both classic aggregation operators as well as advanced neural and fuzzy systems, are presented, tested and evaluated. Results show a good detection accuracy and robustness to environmental and data sets changes, in particular when the cooperative decision-making is implemented with the neuroevolution paradigm.

This work proposes a novel semantic perception system based on computer vision and machine learning techniques. The main goal is to identify objects in the environment and extract their characteristics, allowing a dynamic interaction with the environment. The system is composed of a GPU processing source and a 3D vision sensor that provides RGB image and PointCloud data. The perception system is structured in three steps: Lexical Analysis, Syntax Analysis and finally an Analysis of Anticipation. The Lexical Analysis detects the actual position of the objects (or tokens) in the environment, through the combination of RGB image and PointCloud, surveying their characteristics. All information extracted from the tokens will be used to retrieve relevant features such as object velocity, acceleration and direction during the Syntax Analysis step. The anticipation step predicts future behaviors for these dynamic objects, promoting an interaction with them in terms of collisions, pull, and push actions. As a result, the proposed perception source can assign relevant information to mobile robots, not only about distances as traditional sensors, but about other environment characteristics and object behaviors. This novel perception source introduces a new class of skills to mobile robots. Experimental results obtained with a real robot are presented, showing the proposed perception source efficacy and potential.

This paper presents a systematic review of the perception systems and simulators for autonomous vehicles (AV). This work has been divided into three parts. In the first part, perception systems are categorized as environment perception systems and positioning estimation systems. The paper presents the physical fundamentals, principle functioning, and electromagnetic spectrum used to operate the most common sensors used in perception systems (ultrasonic, RADAR, LiDAR, cameras, IMU, GNSS, RTK, etc.). Furthermore, their strengths and weaknesses are shown, and the quantification of their features using spider charts will allow proper selection of different sensors depending on 11 features. In the second part, the main elements to be taken into account in the simulation of a perception system of an AV are presented. For this purpose, the paper describes simulators for model-based development, the main game engines that can be used for simulation, simulators from the robotics field, and lastly simulators used specifically for AV. Finally, the current state of regulations that are being applied in different countries around the world on issues concerning the implementation of autonomous vehicles is presented. This work was partially supported by DGT (ref. SPIP2017-02286) and GenoVision (ref. BFU2017-88300-C2-2-R) Spanish Government projects, and the “Research Programme for Groups of Scientific Excellence in the Region of Murcia" of the Seneca Foundation (Agency for Science and Technology in the Region of Murcia – 19895/GERM/15).

Mestrado em Engenharia de Automação Industrial The industrial automation has made its way in responding to the growing market’s needs. Companies that wish to keep up with the competition have a common goal: improve the product’s quality while reducing manufacturing costs and time. In the last decade, the autonomous guided vehicles (AGV) have gained expression due to the fact that they are capable of responding this the last mentioned necessity. The context of the current dissertation is inserted in the development of this thematic through the recovery of an equipment with industrial scale applications. The main goal is centered in the Robuter II platform’s retrofitting. For that, it is intended to replace the old control part by a modern solution that allows the integration of different modules based on a ROS distributed architecture. A detailed analysis of the existing platform was made in order to redo all the electrical installation, as well as to setup all of the used equipment. In the end, a vehicle capable of navigating, both manual and autonomously, was achieved. The vehicle can be operated manually (via remote control) and as a proof of concept, autonomous navigation was carried out through a simple artificial vision algorithm. It was also verified the versatility of the developed solution by integrating different equipment and designed code in a simple way. This document describes generally the project where all the different steps are identified, as well as all the work developed until the present moment. Furthermore, the guidelines to follow in order to achieve the proposed goals, is presented. Finally, navigation experimental results and the integration of different works on the platform are presented. A automação industrial é uma parte fundamental para responder às crescentes necessidades do mercado. As empresas que desejam estar a par da competição, têm todas uma premissa em comum — melhorar a qualidade do produto, reduzindo custos e tempo de fabrico. Na última década, os veículos autonomamente guiados (AGV) têm ganho expressão devido ao facto de serem capazes de responder a esta última necessidade. O contexto da presente dissertação insere-se no desenvolvimento desta temática através da recuperação de um equipamento com aplicações à escala industrial. O objetivo principal passa por fazer o retrofitting da plataforma Robuter II, que se encontra obsoleta. Para isso, pretende-se substituir toda a parte de controlo por uma solução mais atual que permita a integração de diferentes módulos com base numa arquitetura distribuída baseada em ROS. Foi então necessário proceder a uma análise detalhada da plataforma existente para refazer toda a instalação elétrica da mesma, bem como proceder à instalação de diversos equipamentos. No final, obteve-se um veículo capaz de navegar de forma manual (com controlo remoto) e foi ainda realizada uma prova de conceito de navegação autónoma através da realização de um algoritmo simples de visão artificial. Foi ainda verificada a versatilidade suficiente para integrar diferentes equipamentos e código desenvolvido de forma simples. Neste documento é feita uma descrição geral do projeto onde são identificadas as várias etapas do mesmo e o trabalho desenvolvido até ao momento. Para além disso, é apresentada a forma como se irá proceder para a implementação das metas propostas. Por último, são apresentados resultados experimentais de navegação e integração de outros trabalhos na plataforma.

Mestrado em Engenharia de Automação Industrial Submitted by Alexandra Bastos (alexandrabastos@ua.pt) on 2018-02-26T20:08:17Z No. of bitstreams: 1 Tese_Bruno Vieira.pdf: 11047955 bytes, checksum: 91c7fed0ee055655a78e76869e54e8c3 (MD5) Made available in DSpace on 2018-02-26T20:08:17Z (GMT). No. of bitstreams: 1 Tese_Bruno Vieira.pdf: 11047955 bytes, checksum: 91c7fed0ee055655a78e76869e54e8c3 (MD5) Previous issue date: 2017-07-21

International audience; In this paper, we introduce a novel computer vision-based perception system, dedicated to the autonomous navigation of visually impaired people. A first feature concerns the real-time detection and recognition of obstacles and moving objects present in potentially cluttered urban scenes. To this purpose, a motion-based, real-time object detection and classification method is proposed. The method requires no a priori information about the obstacle type, size, position or location. In order to enhance the navigation/positioning capabilities offered by traditional GPS-based approaches, which are often unreliably in urban environments, a building/landmark recognition approach is also proposed. Finally, for the specific case of indoor applications, the system has the possibility to learn a set of user-defined objects of interest. Here, multi-object identification and tracking is applied in order to guide the user to localize such objects of interest. The feedback is presented to user by audio warnings/alerts/indications. Bone conduction headphones are employed in order to allow visually impaired to hear the systems warnings without obstructing the sounds from the environment. At the hardware level, the system is totally integrated on an android smartphone which makes it easy to wear, non-invasive and low-cost

In this paper, we synthesized and evaluated the biological activity of structural analogues of natural strigolactones in which the butenolide D-ring has been replaced with a γ-lactam. The key step to obtain the α,β-unsaturated-γ-lactam was an RCM on suitably substituted amides. Strigolactones (SLs) are plant hormones with various developmental functions. As soil signaling chemicals, they are required for establishing beneficial mycorrhizal plant/fungus symbiosis. Beside these auxinic roles, recently SLs have been successfully investigated as antitumoral agents. Peculiar to the SL perception system is the enzymatic activity of the hormone receptor. SARs data have shown that the presence of the butenolide D-ring is crucial to retain the biological activity. The substitution of the butenolide with a lactam might shed light on the mechanism of perception. In the following, a dedicated in silico study suggested the binding modes of the synthesized compounds to the receptor of SLs in plants.

This paper deals with the problem of humanoid robot localization and proposes a new method for position estimation that has been developed for the RoboCup Standard Platform League environment. Firstly, a complete vision system has been implemented in the Nao robot platform that enables the detection of relevant field markers. The detection of field markers provides some estimation of distances for the current robot position. To reduce errors in these distance measurements, extrinsic and intrinsic camera calibration procedures have been developed and described. To validate the localization algorithm, experiments covering many of the typical situations that arise during RoboCup games have been developed: ranging from degradation in position estimation to total loss of position (due to falls, ‘kidnapped robot’, or penalization). The self-localization method developed is based on the classical particle filter algorithm. The main contribution of this work is a new particle selection strategy. Our approach reduces the CPU computing time required for each iteration and so eases the limited resource availability problem that is common in robot platforms such as Nao. The experimental results show the quality of the new algorithm in terms of localization and CPU time consumption., This work has been supported by the Spanish Science and Innovation Ministry (MICINN) under the CICYT project COBAMI: DPI2011-28507-C02-01/02. The responsibility for the content remains with the authors.

International audience; Using functional magnetic resonance imaging (fMRI) repetition suppression, we explored the selectivity of the human action perception system (APS), which consists of temporal, parietal and frontal areas, for the appearance and/or motion of the perceived agent. Participants watched body movements of a human (biological appearance and movement), a robot (mechanical appearance and movement) or an android (biological appearance, mechanical movement). With the exception of extrastriate body area, which showed more suppression for human like appearance, the APS was not selective for appearance or motion per se. Instead, distinctive responses were found to the mismatch between appearance and motion: whereas suppression effects for the human and robot were similar to each other, they were stronger for the android, notably in bilateral anterior intraparietal sulcus, a key node in the APS. These results could reflect increased prediction error as the brain negotiates an agent that appears human, but does not move biologically, and help explain the uncanny valley phenomenon.

International audience; —The existing R&D efforts for protecting vulnerable road users (VRU) are mainly based on perception techniques, which aim to detect VRUs utilizing vehicle embedded sensors. The efficiency of such a technique is largely affected by the sensor's visibility condition. Vehicle-to-Pedestrian (V2P) communication can also contribute to the VRU safety by allowing vehicles and pedestrians to exchange information. This solution is, however, largely affected by the reliability of the exchanged information, which most generally is the GPS data. Since perception and communication have complementary features, we can expect that a combination of such approaches can be a solution to the VRU safety. This is the motivation of the current work. We develop theoretical models to present the characteristics of perception and communications systems. Experimental studies are conducted to compare the performances of these techniques in real-world environments. Our results show that the perception system reliably detects pedestrians and other objects within 50 m of range in the line-of-sight (LOS) condition. In contrast, the V2P communication coverage is approximately 340 and 200 meters in LOS and non-LOS (NLOS) conditions, respectively. However, the communication-based system fails to correctly position the VRU w.r.t the vehicle, preventing the system from meeting the safety requirement. Finally, we propose a cooperative system that combines the outputs of the communication and perception systems.

For autonomous or semi-autonomous intelligent vehicles, perception constitutes the first fundamental task to be performed before decision and action/control. Through the analysis of video, Lidar and radar data, it provides a specific representation of the environment and of its state, by extracting key properties from sensor data with time integration of sensor information. Compared to other perception modalities such as GPS, inertial or range sensors (Lidar, radar, ultrasonic), the cameras offer the greatest amount of information. Thanks to their versatility, cameras allow intelligent systems to achieve both high-level contextual and low-level geometrical information about the observed scene, and this is at high speed and low cost. Furthermore, the passive sensing technology of cameras enables low energy consumption and facilitates small size system integration. The use of cameras is however, not trivial and poses a number of theoretical issues related to how this sensor perceives its environmen. In this thesis, we propose a vision-only system for moving object detection. Indeed,within natural and constrained environments observed by an intelligent vehicle, moving objects represent high risk collision obstacles, and have to be handled robustly. We approach the problem of detecting moving objects by first extracting the local contextusing a color-based road segmentation. After transforming the color image into illuminant invariant image, shadows as well as their negative influence on the detection process can be removed. Hence, according to the feature automatically selected onthe road, a region of interest (ROI), where the moving objects can appear with a high collision risk, is extracted. Within this area, the moving pixels are then identified usin ga plane+parallax approach. To this end, the potential moving and parallax pixels a redetected using a background subtraction method; then three different geometrical constraints : the epipolar constraint, the structural consistency constraint and the trifocaltensor are applied to such potential pixels to filter out parallax ones. Likelihood equations are also introduced to combine the constraints in a complementary and effectiveway. When stereo vision is available, the road segmentation and on-road obstacles detection can be refined by means of the disparity map with geometrical cues. Moreover, in this case, a robust tracking algorithm combining image and depth information has been proposed. If one of the two cameras fails, the system can therefore come back to a monocular operation mode, which is an important feature for perception system reliability and integrity. The different proposed algorithms have been tested on public images data set with anevaluation against state-of-the-art approaches and ground-truth data. The obtained results are promising and show that the proposed methods are effective and robust on the different traffic scenarios and can achieve reliable detections in ambiguous situations., Pour les véhicules intelligents autonomes ou semi-autonomes, la perception constitue la première tâche fondamentale à accomplir avant la décision et l’action. Grâce à l’analyse des données vidéo, Lidar et radar, elle fournit une représentation spécifique de l’environnement et de son état, à travers l’extraction de propriétés clés issues des données des capteurs. Comparé à d’autres modalités de perception telles que le GPS, les capteurs inertiels ou les capteurs de distance (Lidar, radar, ultrasons), les caméras offrent la plus grande quantité d’informations. Grâce à leur polyvalence, les caméras permettent aux systèmes intelligents d’extraire à la fois des informations contextuelles de haut niveau et de reconstruire des informations géométriques de la scène observée et ce, à haute vitesse et à faible coût. De plus, la technologie de détection passive des caméras permet une faible consommation d’énergie et facilite leur miniaturisation. L’utilisation des caméras n’est toutefois pas triviale et pose un certain nombre de questions théoriques liées à la façon dont ce capteur perçoit son environnement. Dans cette thèse, nous proposons un système de détection d’objets mobiles basé seule- ment sur l’analyse d’images. En effet, dans les environnements observés par un véhicule intelligent, les objets en mouvement représentent des obstacles avec un risque de collision élevé, et ils doivent être détectés de manière fiable et robuste. Nous abordons le problème de la détection d’objets mobiles à partir de l’extraction du contexte local reposant sur une segmentation de la route. Après transformation de l’image couleur en une image invariante à l’illumination, les ombres peuvent alors être supprimées réduisant ainsi leur influence négative sur la détection d’obstacles. Ainsi, à partir d’une sélection automatique de pixels appartenant à la route, une région d’intérêt où les objets en mouvement peuvent apparaître avec un risque de collision élevé, est extraite. Dans cette zone, les pixels appartenant à des objets mobiles sont ensuite identifiés à l’aide d’une approche plan+parallaxe. À cette fin, les pixels potentiellement mobiles et liés à l’effet de parallaxe sont détectés par une méthode de soustraction du fond de l’image; puis trois contraintes géométriques différentes: la contrainte épipolaire, la contrainte de cohérence structurelle et le tenseur trifocal, sont appliquées à ces pixels pour filtrer ceux issus de l’effet de parallaxe. Des équations de vraisemblance sont aussi proposées afin de combiner les différents contraintes d’une manière complémentaire et efficace. Lorsque la stéréovision est disponible, la segmentation de la route et la détection d’obstacles peuvent être affinées en utilisant une segmentation spécifique de la carte de disparité. De plus, dans ce cas, un algorithme de suivi robuste combinant les informations de l’image et la profondeur des pixels a été proposé. Ainsi, si l’une des deux caméras ne fonctionne plus, le système peut donc revenir dans un mode de fonctionnement monoculaire ce qui constitue une propriété importante pour la fiabilité et l’intégrité du système de perception. Les différents algorithmes proposés ont été testés sur des bases de données d’images publiques en réalisant une évaluation par rapport aux approches de l’état de l’art et en se comparant à des données de vérité terrain. Les résultats obtenus sont prometteurs et montrent que les méthodes proposées sont efficaces et robustes pour différents scénarios routiers et les détections s’avèrent fiables notamment dans des situations ambiguës.

International audience; Intelligent vehicles (IVs) need a perception system to model the surrounding environment. The Hybrid Sampling Bayesian Occupancy Filter (HSBOF) is a perception algorithm monitoring a grid-based model of the environment called " occupancy grid ". It is a highly data-parallel algorithm and requires a high computational performance to be executed in reasonable time. It is currently implemented in CUDA on a NVIDIA GPU. However, the GPU is power consuming and its purchase cost is too high for the embedded market. In this paper, we prove that, the couple embedded many-core/OpenCL is a feasible hardware/software architecture for replacing the GPU/CUDA. Our OpenCL implementation and experimental results on a testing hardware showed that a many-core can produce an occupancy grid every 168ms while consuming 40 times less power than the GPU. The results are promising for a future integration into IVs.

We present RoboSherlock, an open source software framework for implementing perception systems for robots performing human-scale everyday manipulation tasks. In RoboSherlock, perception and interpretation of realistic scenes is formulated as an unstructured information management (UIM) problem. The application of the UIM principle supports the implementation of perception systems that can answer task-relevant queries about objects in a scene, boost object recognition performance by combining the strengths of multiple perception algorithms, support knowledge-enabled reasoning about objects and enable automatic and knowledge-driven generation of processing pipelines. We demonstrate the potential of the proposed framework by three feasibility studies of systems for real-world scene perception that have been built on top of RoboSherlock.

This article describes the core algorithms of the perception system to be included within an autonomous underwater vehicle (AUV). This perception system is based on the acoustic data acquired from a side scan sonar (SSS). These data should be processed in an efficient time, so as to the perception system could detect and recognize a predefined target. This detection and recognition outcome is then an important piece of knowledge for the AUV's dynamic mission planner (DMP). Effectively, the DMP should propose different trajectories, navigation depths and other parameters that will change the robot's behavior, according to the perception system output. Hence, the time to make a decision is critical to assure safe robot operation and to acquire good quality data, and consequently the efficiency of the on-line image processing from acoustic data, is a key issue. Current techniques for acoustic data processing are time and computationally intensive. Hence, it was decided to process data coming from a SSS using a technique that is used for radars, due to its efficiency and its amenability to on-line processing. The engineering problem to solve in this case, is underwater pipeline tracking for routinely inspections in the off-shore industry. Then, an automatic oil pipeline detection system was developed borrowing techniques from processing of radar measurements. The radar technique is known as Cell Average-Constant False Alarm Rate (CA-CFAR). With a slight variation of the algorithms underlying this radar technique, consisting of the previous accumulation of partial sums, a great improvement in computing time and effort is achieved. Finally, a comparison with previous approaches over images acquired with a SSS from a vessel in the Salvador de Bahia bay in Brazil, showed the feasibility of using this on-board technique for AUV perception. Fil: Villar, Sebastian Aldo. Universidad Nacional del Centro de la Provincia de Bs.as.. Facultad de Ingenieria Olavarria. Departamento de Electromecanica. Grupo Intelymec; Argentina; Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina; Fil: Acosta, Gerardo Gabriel. Universidad de Las Islas Baleares. Departamento de Fisica; España; Universidad Nacional del Centro de la Provincia de Buenos Aires. Facultad de Ingenieria Olavarria. Departamento de Electromecanica. Grupo Intelymec; Argentina; Fil: Sousa, André L.. Universidad de Las Islas Baleares. Departamento de Fisica; España; Fil: Rozenfeld, Alejandro Fabian. Universidad de Las Islas Baleares. Departamento de Fisica; España; Universidad Nacional del Centro de la Provincia de Bs.as.. Facultad de Ingenieria Olavarria. Departamento de Electromecanica. Grupo Intelymec; Argentina

[Departement_IRSTEA]Ecotechnologies [TR1_IRSTEA]INSPIRE; In this paper, an algorithm dedicated to light ATVs, which estimates and anticipates the rollover, is proposed. It is based on the on-line estimation of the Lateral Load Transfer (LLT), allowing the evaluation of dynamic instabilities. The LLT is computed thanks to a dynamical model split into two 2D projections. Relying on this representation and a low cost perception system, an observer is proposed to estimate on-line the terrain properties (grip conditions and slope), then allowing to deduce accurately the risk of instability. Associated to a predictive control algorithm, based on the extrapolation of riders action, the risk can be anticipated, enabling to warn the pilot and to consider the implementation of active actions.