**Êtes-vous un étudiant de l'EPFL à la recherche d'un projet de semestre?**

Travaillez avec nous sur des projets en science des données et en visualisation, et déployez votre projet sous forme d'application sur GraphSearch.

Publication# Distributed intelligent algorithms for robotic sensor networks monitoring discontinuous anisotropic environmental fields

Résumé

Robotic sensor networks, at the junction between distributed robotics and wireless sensor networks, represent a strategic convergence between mobile and networked systems. In this thesis, we have begun to explore this crossover, and where possible, to bring tools, experience, and insight from the field of robotics to bear in the field of sensor networks. We present here a formal and general framework for the classification and construction of distributed intelligent controllers to facilitate implementation, understanding, and analysis, including a complete parameterized system description, and its corresponding generalized performance metrics. The methods shown are capable of uniquely and unambiguously describing any mechanism for distributed control of a robotic sensor network engaged in a monitoring task. A variety of simple distributed intelligent algorithms are illustrated within this framework, which introduce methods for activity control in time, space, and mobility. Appropriate tools, equipment, and controlled testing environments for systematic experimentation have been designed and built, both for a physical system and for corresponding experimentally validated simulations. The general methods presented are intended neither as an exhaustive collection of possible controllers, nor as a replacement for application-specific solutions, but as a flexible, reusable roadmap for system design allowing a user to make educated design choices systematically and rigorously while encoding available information into the provided template, adapting the control model to the constraints of any given specific scenario, accounting for issues of data quality, measurement, communication, mobility, or any combination of the above.

Official source

Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.

Concepts associés

Chargement

Publications associées

Chargement

Concepts associés (14)

Robotique

thumb|upright=1.5|Nao, un robot humanoïde.
thumb|upright=1.5|Des robots industriels au travail dans une usine.
La robotique est l'ensemble des techniques permettant la conception et la réalisation de

Robot

vignette|Atlas (2013), robot androïde de Boston Dynamics
vignette|Bras manipulateurs dans un laboratoire (2009)
vignette|NAO (2006), robot humanoïde éducatif d'Aldebaran Robotics
vignette|DER1 (2005),

Réseau de capteurs sans fil

Un réseau de capteurs sans fil est un réseau ad hoc d'un grand nombre de nœuds, qui sont des micro-capteurs capables de recueillir et de transmettre des données d'une manière autonome. La position de

Publications associées (23)

Chargement

Chargement

Chargement

In the last decade, drones became frequently used to provide eye-in-the-sky overview in the outdoor environment. Their main advantage compared to the other types of robots is that they can fly above obstacles and rough terrains and they can quickly cover large areas. These properties also open a new application; drones could provide a multi-hop, line of sight communication for groups of ground users. The aim of this thesis is to develop a drone team that will establish wireless ad-hoc network between users on the ground and distributively adapt links and spatial arrangement to the requirements and motion of the ground users. For this application, we use fixed wing drones. Such platforms can be easily and quickly deployed. Fixed wing drones have higher forward speed and higher battery life than hovering platforms. On the other hand, fixed wing drones have unicycle dynamics with constrained forward speed which makes them unable to hover or perform sharp turns. The first challenge consists in bridging unicycle dynamics of the fixed wing drones. Some control strategies have been proposed and validated in simulations using the average distance between the target and the drone as a performance metric. However, besides the distance metric, energy expenditure of the flight also plays an important role in assessing the overall performance of the flight. We propose a new methodology that introduces a new metric (energy expenditure), we compare existing methods on a large set of target motion patterns and present a comparison between the simulation and field experiments on proposed target motion patterns. The second challenge consists in developing a formation control algorithm that will allow fixed wing robots to provide a wide area coverage and to relay data in a wireless ad-hoc network. In such applications fixed wing drones have to be able to regulate an inter-drone distance. Their reduced maneuverability presents the main challenge to design a formation algorithm that will regulate an inter-drone distance. To address this challenge, we present a distributed control strategy that relies only on local information. Each drone has its own virtual agent, it follows the virtual agent by performing previously evaluated and selected target tracking strategy, and flocking interaction rules are implemented between virtual agents. It is shown in simulation and in field experiments with a team of fixed wing drones that using this distributed formation algorithm, drones can cover an area by creating an equilateral triangular lattice and regulate communication link quality between neighboring drones. The third challenge consists in allowing connectivity between independently moving ground users using fixed wing drone team. We design two distributed control algorithms that change drones' spatial arrangement and interaction topology to maintain the connectivity. We propose a potential field based strategy which adapts distance between drones to shrink and expand the fixed wing drones' formation. In second approach, market-based adaptation, drones distributively delete interaction links to expand the formation graph to a tree graph. In simulations and field experiments we show that our proposed strategies successfully maintain independently moving ground users connected. Overall, this thesis presents synthesis of distributed algorithms for fixed wing drones to establish and maintain wireless ad-hoc communication networks.

Many robotics problems are formulated as optimization problems. However, most optimization solvers in robotics are locally optimal and the performance depends a lot on the initial guess. For challenging problems, the solver will often get stuck at poor local optima without a good initialization. In this thesis, we consider various techniques to provide a good initial guess to the solver based on previous experience. We use the term memory of motion to collectively refer to these techniques. The key idea is to use the existing system models, cost functions, and simulation tools to generate a database of solutions, and then construct a memory of motion model. During online execution, we can then query the initial guess of a given task from the memory of motion. We show that it improves the solver performance in terms of the solution quality, the success rates, and the computation time. We consider two different formulations, i.e., supervised learning and probability density estimation. In the first part, we formulate a regression problem to find the mapping between the task parameters and the solutions. Such a formulation is convenient, as there are a lot of function approximations available, but using them as a black box tool may result in poor predictions. It is especially the case for multimodal problems where there can be several different solutions for a given task and standard function approximators will simply average the different modes. We first propose an ensemble of function approximators that can handle multimodal problems to initialize an optimization-based motion planner. We then investigate the problem of initializing an optimal control solver for legged robot locomotion, where we need to also provide the initial guess of the control sequence. We evaluate the effect of different initialization components on the optimal control solver performance. In the second part, we consider another formulation by first transforming the cost function into an unnormalized Probability Density Function (PDF) and approximating it using various models. This formulation addresses several shortcomings of the supervised learning approaches by using the cost function itself to train or construct the predictive model. It allows us to generate initial guesses that have high probabilities of having low-cost values instead of simply imitating the dataset. We first show that we can obtain a trajectory distribution of an iLQR problem as a Gaussian distribution, and tracking this distribution results in a cost-efficient and robust controller. We then propose a generative adversarial framework to learn the distribution of robot configurations under constraints. Finally, we use tensor methods to approximate the unnormalized PDF. Since it does not rely on gradient information, the method is quite robust in finding the (possibly multiple) global optima or at least the good local optima of various challenging problems including some benchmark optimization functions, inverse kinematics, and motion planning.

This dissertation describes a complete methodological framework for designing, modeling and optimizing a specific class of distributed systems whose dynamics result from the multiple, stochastic interactions of their constitutive components. These components can be robots endowed with very minimal capabilities, or even simpler entities such as insects, bacteria, particles, or molecules. We refer to such components as Smart Minimal Particles (SMPs). One of the main difficulties facing the modeling of SMPs is the potential complexity and richness of their dynamics. On the one hand, one needs detailed models that account for the physico-chemical properties of the lower-level components (e.g., shape, material, surface chemistry, charge, etc.), which, in turn, determine the nature and the magnitude of their interactions. On the other hand, one is also interested in models that can yield accurate numerical predictions of macroscopic quantities, and investigate formally their dependence on the system’s design and control parameters. These competing requirements motivate a combination of models at multiple levels of abstraction, as advocated by the Multi-Level Modeling Methodology (MLMM), which was introduced in prior works. The MLMM enables the fulfillment of both requirements in a very efficient way by incrementally building up models at increasing levels of abstraction in order to capture the relevant features of the system. This thesis extends and consolidates the MLMM along several axes. In a first step, we provide a theoretical consolidation of the MLMM. We propose a thorough classification of the different models of SMPs, and we discuss their underlying assumptions and simplifications. We shed light on the fundamental impact of embodiment and spatiality on models’ accuracy, and we define the conditions under which the macro-deterministic approximation is valid. These theoretical considerations are experimentally supported by five case studies of aggregation and Self-Assembly (SA) at different scales. The five case studies utilize three types of components: (i) miniature wheeled robots (Alice, 2 cm in size) endowed with limited computation, sensing, actuation, and communication capabilities, (ii) water-floating passive modules (Lily, 3 cm in size) endowed with four permanent magnets for mutual latching, and (iii) micro-fabricated cylinders (about 100 μm in diameter, studied in realistic simulation only) that can achieve SA in liquids. In a second step, we introduce the core contribution of this thesis, that is, a systematic and generic methodology for bridging the gap between real, physical systems and computationally efficient models at multiple abstraction levels. In particular, we describe the M3 computational framework, which enables the automated construction of models of SMPs. Our approach consists in observing (or simulating realistically) a system of interest, and building a hierarchical suite of models based on the observations (i.e., trajectories) collected during these experiments (or simulations). Internally, the framework first builds up a microscopic representation of the system based on these observations and on a list of interactions of interest specified by the user. This representation, called the Canonical Microscopic Model (CMM), is a formal and generic description of SMPs, and it serves as a blueprint for the construction of a macroscopic model, specified using the Chemical Reaction Network (CRN) formalism. The rates of the CRN are finally calibrated using a Maximum Likelihood Estimation (MLE) scheme. We validate the M3 framework on each of the three platforms discussed earlier, thereby illustrating its relevance both as a modeling and as an analysis tool. Finally, we discuss the role of multi-level modeling when designing and optimizing SMPs. In particular, we show that top-down model-based design of multi-robot systems is generally not amenable to efficient implementations when dealing with very resource-constrained robots. Instead, faithful and computationally efficient models built incrementally from the bottom up prove to be an essential tool for designing such systems. We further corroborate this claim by applying our automated modeling framework to the real-time control of the stochastic SA of Lily modules. Our scientific contribution is therefore three-fold. First, we provide a solid experimental and theoretical consolidation of the MLMM, which has been the subject of intense research efforts for the last decade. Second, we propose, for the first time, an approach to generate models at high abstraction level in a completely automated fashion, based solely on observations of the system of interest. Third, we provide deep insights into the modeling and the design of SMPs, with a specific emphasis on self-assembling systems ranging from the centimeter scale down to the micrometer scale.