Dissertations / Theses on the topic 'Apprentissage pour la planification'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Apprentissage pour la planification.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Hren, Jean-François. "Planification optimiste pour systèmes déterministes." Thesis, Lille 1, 2012. http://www.theses.fr/2012LIL10188/document.
Full textIn the field of reinforcement learning, planning in the case of deterministic systems consists of doing a forward search using a generative model of the system so as to find the action to apply in its current state. In our case, the forward search leads us to build a look-ahead tree, its root being the current state of the system. If the computational resources are limited and unknown, we have to use an algorithm which tries to minimize its regret. In other words, an algorithm returning an action to apply which is as close as possible to the optimal one in term of quality and with respect to the computational resources used. We present the optimistic planing algorithm in the case of a discrete action space. We prove a lower and upper bound in the worst case and in a particular class of problems. Also we present two algorithms using the optimistic approach but in the case of a continuous action space
Padonou, Esperan. "Apprentissage Statistique en Domaine Circulaire Pour la Planification de Contrôles en Microélectronique." Thesis, Lyon, 2016. http://www.theses.fr/2016LYSEM009/document.
Full textDriven by industrial needs in microelectronics, this thesis is focused on probabilistic models for spatial data and Statistical Process Control. The spatial problem has the specificity of being defined on circular domains. It is addressed through a Kriging model where the deterministic part is made of orthogonal polynomials and the stochastic term represented by a Gaussian process. Defined with the Euclidean distance and the uniform measure over the disk, traditional Kriging models do not exploit knowledge on manufacturing processes. To take rotations or diffusions from the center into account, we introduce polar Gaussian processes over the disk. They embed radial and angular correlations in Kriging predictions, leading to significant improvements in the considered situations. Polar Gaussian processes are then interpreted via Sobol decomposition and generalized in higher dimensions. Different designs of experiments are developed for the proposed models. Among them, Latin cylinders reproduce in the space of polar coordinates the properties of Latin hypercubes. To model spatial and temporal data, Statistical Process Control is addressed by monitoring Kriging parameters, based on standard control charts. Furthermore, the monitored time – series contain outliers and structural changes, which cause bias in prediction and false alarms in risk management. These issues are simultaneously tackled with a robust and adaptive smoothing
Hérail, Philippe. "Apprentissage de Modèles Hiérarchiques par Démonstration pour la Planification et l'Action Délibérée." Electronic Thesis or Diss., Université de Toulouse (2023-....), 2024. http://www.theses.fr/2024TLSEI006.
Full textThe development of autonomous agents, especially embodied agents such as robots, requires complex architectures operating at different levels of abstractions. Given the complexity of real environments, hand-crafting all the models used at the different levels quickly becomes impractical. In recent years, there has been a growing body of work focusing on learning such models at the sensorimotor level, i.e. for perception and basic motor capabilities. However, thesame cannot be said for high-level models enabling deliberative functions.Among such high-level models, we will focus our attention on Hierarchical Task Networks (HTNs), which are a common planning formalism used in many practical applications, from video-games to robotic agents. Presently, designing HTN models remains a mostly manual task, which requires expertise both of the application domain and of the systems used for hierarchical planning. While some approaches do exist for learning HTNs, they suffer from some limitations, mainly in the structure of the domains that can be learned or in the required data annotation.In this thesis, we will propose a technique for learning HTNs with multiple hierarchy levels with minimal annotation work required. To this end, we will propose two main contributions: a procedure for learning HTN structures from demonstrations and one for learning their parameters from these demonstrations.The structure learning approach will leverage frequent pattern mining to detect interesting behavioural patterns to abstract in the demonstrations, which we couple with an existing goal regression algorithm. The quality of a given HTN structure during the search will be evaluated through a novel metric based on the Minimum Description Length (MDL) principle to use as an efficient proxy for planning performance.In addition, we propose a new method for identifying a sensible set of parameters for HTNs, relying on a MAX-SMT approach, which can be applied to most HTN models. Coupling our contributions for learning an HTN model structure and the identification of its parameters allows us to produces complete HTN models which we evaluate on standard benchmarks of the HTN planning community
Infantes, Guillaume. "Apprentissage de modèles de comportement pour le contrôle d'exécution et la planification robotique." Phd thesis, Université Paul Sabatier - Toulouse III, 2006. http://tel.archives-ouvertes.fr/tel-00129505.
Full textTremblet, David. "Apprentissage de contraintes pour améliorer la précision des modèles de planification et ordonnancement." Electronic Thesis or Diss., Ecole nationale supérieure Mines-Télécom Atlantique Bretagne Pays de la Loire, 2024. http://www.theses.fr/2024IMTA0417.
Full textManufacturing decisions often rely on mathematical models to suggest decisions to the managers in charge of production. For example, lot-sizing models are commonly used to plan factory production. The model calculates capacity usage for a plan with a rough approximation that does not account for all the complexities encountered on the shop floor. Although this approximation allows the model to be solved efficiently, the resulting decision usually leads to errors when the plan is executed on the shop floor. This thesis aims to use machine learning to improve the models traditionally used in operations research for manufacturing applications. The methodology aims to replace parts of the optimization models (constraints, objectives) with machine learning models (linear regression, neural networks, etc.) previously trained on available data. As a result, these tools can take advantage of the massive amount of data generated on the shop floor and external data sources to make better decisions. This approach is evaluated on a lot-sizing model where we learn capacity utilization constraints from the production schedule using machine learning models. The resulting model determines optimal production plans where production quantities remain feasible once sent to the shop floor. The resulting tool is also well adapted to today's production systems, which are increasingly reconfigurable and constantly evolving. The model can be retrained from shop floor data as changes occur on the shop floor, eliminating the need for an optimization expert to modify the optimization model each time the shop floor evolves
Castellanos-Paez, Sandra. "Apprentissage de routines pour la prise de décision séquentielle." Thesis, Université Grenoble Alpes (ComUE), 2019. http://www.theses.fr/2019GREAM043.
Full textIntuitively, a system capable of exploiting its past experiences should be able to achieve better performance. One way to build on past experiences is to learn macros (i.e. routines). They can then be used to improve the performance of the solving process of new problems. In automated planning, the challenge remains on developing powerful planning techniques capable of effectively explore the search space that grows exponentially. Learning macros from previously acquired knowledge has proven to be beneficial for improving a planner's performance. This thesis contributes mainly to the field of automated planning, and it is more specifically related to learning macros for classical planning. We focused on developing a domain-independent learning framework that identifies sequences of actions (even non-adjacent) from past solution plans and selects the most useful routines (i.e. macros), based on a priori evaluation, to enhance the planning domain.First, we studied the possibility of using sequential pattern mining for extracting frequent sequences of actions from past solution plans, and the link between the frequency of a macro and its utility. We found out that the frequency alone may not provide a consistent selection of useful macro-actions (i.e. sequences of actions with constant objects).Second, we discussed the problem of learning macro-operators (i.e. sequences of actions with variable objects) by using classic pattern mining algorithms in planning. Despite the efforts, we find ourselves in a dead-end with the selection process because the pattern mining filtering structures are not adapted to planning.Finally, we provided a novel approach called METEOR, which ensures to find the frequent sequences of operators from a set of plans without a loss of information about their characteristics. This framework was conceived for mining macro-operators from past solution plans, and for selecting the optimal set of macro-operators that maximises the node gain. It has proven to successfully mine macro-operators of different lengths for four different benchmarks domains and thanks to the selection phase, be able to deliver a positive impact on the search time without drastically decreasing the quality of the plans
Qiu, Danny. "Nouvelles méthodes d'apprentissage automatique pour la planification des réseaux mobiles." Electronic Thesis or Diss., Institut polytechnique de Paris, 2023. http://www.theses.fr/2023IPPAS010.
Full textMobile connectivity is an important driver of our societies, which is why mobile data consumption has continued to grow steadily worldwide. To avoid global congestion, mobile network operators are bound to evolve their networks.Mobile networks are strengthened through the deployment of new base stations and antennas. As this task is very expensive, a great attention is given to identifying cost-effective and competitive deployments.In this context, the objective of this thesis is to use machine learning to improve deployment decisions.The first part of the thesis is dedicated to developing machine learning models to assist in the deployment of base stations in new locations. Assuming that network knowledge for an uncovered area is unavailable, the models are trained solely on urban fabric features.At first, models were simply trained to estimate the class of major activity of a base station.Subsequently, this work was extended to predict the typical hourly profile of weekly traffic. Since the train time could be long, several methods for reducting mobile data have been studied.The second part of the thesis focuses on the deployment of new cells to increase the capacity of existing sites. For this purpose, a cell coverage model was developed by deriving the Voronoi diagram representing the coverage of base stations.The first study examined the spectrum refarming of former generations of mobile technology for the deployment of the newest generations.Models are trained to assist in prioritizing capacity additions on sectors that can benefit from the greatest improvement in resource availability.The second study examined the deployment of a new generation of mobile technology, considering two deployment strategies: driven by profitability or by the improvement of the quality of service.Therefore, the methods developed in this thesis offer ways to train models to predict the connectivity demand of a territory as well as its evolution. These models could be integrated into a geo-marketing tool, as well as providing useful information for network dimensioning
Grand, Maxence. "Apprentissage de Modèle d'Actions basé sur l'Induction Grammaticale Régulière pour la Planification en Intelligence Artificielle." Electronic Thesis or Diss., Université Grenoble Alpes, 2022. http://www.theses.fr/2022GRALM044.
Full textThe field of artificial intelligence aims to design and build autonomous agents able to perceive, learn and act without any human intervention to perform complex tasks. To perform complex tasks, the autonomous agent must plan the best possible actions and execute them. To do this, the autonomous agent needs an action model. An action model is a semantic representation of the actions it can execute. In an action model, an action is represented using (1) a precondition: the set of conditions that must be satisfied for the action to be executed and (2) the effects: the set of properties of the world that will be altered by the execution of the action. STRIPS planning is a classical method to design these action models. However, STRIPS action models are generally too restrictive to be used in real-world applications. There are other forms of action models: temporal action models allowing to represent actions that can be executed concurrently, HTN action models allowing to represent actions as tasks and subtasks, etc. These models are less restrictive, but the less restrictive the models are the more difficult they are to design. In this thesis, we are interested in approaches facilitating the acquisition of these action models based on machine learning techniques.In this thesis, we present AMLSI (Action Model Learning with State machine Interaction), an approach for action model learning based on Regular Grammatical Induction. First, we show that the AMLSI approach allows to learn (STRIPS) action models. We will show the different properties of the approach proving its efficiency: robustness, convergence, require few learning data, quality of the learned models. In a second step, we propose two extensions for temporal action model learning and HTN action model learning
Arora, Ankuj. "Apprentissage du modèle d'action pour une interaction socio-communicative des hommes-robots." Thesis, Université Grenoble Alpes (ComUE), 2017. http://www.theses.fr/2017GREAM081/document.
Full textDriven with the objective of rendering robots as socio-communicative, there has been a heightened interest towards researching techniques to endow robots with social skills and ``commonsense'' to render them acceptable. This social intelligence or ``commonsense'' of the robot is what eventually determines its social acceptability in the long run.Commonsense, however, is not that common. Robots can, thus, only learn to be acceptable with experience. However, teaching a humanoid the subtleties of a social interaction is not evident. Even a standard dialogue exchange integrates the widest possible panel of signs which intervene in the communication and are difficult to codify (synchronization between the expression of the body, the face, the tone of the voice, etc.). In such a scenario, learning the behavioral model of the robot is a promising approach. This learning can be performed with the help of AI techniques. This study tries to solve the problem of learning robot behavioral models in the Automated Planning and Scheduling (APS) paradigm of AI. In the domain of Automated Planning and Scheduling (APS), intelligent agents by virtue require an action model (blueprints of actions whose interleaved executions effectuates transitions of the system state) in order to plan and solve real world problems. During the course of this thesis, we introduce two new learning systems which facilitate the learning of action models, and extend the scope of these new systems to learn robot behavioral models. These techniques can be classified into the categories of non-optimal and optimal. Non-optimal techniques are more classical in the domain, have been worked upon for years, and are symbolic in nature. However, they have their share of quirks, resulting in a less-than-desired learning rate. The optimal techniques are pivoted on the recent advances in deep learning, in particular the Long Short Term Memory (LSTM) family of recurrent neural networks. These techniques are more cutting edge by virtue, and produce higher learning rates as well. This study brings into the limelight these two aforementioned techniques which are tested on AI benchmarks to evaluate their prowess. They are then applied to HRI traces to estimate the quality of the learnt robot behavioral model. This is in the interest of a long term objective to introduce behavioral autonomy in robots, such that they can communicate autonomously with humans without the need of ``wizard'' intervention
Cuperlier, Nicolas. "Apprentissage et prédiction de séquences sensori-motrices : architecture neuromimétique pour la navigation et la planification d'un robot mobile." Cergy-Pontoise, 2006. http://www.theses.fr/2006CERG0316.
Full textNavigation of an autonomous mobile robot in an unknown environment is a complex task that raises numerous issues in perception, categorisation, planning, and motor control. Solving all these problems in an integrated manner remains a challenge for roboticians. Thus, we propose a unified neuronal framework, based on the modeling of different parts of the mammalian brain’s functionalities: the hippocampus, the prefrontal cortex and the basal ganglia. Key topics are the multi-modal data integration like vision (the prevailing input), path integration, motivation, and also the inner and outer interactions between the structures. A first part of our work consists in modeling neural networks able to learn and predict sensory-motor combinations (transition cells) which are inputs of a cognitive map used to plan according to conflicting motivations. The cognitive map is learned without using any Cartesian coordinates nor occupancy grids. Already known transitions are used in exploration in order to preferentially explore unknown zones to reduce exploration time and enhance the completion of the cognitive map. Links of this map are learned or reinforced according to the behavior and enable to take into account dynamical changes of the environment. Exploration periods may be alternated with planning periods. The second part of this thesis brings an interesting solution for computing and selecting the final movement to perform. It also gives a stable motor control. Instead of using a (( Winner Takes All )) mechanism to select the movement, we increase the planned movement accuracy via a soft competition. Hence several movements are proposed and fed in another layer where the final motor command is obtained as the stable solution of a dynamical system: a one dimensional neural field coding for the heading direction. This field allows to endow the system with a final movement selection leading to a better movement generalization and consequently to a more reliable movement while planning. Our model gives a control architecture allowing to exhibit on a mobile robot navigation behaviors inspired from biology. This architecture can be considered as an attempt to explain underlying mechanisms implemented by mammals for these kind of behaviors. Furthermore, we can list the following benefits of our model: on-line localization, active exploration, planning and mapping in an uncompletely explored environment. These benifits cast an original light on the S. L. A. M problem (Simultaneous Localization and Map building of an unknown environment)
Chaouche, Ahmed Chawki. "Une approche multi-agent pour la conception de systèmes d'intelligence ambiante : un modèle formel intégrant planification et apprentissage." Thesis, Paris 6, 2015. http://www.theses.fr/2015PA066084/document.
Full textThis work presents a concrete software architecture dedicated to ambient intelligence (AmI) features and requirements. The proposed behavioral model, called Higher-order Agent (HoA) captures the evolution of the mental representation of the agent and the one of its plan simultaneously. Plan expressions are written and composed using a formal algebraic language, namely AgLOTOS, so that plans are built automatically and on the fly, as a system of concurrent processes. Due to the compositional structure of AgLOTOS expressions, the updates of sub-plans are realized automatically accordingly to the revising of intentions, hence maintaining the consistency of the agent. Based on a specific semantics, a guidance service is also proposed to assist the agent in its execution. This guidance allows to improve the satisfaction of the agent's intentions with respect to the possible concurrent plans and the current context of the agent. Adopting the idea that "location" and "time" are key stones information in the activity of the agent, we show how to enforce guidance by ordering the different possible plans. As a major contribution, we demonstrate two original utility functions that are designed from the past-experiences of the action executions, and that can be combined accordingly to the current balance policy of the agent. A use case scenario is developed to show how the agent can act, even if it suffers from unexpected changes of contexts, it does not have many experiences and whose past experiences reveals some failure cases
Chaouche, Ahmed Chawki. "Une approche multi-agent pour la conception de systèmes d'intelligence ambiante : un modèle formel intégrant planification et apprentissage." Electronic Thesis or Diss., Paris 6, 2015. http://www.theses.fr/2015PA066084.
Full textThis work presents a concrete software architecture dedicated to ambient intelligence (AmI) features and requirements. The proposed behavioral model, called Higher-order Agent (HoA) captures the evolution of the mental representation of the agent and the one of its plan simultaneously. Plan expressions are written and composed using a formal algebraic language, namely AgLOTOS, so that plans are built automatically and on the fly, as a system of concurrent processes. Due to the compositional structure of AgLOTOS expressions, the updates of sub-plans are realized automatically accordingly to the revising of intentions, hence maintaining the consistency of the agent. Based on a specific semantics, a guidance service is also proposed to assist the agent in its execution. This guidance allows to improve the satisfaction of the agent's intentions with respect to the possible concurrent plans and the current context of the agent. Adopting the idea that "location" and "time" are key stones information in the activity of the agent, we show how to enforce guidance by ordering the different possible plans. As a major contribution, we demonstrate two original utility functions that are designed from the past-experiences of the action executions, and that can be combined accordingly to the current balance policy of the agent. A use case scenario is developed to show how the agent can act, even if it suffers from unexpected changes of contexts, it does not have many experiences and whose past experiences reveals some failure cases
Mezine, Adel. "Conduite d'expériences par apprentissage actif pour l'identification de systèmes dynamiques biologiques : application à l'estimation de paramètres d'équations différentielles ordinaires." Thesis, Université Paris-Saclay (ComUE), 2016. http://www.theses.fr/2016SACLE030/document.
Full textContinuous progress in screening and high-throughput sequencing techniques in recent years paves the way for the identification of dynamic biological systems such as gene regulatory networks. However, the scarcity of the experimental data often leads to anuncertain estimation of parameters of interest. These uncertainties can be solved by generating new data in different experimental conditions, which induces additional costs. This thesis proposes a general active learning approach to develop tools of sequential experimental design for the identification of dynamical biological systems. The problem is formulated as a one-player game : the player has a budget dedicated for his experiments, each experiment has a different cost ; at every turn, he chooses one or more experiments to be performed on the system with the ultimate aim of maximizing the quality of the estimate, until the available budget is exhausted. The proposed approach called Experimental DEsign for Network inference (EDEN), is based on UCT (Upper Confident bounds for Trees) algorithm which combines Monte-Carlo tree search algorithms with multi-arm bandits to perform an effective exploration of the possible sequences of experiments. A strong point of the approach is anticipation : an experiment is selected at each round, knowing that this round will be followed by a number of other experiments, according to the available budget. This generic approach is rolled out in parameter estimation in nonlinear ordinary differential equations using partial observations. EDEN is applied on two problems : signaling network and gene regulatory network identification. Compared to the competitors, it exhibits very good results on a DREAM7 challenge where a limited budget and a wide range of experiments (perturbations, measurements) are available
Pessoa, Luís. "Méthodologie d'apprentissage interactif dirigeants / consultant pour la formulation et la mise en oeuvre de la stratégie." Lyon 3, 2007. https://scd-resnum.univ-lyon3.fr/out/theses/2007_out_pessoa_l.pdf.
Full textDeparting from a contributing principle for the growth of organisations efficacity and Efficiency (pratical purpose) we develloped a Strategic Reflexion Process containing a set of skills, a set of key-concepts and a working method that can guide organisation excutives and managers to build, themselves, a strategy and it's practical implementation, aiding them to work out a solution for their strategic problems. The "interactive learning methodology" that is presented is composed of interrelational processes, concepts, skills and working method, it is a praxeology, a thinking way for organisational collective action, renewed without end, forming an heuristic and powerfull instrument to knowledge, judgement and construction of strategy
Zaninotti, Marion. "Planification en ligne de la stratégie de navigation pour un drone autonome en environnement urbain." Electronic Thesis or Diss., Toulouse, ISAE, 2024. http://www.theses.fr/2024ESAE0063.
Full textUAVs can now be used for various applications, including service robotics, exploration and monitoring of environments, precision agriculture, as well as search and rescue missions. The need for autonomous navigation for UAVs is therefore becoming increasingly important. Many UAVs use GPS (Global Positioning System) for localization. However, in urban environments, the measured position can be inaccurate or even unavailable, which can compromise mission safety.In this context, the problem of efficient and safe navigation for an autonomous UAV, under uncertain GNSS availability, has been modeled as a POMDP (Partially Observable Markov Decision Process). Nevertheless, planning in such a complex model suffers from high computational cost and yields insufficient results under real-time constraints.Recently, research has focused on integrating offline learning to guide online planning. Inspired by the state-of-the-art CAMP (Context-specific Abstract Markov Decision Process) modeling, we propose a method that involves learning a constraint to be imposed during online planning for this problem. Imposing this constraint allows for an abstraction of the state space by restricting the UAV's navigation to a corridor within the environment.We then generalize this method to all SSP (Stochastic Shortest Path) problems with dead ends. The weight assigned to safety versus path efficiency is learned, a global path is planned based on this weight, and the constraint is derived from this global path. The resolution thus relies on a hybrid approach combining global path planning and online path planning.Afterward, we apply this generalized method to the FrozenLake problem, where an agent seeks a path across a frozen lake to reach a goal while avoiding holes, and to the initial UAV navigation problem. The results of all the experiments demonstrate that using such a method can improve the quality of solutions obtained through online planning, particularly for complex navigation environments and missions
Guillame-Bert, Mathieu. "Apprentissage de règles associatives temporelles pour les séquences temporelles de symboles." Thesis, Grenoble, 2012. http://www.theses.fr/2012GRENM081/document.
Full textThe learning of temporal patterns is a major challenge of Data mining. We introduce a temporal pattern model called Temporal Interval Tree Association Rules (Tita rules or Titar). This pattern model can be used to express both uncertainty and temporal inaccuracy of temporal events. Among other things, Tita rules can express the usual time point operators, synchronicity, order, and chaining,disjunctive time constraints, as well as temporal negation. Tita rules are designed to allow predictions with optimum temporal precision. Using this representation, we present the Titar learner algorithm that can be used to extract Tita rules from large datasets expressed as Symbolic Time Sequences. This algorithm based on entropy minimization, apriori pruning and statistical dependence analysis. We evaluate our technique on simulated and real world datasets. The problem of temporal planning with Tita rules is studied. We use Tita rules as world description models for a Planning and Scheduling task. We present an efficient temporal planning algorithm able to deal with uncertainty, temporal inaccuracy, discontinuous (or disjunctive) time constraints and predictable but imprecisely time located exogenous events. We evaluate our technique by joining a learning algorithm and our planning algorithm into a simple reactive cognitive architecture that we apply to control a robot in a virtual world
Guillame-bert, Mathieu. "Apprentissage de règles associatives temporelles pour les séquences temporelles de symboles." Phd thesis, Université de Grenoble, 2012. http://tel.archives-ouvertes.fr/tel-00849087.
Full textDefretin, Joseph. "Stratégies de vision active pour la reconnaissance d'objets." Phd thesis, École normale supérieure de Cachan - ENS Cachan, 2011. http://tel.archives-ouvertes.fr/tel-00696044.
Full textLeurent, Edouard. "Apprentissage par renforcement sûr et efficace pour la prise de décision comportementale en conduite autonome." Thesis, Lille 1, 2020. http://www.theses.fr/2020LIL1I049.
Full textIn this Ph.D. thesis, we study how autonomous vehicles can learn to act safely and avoid accidents, despite sharing the road with human drivers whose behaviors are uncertain. To explicitly account for this uncertainty, informed by online observations of the environment, we construct a high-confidence region over the system dynamics, which we propagate through time to bound the possible trajectories of nearby traffic. To ensure safety under such uncertainty, we resort to robust decision-making and act by always considering the worst-case outcomes. This approach guarantees that the performance reached during planning is at least achieved for the true system, and we show by end-to-end analysis that the overall sub-optimality is bounded. Tractability is preserved at all stages, by leveraging sample-efficient tree-based planning algorithms. Another contribution is motivated by the observation that this pessimistic approach tends to produce overly conservative behaviors: imagine you wish to overtake a vehicle, what certainty do you have that they will not change lane at the very last moment, causing an accident? Such reasoning makes it difficult for robots to drive amidst other drivers, merge into a highway, or cross an intersection — an issue colloquially known as the “freezing robot problem”. Thus, the presence of uncertainty induces a trade-off between two contradictory objectives: safety and efficiency. How to arbitrate this conflict? The question can be temporarily circumvented by reducing uncertainty as much as possible. For instance, we propose an attention-based neural network architecture that better accounts for interactions between traffic participants to improve predictions. But to actively embrace this trade-off, we draw on constrained decision-making to consider both the task completion and safety objectives independently. Rather than a unique driving policy, we train a whole continuum of behaviors, ranging from conservative to aggressive. This provides the system designer with a slider allowing them to adjust the level of risk assumed by the vehicle in real-time
Madi, wamba Gilles. "Combiner la programmation par contraintes et l’apprentissage machine pour construire un modèle éco-énergétique pour petits et moyens data centers." Thesis, Ecole nationale supérieure Mines-Télécom Atlantique Bretagne Pays de la Loire, 2017. http://www.theses.fr/2017IMTA0045/document.
Full textOver the last decade, cloud computing technologies have considerably grown, this translates into a surge in data center power consumption. The magnitude of the problem has motivated numerous research studies around static or dynamic solutions to reduce the overall energy consumption of a data center. The aim of this thesis is to integrate renewable energy sources into dynamic energy optimization models in a data center. For this we use constraint programming as well as machine learning techniques. First, we propose a global constraint for tasks intersection that takes into account a ressource with variable cost. Second, we propose two learning models for the prediction of the work load of a data center and for the generation of such curves. Finally, we formalize the green energy aware scheduling problem (GEASP) and propose a global model based on constraint programming as well as a search heuristic to solve it efficiently. The proposed model integrates the various aspects inherent to the dynamic planning problem in a data center : heterogeneous physical machines, various application types (i.e., ractive applications and batch applications), actions and energetic costs of turning ON/OFF physical machine, interrupting/resuming batch applications, CPU and RAM ressource consumption of applications, migration of tasks and energy costs related to the migrations, prediction of green energy availability, variable energy consumption of physical machines
Blanc, Bernard. "L'impact de l'instrumentation de gestion sur les activités : le cas du plan stratégique de patrimoine, un instrument producteur de sens pour les organismes du logement social." Paris 10, 2007. http://www.theses.fr/2007PA100014.
Full textThe analysis of the case of the design and the diffusion of a new artefact, the «Strategic Plan of Property» (PSP), enables us to highlight two great registers of transformation at work in the professional environment of the organizations of the social housing in France. On a first level of reading one observes a strategic project of transformation of the sector, initiated by the centers of being able which are the Directorate-General with Town planning with the Habitat and Construction and the Social Union for the Habitat aiming at passing from the administrative sector to the industrial sector via the PSP. On a second level of reading one observes that this transformation is made on the mode "top down" and that tool PSP plays a paramount part there. But it is a relative failure because the observation of the organizations shows a diversity of the practices. There is a decoupling between tool and practical. In the case of an organization like Silène, artefact PSP yields the place to instrument GPS (Project Management of Site). The tool plays a part of release, reference frame of direction, to make that the actors consider their activity and transforms it. By supporting us on the role of this tool, the PSP, in the construction of the direction of the activity in organizations HLM in France and more particularly in one of them, we can study a broader question which is the relation between the instrumentation of management and the transformation of the practices ? To widen this question we will examine some one of the theoretical executives available : theory of interpretation, theory of the structuring and sensemaking as well as the theory of the activity
Ndour, Cheikh. "Modélisation statistique de la mortalité maternelle et néonatale pour l'aide à la planification et à la gestion des services de santé en Afrique Sub-Saharienne." Phd thesis, Université de Pau et des Pays de l'Adour, 2014. http://tel.archives-ouvertes.fr/tel-00996996.
Full textAissani, Nassima. "Pilotage adaptatif et réactif pour un système de production à flux continu : application à un système de production pétrochimique." Phd thesis, Valenciennes, 2010. http://tel.archives-ouvertes.fr/tel-00553512.
Full textChoffin, Benoît. "Algorithmes d’espacement adaptatif de l’apprentissage pour l’optimisation de la maîtrise à long terme de composantes de connaissance." Electronic Thesis or Diss., université Paris-Saclay, 2021. http://www.theses.fr/2021UPASG001.
Full textBetween acquiring new knowledge and reviewing old knowledge to mitigate forgetting, learners may find it difficult to organize their learning time effectively. Adaptive spacing algorithms, like SuperMemo, can help learners deal with this trade-off. Such algorithms sequentially plan reviews of a given piece of knowledge to adapt to the specific and ongoing needs of each learner. Compared to a fixed and identical temporal spacing between reviews, several experiments have shown that adaptive spacing improves long-term memory retention of the piece of knowledge.To date, research on adaptive spacing algorithms has focused on the pure memorization of simple pieces of knowledge, which are often represented by flashcards. However, several studies in cognitive psychology have shown that the benefits of spacing out learning episodes on long-term retention also extend to more complex knowledge, such as learning concepts and procedures in mathematics. In this thesis, we have therefore sought to develop adaptive and personalized spacing algorithms for optimizing long-term mastery of knowledge components (KCs).First, we develop and present a new statistical model of learning and forgetting of knowledge components, coined DAS3H, and we empirically show that DAS3H has better predictive performance than several learner models in educational data mining. Second, we develop several adaptive spacing heuristics for long-term mastery of KCs and compare their performance on simulated data. Two of these heuristics use the DAS3H model to select which KC should be reviewed by a given learner at a given time. In addition, we propose a new greedy procedure to select the most promising subset of KCs instead of the best KC to review. Finally, in the last chapter of this thesis, we develop AC4S, a deep reinforcement learning algorithm for adaptive spacing for KCs. We compare this data-driven approach to the heuristic methods that we presented previously
Lelerre, Mathieu. "Processus Décisionnels de Markov pour l'autonomie ajustable et l'interaction hétérogène entre engins autonomes et pilotés." Thesis, Normandie, 2018. http://www.theses.fr/2018NORMC246/document.
Full textRobots will be more and more used in both civil and military fields. These robots, operating in fleet, can accompany soldiers in fight, or accomplish a mission while being supervised by a control center. Considering the requirement of a military operation, it is complicated to let robots decide their action without an operator agreement or watch, in function of the situation.In this thesis, we focus on two problematics:First, we try to exploit adjustable autonomy to make a robot accomplishes is mission as efficiency as possible, while he respects restrictions, assigned by an operator, on his autonomy level. For this, it is able to define for given sets of states and actions a restriction level. This restriction can force, for example, the need of being tele-operated to access a dangerous zone.Secondly, we consider that several robots can be deployed at the same time. These robots have to coordinate to accomplish their objectives. However, since operators can take the control of some robots, the coordination is harder. In fact, the operator has preferences, perception, hesitation, stress that are not modeled by the agent. It is then hard to estimate his next actions, so to coordinate with him. We propose in this thesis an approach to estimate the policy executed by a tele-operated robot from learning methods, based on observed actions from this robot.The notion of planning his important in these works. These are based on planning models, such as Markov Decision Processes
Allek, Fayssal. "Une approche pour les compétences fondamentales du développement d’une entreprise sur un nouveau marché : cas de compétences technologiques." Caen, 2010. http://www.theses.fr/2010CAEN0662.
Full textPonzoni, Carvalho Chanel Caroline. "Planification de perception et de mission en environnement incertain : Application à la détection et à la reconnaissance de cibles par un hélicoptère autonome." Thesis, Toulouse, ISAE, 2013. http://www.theses.fr/2013ESAE0011/document.
Full textMobile and aerial robots are faced to the need of planning actions with incomplete information about the state of theworld. In this context, this thesis proposes a modeling and resolution framework for perception and mission planningproblems where an autonomous helicopter must detect and recognize targets in an uncertain and partially observableenvironment. We founded our work on Partially Observable Markov Decision Processes (POMDPs), because it proposes ageneral optimization framework for perception and decision tasks under long-term horizon. A special attention is given tothe outputs of the image processing algorithm in order to model its uncertain behavior as a probabilistic observationfunction. A critical study on the POMDP model and its optimization criterion is also conducted. In order to respect safetyconstraints of aerial robots, we then propose an approach to properly handle action feasibility constraints in partiallyobservable domains: the AC-POMDP model, which distinguishes between the verification of environmental properties andthe information about targets' nature. Furthermore, we propose a framework to optimize and execute POMDP policies inparallel under time constraints. This framework is based on anticipated and probabilistic optimization of future executionstates of the system. Finally, we embedded this algorithmic framework on-board Onera's autonomous helicopters, andperformed real flight experiments for multi-target detection and recognition missions
Krichen, Omar. "Conception d'un système tutoriel intelligent orienté stylet pour l'apprentissage de la géométrie basé sur une interprétation à la volée de la production manuscrite de figures." Thesis, Rennes, INSA, 2020. http://www.theses.fr/2020ISAR0006.
Full textThis PhD is in the context of the « e-Fran » national project called ACTIF and deals with the design of the pen-based intelligent tutoring system IntuiGeo, for geometry learning in middle school. The contribution of this work are grouped into two axes.The first axis focused on the design of a recognition engine capable of on the fly interpretation of Han-drawn geometrical figures. It is based on a generic grammatical formalism, CD-CMG (Context Driven Constraints Multiset Grammar). The challenge being to manage the complexity of the real-time analysis process, the first contribution of this work consisted in extending the formalism, without losing its generic aspect. The second axis of this work addresses the tutorial aspect of our system.We define au author mode where the tutor is able to generate construction exercises from a solution example drawn by the teacher.The problem specific knowledge is represented by a knowledge graph. This representation enables the tutor to consider all possible resolution strategies, and to evaluate the pupil’s production in real-time. Furthermore, we define an expert module, based on a dynamic planning environment, capable of synthesizing resolution strategies. The tutoring system is able to generate guidance and corrective feedbacks that are adapted to the pupil’s resolution state. The results of our experiment conducted in class demonstrate the positive pedagogical impact of the system on the pupils performance, especially in terms of learning transferability between the digital and traditional support
Lacaze-Labadie, Rémi. "Planification et modèle graphique pour la génération dynamique de scénarios en environnements virtuels." Thesis, Compiègne, 2019. http://www.theses.fr/2019COMP2481/document.
Full textOur work is related to the training of crisis management in virtual environments. The specification of possible unfoldings of events in a simulation is essential for human learning in a virtual environment. This allows both to propose and orchestrate personalized learning situations and also to bring the learner toward relevant and educative scenarios. The work presented in this thesis focuses on the dynamic generation of scenarios and their execution in a virtual environment. For that, we aim at a set of objectives that are often contradictory : the freedom of action of the user, the generation of various scenarios that respect the authorial intent, the narrative control and the capacity of the system to adapt to deviations fromthe learner. The different approaches of interactive storytelling tackle more or less some of these objectives, but it is difficult to satisfy them all, and this is the challenge of our work. In addition to these objectives, we also aim at facilitating the modeling of the narrative content, which is still a real issue today when it comes to model complex environments such as the ones related to crisis management. We propose an emergent approachwhere the scenario experienced by the learner will emerge fromthe interactions between the learner, the virtual characters and our narrative system MENTA. MENTA is in charge of the narrative control by proposing a set of adjustments (over the simulation) that satisfies narrative objectives chosen by the trainer (e. g., a list of specific skills). These adjustments take the form of a prescribed scenario that is generated by MENTA via a planning engine that we have coupled with fuzzy cognitive maps through a macro-operator FRAG. A FRAG is used to model FRAGment of scenario in the form of scripted sequences of actions/events. The originality of our approach relies on a strong coupling between planning and graphical models which preserves the exploration capability and the generative power of a planning engine (which contributes to the generation of various and adaptable scenarios), while facilitating the modeling of narrative content as well as the authorial intent thanks to fragments of scenario that are scripted by the author and used during the planning process. We have worked on a concrete application example of scenarios dealing with the management of a massive influx of victims. Then, we have implemented MENTA and generated scenarios related to this example. Finally, we have tested and analyzed the performance of our system
Al, Samrout Marwa. "Approches mono et bi-objective pour l'optimisation intégrée des postes d'amarrage et des grues de quai dans les opérations de transbordement." Electronic Thesis or Diss., Normandie, 2024. http://www.theses.fr/2024NORMLH21.
Full textInternational maritime transport is vital for global trade, representing over 85% of exchanges, with 10.5 billion tons transported each year. This mode of transport is the most economical and sustainable, contributing only 2.6% of CO2 emissions. In France, the maritime sector accounts for 1.5% of GDP and nearly 525,000 jobs. Maritime ports, crucial for the logistics chain, facilitate the transshipment of goods and increasingly adopt digital solutions based on artificial intelligence to improve their efficiency. France has eleven major seaports, seven of which are located in mainland France.The thesis focuses on optimizing container terminals to enhance the efficiency and performance of ports. It addresses the issues of berth allocation planning and crane activation in container terminals in response to recent changes in maritime logistics, such as the arrival of mega-ships and automation. It highlights gaps in the existing literature and offers an in-depth analysis of current challenges. The document is divided into three chapters:The first chapter explores the history of containerization, types of containers, and challenges in operational planning. It focuses on the berth allocation problem (BAP), its resolution methods, and the integration of artificial intelligence (AI) to optimize logistical processes. The second chapter introduces the dynamic allocation problem with ship-to-ship transshipment. It proposes a mixed-integer linear program (MILP) to optimize the berthing schedule and transshipment between vessels. The objective is to reduce vessel stay times in the terminal, as well as penalties due to vessel delays, and to determine the necessary transshipment method. The method combines a packing-type heuristic and an improved genetic algorithm, demonstrating effectiveness in reducing vessel stay times. We conducted a statistical analysis to identify effective control parameters for the GA, then applied this algorithm with the determined control parameters to perform numerical experiments on randomly generated instances. Additionally, we conducted a comparative study to evaluate different crossover operators using ANOVA. We then presented a series of examples based on random data, solved using the CPLEX solver, to confirm the validity of the proposed model. The proposed method is capable of solving the problem in an acceptable computation time for medium and large instances. The final chapter presents an integrated berth and crane allocation problem, focusing on ship-to-ship transshipment. Three approaches are proposed. The first approach uses the NSGA-III genetic algorithm, supplemented by a statistical analysis to optimize parameters and evaluate different crossover operators. By analyzing AIS database data, numerical tests demonstrate the effectiveness of this method at the port of Le Havre, yielding satisfactory results within a reasonable computation time. The second approach involves two regression models, Gradient Boosting Regression (GBR) and Random Forest Regression (RFR), trained on selected features. The methodology includes preprocessing steps and hyperparameter optimization. While NSGA-III achieves the highest accuracy, it requires a longer execution time. In contrast, although GBR and RFR are slightly less precise, they significantly improve efficiency, highlighting the trade-off between accuracy and execution time in practical applications
Lesner, Boris. "Planification et apprentissage par renforcement avec modèles d'actions compacts." Caen, 2011. http://www.theses.fr/2011CAEN2074.
Full textWe study Markovian Decision Processes represented with Probabilistic STRIPS action models. A first part of our work is about solving those processes in a compact way. To that end we propose two algorithms. A first one based on propositional formula manipulation allows to obtain approximate solutions in tractable propositional fragments such as Horn and 2-CNF. The second algorithm solves exactly and efficiently problems represented in PPDDL using a new notion of extended value functions. The second part is about learning such action models. We propose different approaches to solve the problem of ambiguous observations occurring while learning. Firstly, a heuristic method based on Linear Programming gives good results in practice yet without theoretical guarantees. We next describe a learning algorithm in the ``Know What It Knows'' framework. This approach gives strong theoretical guarantees on the quality of the learned models as well on the sample complexity. These two approaches are then put into a Reinforcement Learning setting to allow an empirical evaluation of their respective performances
Hren, Jean-Francois. "Planification Optimiste pour Systèmes Déterministes." Phd thesis, Université des Sciences et Technologie de Lille - Lille I, 2012. http://tel.archives-ouvertes.fr/tel-00845898.
Full textLengagne, Sebastien. "Planification et re-planification de mouvements sûrs pour les robots humanoïdes." Phd thesis, Université Montpellier II - Sciences et Techniques du Languedoc, 2009. http://tel.archives-ouvertes.fr/tel-00431302.
Full textLengagne, Sébastien. "Planification et re-planification de mouvements sûrs pour les robots humanoïdes." Montpellier 2, 2009. http://www.theses.fr/2009MON20104.
Full textThese works deal with the computation of optimal motions for the humanoid robots. Most of the motion planning methods come from the motion planning of the manipulator robots. They rely on optimization algorithms which need a motion parametrization and a time-discretization of the constraints that define the physical limits of the robot. We show that a time-grid discretization is hazardous for the safety and the integrity of the robot. That is why, we propose a new method for the guaranteed discretization that computes the extrema of the constraints over time-interval that covers the whole motion duration. This method of discretization is time consuming. Thus, we developped a hybrid method that ensures the constraint validity within the same range of time of the state-of-the-art methods. With this method, we created a database of motions to follow a moving target. Consequently, we can generate an optimal motion that fits to the environment. However, there is no method which is fast enough to compute a new motion adapted to a new environment. Thus, we present a re-planning method that produces a new motion from a previous one. To do it, we compute, offline, a feasable sub-set around the motion that respects the constraint validity. The re-planning process consists in finding, in this sub-set, a new motion that is adapted to the new environment. We tested this re-planning method with a kicking motion where the position of the ball changes and we are able to find and adapted motion within 1. 5s of CPU-time
Dalibard, Sébastien. "Planification de mouvement pour systèmes anthropomorphes." Phd thesis, Institut National Polytechnique de Toulouse - INPT, 2011. http://tel.archives-ouvertes.fr/tel-00619439.
Full textMezouar, Youcef. "Planification de trajectoires pour l'asservissement visuel." Rennes 1, 2001. http://www.theses.fr/2001REN10138.
Full textRoussel, Olivier. "Planification de mouvement pour tiges élastiques." Thesis, Toulouse 3, 2015. http://www.theses.fr/2015TOU30355/document.
Full textThe motion planning problem has been broadly studied in the case of articulated rigid body systems but so far few work have considered deformable bodies. In particular, elastic rods such as electric cables, hydraulic or pneumatic hoses, appear in many industrial contexts. Due to complex models and high number of degrees of freedom, the extension of motion planning methods to such bodies is a difficult problem. By taking advantage of the properties of static equilibrium configurations, this thesis presents several approaches to the motion planning problem for elastic rods
Vu, Thanh Tung. "Modèles spatiaux pour la planification cellulaire." Thesis, Paris, ENST, 2012. http://www.theses.fr/2012ENST0043/document.
Full textNowadays, cellular technology is almost everywhere. It has had an explosive success over the last two decades and the volume of traffic will still increase in the near future. For this reason, it is also regarded as one cause of worldwide energy consumption, with high impact on carbon dioxide emission. On the other hand, new mathematical tools have enabled theconception of new models for cellular networks: one of these tools is stochastic geometry, or more particularly spatial Poisson point process. In the last decade, researchers have successfully used stochastic geometry to quantify outage probability, throughput or coverage of cellular networks by treating deployment of mobile stations or (and) base stations as Poisson point processes on a plane. These results also take into account to impact of mobility on the performance of such networks. In this thesis, we apply the theory of Poisson point process to solve some problems of cellular networks, in particular we analyze the energy consumption of cellular networks. This thesis has two main parts. The first part deals with some dimensioning and coverage problems in cellular network. We uses stochastic analysis to provide bounds for theoverload probability of OFDMA systems thanks to concentration inequalities and we apply it to solve a dimensioning problem. We also compute the outage probability and handover probability of a typical user. The second part is dedicated to introduce different models for energy consumption of cellular networks. In the first model, the initial location of users form a \PPP\ and each user is associated with an ON-OFF process of activity. In the second model, arrival of users forms a time-space \PPP. We also study the impact of mobility of users by assuming that users randomly move during its sojourn. We focus on the distribution of consumed energy by a base station. This consumed energy is divided into the additive part and the broadcast part. We obtain analytical expressions for the moments of the additive part as well as the mean and variance of the consumed energy. We are able to find an error bound for Gaussian approximation of the additive part. We prove that the mobility of users has a positive impact on the energy consumption. It does not increase or decrease the consumed energy in average but reduces its variance to zero in high mobility regime. We also characterize the convergent rate in function of user's speed
Vu, Thanh Tung. "Modèles spatiaux pour la planification cellulaire." Electronic Thesis or Diss., Paris, ENST, 2012. http://www.theses.fr/2012ENST0043.
Full textNowadays, cellular technology is almost everywhere. It has had an explosive success over the last two decades and the volume of traffic will still increase in the near future. For this reason, it is also regarded as one cause of worldwide energy consumption, with high impact on carbon dioxide emission. On the other hand, new mathematical tools have enabled theconception of new models for cellular networks: one of these tools is stochastic geometry, or more particularly spatial Poisson point process. In the last decade, researchers have successfully used stochastic geometry to quantify outage probability, throughput or coverage of cellular networks by treating deployment of mobile stations or (and) base stations as Poisson point processes on a plane. These results also take into account to impact of mobility on the performance of such networks. In this thesis, we apply the theory of Poisson point process to solve some problems of cellular networks, in particular we analyze the energy consumption of cellular networks. This thesis has two main parts. The first part deals with some dimensioning and coverage problems in cellular network. We uses stochastic analysis to provide bounds for theoverload probability of OFDMA systems thanks to concentration inequalities and we apply it to solve a dimensioning problem. We also compute the outage probability and handover probability of a typical user. The second part is dedicated to introduce different models for energy consumption of cellular networks. In the first model, the initial location of users form a \PPP\ and each user is associated with an ON-OFF process of activity. In the second model, arrival of users forms a time-space \PPP. We also study the impact of mobility of users by assuming that users randomly move during its sojourn. We focus on the distribution of consumed energy by a base station. This consumed energy is divided into the additive part and the broadcast part. We obtain analytical expressions for the moments of the additive part as well as the mean and variance of the consumed energy. We are able to find an error bound for Gaussian approximation of the additive part. We prove that the mobility of users has a positive impact on the energy consumption. It does not increase or decrease the consumed energy in average but reduces its variance to zero in high mobility regime. We also characterize the convergent rate in function of user's speed
Van, Grieken Milagros. "Optimisation pour l'apprentissage et apprentissage pour l'optimisation." Phd thesis, Université Paul Sabatier - Toulouse III, 2004. http://tel.archives-ouvertes.fr/tel-00010106.
Full textPasquier, Michel. "Planification de trajectoires pour un robot manipulateur." Phd thesis, Grenoble INPG, 1989. http://tel.archives-ouvertes.fr/tel-00334461.
Full textGaborit, Paul. "Planification distribuée pour la coopération multi-agents." Phd thesis, Université Paul Sabatier - Toulouse III, 1996. http://tel.archives-ouvertes.fr/tel-00142562.
Full textMaillot, Thibault. "Planification de trajectoire pour drones de combat." Phd thesis, Toulon, 2013. http://tel.archives-ouvertes.fr/tel-00954584.
Full textChamaret, Blaise. "Outils de planification pour les réseaux cellulaires." Saint-Etienne, 1999. http://www.theses.fr/1999STET4002.
Full textJauberthie, Carine. "Méthodologies de planification d'expériences pour systèmes dynamiques." Compiègne, 2002. http://www.theses.fr/2002COMP1434.
Full textBounab, Belkacem. "Planification de prises pour la manipulation robotisée." Toulouse 3, 2011. http://thesesups.ups-tlse.fr/1532/.
Full textThis thesis proposes a new approach for grasp analysis. Based on the theory of central axes of grasp wrench, we developed a new necessary and sufficient condition for n-finger grasps to achieve force-closure property. For n-finger planar grasps, we proposed a new graphical method for testing force-closure of arbitrary planar objects. The proposed geometric algorithm is very simple and requires low computational complexity. Thus, it can be used in real-time implementations and reduce significantly the computational cost compared to linear programming schemes. Further, based on friction-cone linearization, we formalized quantitative test of planar and spatial n-fingered force-closure grasps as a new linear programming problem. The proposed quantitative force-closure test offers a good metric of quality measurement without need to compute the convex hull of the primitive contact wrenches, which efficiently reduces the amount of computational time. Implementations were performed on ``Move3D'' and ``GraspIt'' simulation environments. For grasp synthesis, we formulated the computation of fingertips locations problem as an optimization problem under constraints. Furthermore, we presented an approach for finding appropriate stable grasps for a robotic hand on arbitrary objects. We used simulated annealing technique to synthesize suboptimal grasps of 3D objects. Through numerical simulations on arbitrary shaped objects, we showed that the proposed approach is able to compute good grasps for multifingered hands within reasonable computational time. The proposed grasp planner was implemented on ``GraspIt'' simulator
Pasquier, Michel Laugier Christian Fonlupt Jean. "Planification de trajectoires pour un robot manipulateur." S.l. : Université Grenoble 1, 2008. http://tel.archives-ouvertes.fr/tel-00334461.
Full textMenif, Alexandre. "Planification d'actions hiérarchique pour la simulation tactique." Thesis, Paris Sciences et Lettres (ComUE), 2017. http://www.theses.fr/2017PSLED004/document.
Full textThis thesis explores the application of HTN planning to the animation of an infantry platoon in a real-time simulation software. In order to achieve online planning for nearly 40 soldiers, we show that it is possible to optimize the planner for one HTN domain with a compilation of planning elements into C++ static structures and procedures. Then, we demonstrate that the problem structure lends itself to a combination of HTN planning with abstraction planning, achieved with the modelisation of abstract effects for compound tasks. In some conditions, we can detect those task networks that never lead to any executable solution, and therefore improve the search. Eventually, we show that the problem structure enables to formulate evaluation functions that can be input into a non admissible heuristic search algorithm, and that near optimal solutions can be obtained within a short run-time
Hima, Salim. "Planification de trajectoire pour des dirigeables autonomes." Evry-Val d'Essonne, 2005. http://www.theses.fr/2005EVRY0031.
Full textThe main work in this thesis deals with the problem of trajectory planning for autonomous airships. In the first part, we exposed a mathematical model governing the motion of the airships. The second part is devoted to characterization of admissible trajectories. The choice is made on the trim trajectories, which occupy a particular place in aviation applications. We proposed an algorithm that allows the calculation of the trim minimizing energy, suitable for long duration missions. The third part consists in formulating the problem of planning in a Hybrid Automata form named Motion automata. Its nodes are represented by trim trajectories, while its edges correspond to transitions maneuvres between trim’s. Analysing controllability of motion automaton is possible by exploiting the properties of trim trajectories. In this context, nominal trajectory is given by concatenating a finite number of primitives
Cros, Hervé. "Compilation et apprentissage dans les réseaux de contraintes." Montpellier 2, 2003. http://www.theses.fr/2003MON20171.
Full text