The problem of performing complex maneuvers in challenging terrains is crucial to the advancement of legged robots and assistive devices, yet little progress has been made in exploring practical solutions to operate in these environments. In this thesis, we tackle the problem by developing strategies to predict a robot's center of mass (CoM) behavior based on contact constraints, and any arbitrary CoM path for situations in which the system has single or multiple points of contact through which external reaction forces may be applied. Our method consists of first leveraging previous work on multi-contact dynamics to derive reaction force behavior from internal tension force profiles and kinematic CoM trajectories. We then study the nonlinear dynamics of single contact phases along arbitrary paths and employ numerical integration to derive state-space approximations of CoM behavior. We use this theoretical framework to synthesize complex maneuvers in various terrains by means of a motion planner in which we determine step transition sequences for continuous motions involving contact profiles which vary with time. Furthermore, we validate our strategy through several comparative case studies, examining the motion of a human subject performing a difficult maneuver in an aggressive terrain. We then seed our motion planning algorithm with a limited set of parameters chosen to match those of a human subject and predict CoM behavior for the same motion pattern. These case studies show that the estimated CoM behaviors generated from our planning algorithm closely resemble the behavior of the human subject and therefore validate our methods. / text

Pour les robots marcheurs, c'est à dire bipèdes, quadrupèdes, hexapodes, etc... la notion de stabilité est primordiale. En effet, ces robots possèdent une base flottante sous-actuée : il leur faut prendre appui sur l'environnement pour se mouvoir. Toutefois, cette caractéristique les rend vulnérables: ils peuvent tomber. Il est donc indispensable de pouvoir différencier un mouvement stable d'un mouvement non-stable. Dans cette thèse, la stabilité est considérée du point de vue d'un modèle réduit au Centre de Masse (ou Centre de Gravité). Nous montrons dans un premier temps comment calculer la zone de stabilité de ce modèle dans le cas statique. Bien que cette région soit un objet purement géométrique, nous montrons qu'elle dépend des forces de contact admissibles. Ensuite, nous montrons qu'introduire la notion de robustesse, c'est à dire une marge d'incertitude sur les accélérations (ou les forces de contacts) transforme la forme plane du cas statique en un volume tridimensionnel. Afin de calculer cette forme, nous présentons de nouveaux algorithmes récursifs. Nous appliquons ensuite des algorithmes provenant de l'infographie qui permettent de déformer continûment ces objets géométriques. Cette transformation nous permet d'approximer des changements dans les variables influençant ces formes. Calculer le volume de stabilité explicitement nous permet de découpler les accélérations des positions du CdM, ce qui nous permet de formuler un problème de contrôle prédictif linéaire. Nous proposons aussi une autre formulation linéaire qui, au prix de calculs plus coûteux, permet d'exploiter pleinement la dynamique du robot. Enfin, nous appliquons ces résultats dans une approche hiérarchique qui nous permet de générer des mouvements du corps complet du robot, aussi bien sur une véritable plateforme humanoïde qu'en simulation. / In the context of legged robotics, stability (or equilibrium) is of the utmost importance. Indeed, as legged robots have a non-actuated floating base they can fall. To avoid falling, we must be able to tell apart stable from non-stable motion. This thesis approaches stability from a reduced model point-of-view: our main interest is the Center of Mass. We show how to compute stability regions for this reduced model, at first based on purely static stability. Although purely geometrical in nature, we show how they depend on the admissible contact forces. Then, we show that taking into account robustness, in the sense of acceleration (or contact forces) affordances transforms the usual two-dimensional stability region into a three dimensional one. To compute this shape, we introduce novel recursive algorithms. We show how we can apply computer graphics techniques for shape morphing in order to continuously deform the aforementioned regions. This allows us to approximate changes in the parameters of those shapes, but also to interpolate between shapes. Finally, we exploit the effective decoupling offered by the explicit computation of the stability polyhedron to formulate a linear, minimal jerk model-predictive control problem. We also propose another linear MPC problem that exploits more of the available dynamics, but at an increased computational cost. We then adopt a hierarchical approach, and use those CoM results as input to our whole-body controller. Results are demonstrated on real hardware and in simulation.

Cette thèse propose une approche pour générer un mouvement corps complet avec contacts non coplanaires, permettant à un robot de se déplacer dans un environnement, de manipuler des objets complexes ou de collaborer avec différents agents. Les méthodes développées dans cette thèse tentent de prendre en compte une grande variété de robots, de l'humanoïde au manipulateur à base fixe en passant par les objets sous actionnés. En premier lieu, nous abordons le problème du choix des positions des points de contacts qu'un robot sous-actionné doit prendre pour se déplacer dans l'environnement. Nous calculons, en un seul problème d'optimisation non-linéaire, une séquence de postures qui satisfait une séquence de contacts donnés. Cette formulation permet de trouver la position des contacts optimale, car le choix de la position d'un contact d'une posture va prendre en compte les postures précédentes et suivantes. Elle permet aussi d'effectuer des tâches pour certaines postures qui prendront en compte l'aspect prioritaire du déplacement. Nous introduisons ensuite une méthode de génération de mouvement qui, en se basant sur la programmation quadratique, permet de résoudre le problème de géométrie inverse et de la dynamique inverse pour un robot à base fixe ou mobile, tout en satisfaisant des contraintes d'égalités et d'inégalités.Cette génération de mouvement est assez rapide pour fonctionner à la vitesse de la boucle de contrôle des robotsHRP2-10 et HRP4, et peut donc être utilisé en temps réel. À l'aide d'une machine à état, nous transformons la séquence de postures calculée à priori en une série de tâches à effectuer par le générateur de mouvement, ce qui permet à notre robot de se déplacer dans un environnement complexe. Nous étendons alors notre méthode de génération de mouvement pour calculer la commande d'un nombre arbitraire de robots. Cette extension nous permet de gérer des tâches de manipulation d'objets complexes, de collaboration entre plusieurs agents et de mouvement dans un environnement dynamique. Nous pouvons aussi spécifier directement les tâches dans le repère de l'objet manipulé pour faciliter l'élaboration de notre consigne. Dans l'optique de valider cette méthode sur un robot réel, nous formulons le problème d'estimation des paramètres inertiels d'un objet manipulé grâce à l'algèbre vectorielle spatiale. Finalement, nous validons nos travaux sur les robots HRP2-10 et HRP4. Sur le premier robot, nous validons la génération de posture et la génération de mouvement mono-robot sur le scénario demonté d'une échelle verticale aux normes industrielles. La manipulation d'objets et l'estimation des paramètres inertiels sont validées par la suite sur le robot HRP4. / This PhD proposes a whole body motion generation approach with non coplanar contacts that allowsa robot to move in an environment, manipulate complex objects or collaborate with differentagents.Methods developed in this PhD try to manage many kinds of robots, from the humanoid to thefixed base manipulator and also handling underactuated objects.Firstly, we address the problem contacts positioning that an underactuated robot should taketo move in its environment.We compute in one non-linear optimization problem a sequence of postures that fulfill aninputed contact list. This formulation allows to find the optimal contact placement regardingprevious and next stances. It also allows to execute a task for some posture while taking into accountthe priority of the motion.Next, we introduce a motion generation method that uses quadratic programming to solveinverse kinematics and dynamics problems for a fixed or mobile base robot under equality andinequality constraints.This motion generation is fast enough to fit the HRP2-10 and HRP4 control loop andcan be used in real-time.With a finite state machine we turn the posture sequence into a list of tasks that should beexecuted by the motion generation to allow a robot to move in a complex environment.We extend this motion generation scheme to compute the motion of an arbitrary number of robots.This extension allows us to manage complex object manipulation tasks, multi-agent collaboration andmotion in a dynamic environment. We can also specify a task in the manipulated object frameto ease motion design.To validate this method on a real robot, we formulate inertial parametersestimation of manipulated objects with spatial vector algebra.Finally, we validate our works on the HRP2-10 and HRP4 robot. On the first one,we validate the posture and mono-robot motion generation on a scenario where the robot climbs anindustry standard vertical ladder.On the second one, we validate object manipulation and inertial parameters estimation.

Electrical connectors are the blocks that connect solar panels together. Whenever a photovoltaic plant commences, the main discussion goes around on solar panels, inverters, charge controllers, etc. But the topic of connectors is usually hardly discussed. Connectors in a photovoltaic system can definitely contribute to improve the overall performance of the system, provided that importance is given while selecting the connectors. The electrical connectors used in photovoltaic systems can be connected in two possible ways. Connectors can be connected either in a pure-connection or in a cross-connection. Male and female connectors from the same brand results a pure-connection (P-C). Male and female connectors from two different brands results in a cross-connection (C-C). There have been discussions in photovoltaic, electrical connector markets and international solar events regarding the risks involved, losses and consequences due to a cross-connection. The main reason behind cross-connections is the unawareness of the installers in knowing the difference between a pure-connection and a cross-connection. Even though the installers are aware of this difference, they are not aware of the consequences of cross-connections. Multi-Contact, a leading electrical connector manufacturer of MC4 photovoltaic connectors affected by the counterfeit products of MC4, due to the sudden boom in the solar market during 2011-12. With the help of TÜV Rheinland, Multi-Contact conducted couple of tests namely temperature increase test and accelerated stress tests to understand the disadvantages of cross-connections. This thesis tried to replicate the tests performed by Multi-Contact in an attempt to understand the test results by using connectors that are used in the Swedish market. Performing temperature increase test and accelerated stress tests on most commonly used connectors in the Swedish market is the main aim of this thesis. The first test, gives an understanding of the temperature variations across various connector sets (four connector sets from various manufacturers used in this thesis) and the latter tests helps to understand the quality of the contact resistance of these connector sets. The four connector set manufacturers used in this test were Multi-Contact (MC), Weidmüller (WM), Blussun solar (BSS) and PBM. The quality of contact resistance of a connector is directly related to the quality of the connector set. During the 20 minutes of the temperature increase test, the connector set from WM performed better than its competitors in the P-C. Whereas, the MC-BSS connector set had performed well in the C-C. The connector type of male MC and female BSS showed its dominance throughout the test. Unfortunately, no conclusions were able to be drawn from this test results due to insufficient information about the test procedure. From the results of accelerated stress tests, the C-C set from MC outperformed its P-C counterpart. All ten connector sets used in this project passed the standard and qualified as connectors with good quality contact resistance. Therefore the best results out of only a P-C connector set does not seems to be completely true. With the standard used in this thesis, it is quite difficult to judge the quality of connectors. Rather than saying a P-C is superior and a C-C is inferior in terms of quality, there is a need to come up with a new method to evaluate the quality of connectors. Matching the connectors based on their tolerances could be a potential solution to the mismatching problem in connectors.