The research developed in this PhD thesis deals with the general problem of dynamic control of ''task-oriented'' under-actuated and redundant systems considering more specifically the humanoid robotic systems. This research brings contributions to the problem of motor activities synthesis for constrained systems by their intrinsic capacities and by particular physical interactions with the environment. More specific issues that were addressed relate to: 1) the dynamic control of humanoid systems for carrying out basic activities requiring task/posture coordination perturbed by physical interactions, 2) the building of sequences of continuous dynamic activities based on a repertoire of motor coordination, 3) the planning and the adaptation of activities in the aim of a supervised automatic sequencing for complex non-deterministic tasks. The first chapter of this thesis is devoted to the description of a physical simulation engine and control laws for the development of dynamic behaviors. The second chapter provides a generic command based on the completion of several tasks under constraints. The third chapter develops an implementation of this controller on generic activities through the virtual model of the iCub robot. The fourth chapter develops a high-level controller to plan and adapt a sequence for the realization of more complex activities based on a predetermined repertoire of actions and monitoring their performance, while ensuring the control variables continuity.
