AbstractsComputer Science

Humanoid service robots promise a high adaptability to environments designed for humans due to their human-like body layout. They are thus well-suited to assist humans in domestic environments for everyday tasks or providing elderly care, but also to replace human workers in hazardous environments. The human-like structure allows versatile manipulation with two arms as well as stepping over or onto obstacles with bipedal locomotion. Compared to wheeled platforms, however, the kinematic structure of humanoids requires active balancing while walking and allows only a limited payload, e.g., for additional sensors. Inaccurate motion execution can lead to foot slippage and thus to a poor estimation of ego-motion. Furthermore, the high number of degrees of freedom make planning and control a challenging problem for humanoid robots. Autonomous navigation is a core capability of any service robot that performs high-level tasks involving mobility. Before a robot can fulfill a task, it needs to know where it is in the environment, what the environment looks like, and how it can successfully reach its goal. In this thesis, we present several novel contributions to the field of humanoid robotics with a focus on navigation in complex environments. We hereby cope with challenges in the areas of 3D environment representations, localization, perception, motion planning, and mobile manipulation. As a basis, we first introduce a memory-efficient 3D environment representation along with techniques for building three-dimensional maps. In this representation, our probabilistic localization approach estimates the 6D pose of the humanoid based on data of its noisy onboard sensors. We compare different range sensors as well as sensor and motion models. For the critical task of climbing stairs, we develop an improved particle filter that additionally integrates vision data for a highly accurate pose estimate. We also present methods to perceive staircases in 3D range data. For reaching a navigation goal with a humanoid robot, we introduce and compare different search-based footstep planning approaches with anytime capabilities. We then investigate planning for the whole body of the humanoid while considering constraints such as maintaining balance during a manipulation task. This enables the robot to pick up objects or open doors. Finally, we present an efficient approach for navigation in three-dimensional cluttered environments that is particularly suited for mobile manipulation. All techniques developed in this thesis were thoroughly evaluated both with real robots and in simulation. Our contributions generally advance the navigation capabilities of humanoid robots in complex indoor environments. Humanoide Serviceroboter versprechen durch ihren menschenähnlichen Körperbau eine hohe Anpassungsfähigkeit an Umgebungen die für den Menschen geschaffen wurden. Sie können dadurch im Haushalt zur Hand gehen, bei der Altenpflege behilflich sein, oder gar menschliche Arbeitskräfte in gefährlichen Umgebungen ersetzen. Der menschenähnliche…