Dissertation--Duisburg-Essen--Universität Duisburg-Essen, 2007.

Reproduction de : Thèse de doctorat : Informatique : Toulouse, INPT : 2006. / Titre provenant de l'écran-titre. Bibliogr. 48 réf.

Reproduction de : Thèse de doctorat : Génie mécanique, productique, transport : Poitiers : 2008. Reproduction de : Tesis de doctorado : Ciencias en Ingeniería eléctrica : Instituto tecnologico de La Laguna (Torreon, Mexique) : 2008. / Texte en espagnol. Titre provenant de l'écran-titre. Bibliogr. 62 réf.

Autonomous mobile robots have the potential to be extremely beneficial to society due to their ability to perform tasks that are difficult or dangerous for humans. These robots will necessarily interact with their environment through the two fundamental processes of acting and sensing. Robots learn about the state of the world around them through their sensations, and they influence that state through their actions. However, in order to interact with their environment effectively, these robots must have accurate models of their sensors and actions: knowledge of what their sensations say about the state of the world and how their actions affect that state. A mobile robot’s action and sensor models are typically tuned manually, a brittle and laborious process. The robot’s actions and sensors may change either over time from wear or because of a novel environment’s terrain or lighting. It is therefore valuable for the robot to be able to autonomously learn these models. This dissertation presents a methodology that enables mobile robots to learn their action and sensor models starting without an accurate estimate of either model. This methodology is instantiated in three robotic scenarios. First, an algorithm is presented that enables an autonomous agent to learn its action and sensor models in a class of one-dimensional settings. Experimental tests are performed on a four-legged robot, the Sony Aibo ERS-7, walking forward and backward at different speeds while facing a fixed landmark. Second, a probabilistically motivated model learning algorithm is presented that operates on the same robot walking in two dimensions with arbitrary combinations of forward, sideways, and turning velocities. Finally, an algorithm is presented to learn the action and sensor models of a very different mobile robot, an autonomous car. / text

Cartesian space path planning involves generating the position and orientation trajectories for a manipulator end-effector. Currently, much of the literature in motion planning for robotics concentrates on topics such as obstacle avoidance, dynamic optimizations, or high-level task planning. The focus of this research is on operator-generated motions. This will involve analytically studying the effects of higher-order properties (such as curvature and torsion) on the shape of spatial Cartesian curves. A particular emphasis will be placed on developing physical meanings and graphical visualization for these properties to aid the operator in generating geometrically complex motions. This research begins with a brief introduction to the domain of robotics and manipulator motion planning. An overview of work in the area of manipulator motion planning will demonstrate a lack of research on generating geometrically complex spatial paths. To pursue this goal, this report will then provide a review of the theory of algrebraic curves and their higher-order properties. This involves an evaluation of several different representations for both planar and spatial curves. Then, a survey of interactive curve generation techniques will be performed, which will draw from fields outside of robotics such as Computer Graphics and Computer-Aided Design (CAD). In addition to the reviewed methods, a new method for describing and generating spatial curves is proposed and demonstrated. This method begins with the study of a finite set of local geometric motion shapes (circular arcs, cusps, helices, etc). The local geometric shapes are studied in terms of their geometric parameters (curvature and torsion), analyzed to give physical meaning to these parameters, and displayed graphically as a family of curves based on these controlling parameters. This leads to the development of path constraints with well-defined physical meaning. Then, a curve generation method is developed that can convert these geometric constraints into parametric constraints and blend between them to form a complete motion program (cycle) of smooth paths connecting several carefully developed local curve properties. Up to ten distinct local curve shapes were developed in detail and one curve cycle demonstrated how all this could be combined into a full path planning scenario. Finally, the developed methods are packaged together into existing software and applied to an example demonstration. / text

Not available / text

An autonomous navigational system for a mobile robot was developed based on a Laser-Range-Finder-based path planning and navigational algorithms. The system was enhanced by incorporating collision avoidance algorithms using data from a sonar sensor array, and further improved by establishing two virtual regions in front of the robot for obstacle detection and avoidance. Several virtual detector bands with varying dimensions were also added to the sides of the robot to check for rotational clearance safety and to determine the direction of rotation. The autonomous navigational system was tested extensively under indoor environment. Test results showed that the system performed satisfactorily in navigating the mobile robot in three structured mazes under indoor conditions. / An artificial landmark localization algorithm was also developed to continuously record the positions of the robot whilst it was moving. The algorithm was tested on a grid layout of 6 m x 6 m. The performance of the artificial landmark localization technique was compared with odometric and inertial measurements obtained using a dead-reckoning method and a gyroscope-corrected dead-reckoning method. The artificial landmark localization method resulted in much smaller root mean square error (0.033 m) of position estimates compared to the other two methods (0.175 m and 0.135 m respectively).

No description available.

No description available.

No description available.