Browsing by Subject "Robots--Control systems"
Now showing 1 - 5 of 5
Results Per Page
Sort Options
Item The constructivist learning architecture: a model of cognitive development for robust autonomous robots(2004) Chaput, Harold Henry; Kuipers, Benjamin; Miikkulainen, RistoAutonomous robots are used more and more in remote and inaccessible places where they cannot be easily repaired if damaged or improperly programmed. A system is needed that allows these robots to repair themselves by recovering gracefully from damage and adapting to unforeseen changes. Newborn infants employ such a system to adapt to a new and dynamic world by building a hierarchical representation of their environment. This model allows them to respond robustly to changes by falling back to an earlier stage of knowledge, rather than failing completely. A computational model that replicates these phenomena in infants would afford a mobile robot the same adaptability and robustness that infants have. This dissertation presents such a model, the Constructivist Learning Architecture (CLA), that builds a hierarchical knowledge base using a set of interconnected self-organizing learning modules. The dissertation then demonstrates that CLA (1) replicates current studies in infant cognitive development, (2) builds sensorimotor schemas for robot control, (3) learns a goal-directed task from delayed rewards, and (4) can fall back and recover gracefully from damage. CLA is a new approach to robot control that allows robots to recover from damage or adapt to unforeseen changes in the environment. CLA is also a new approach to cognitive modeling that can be used to better understand how people learn for their environment in infancy and adulthood.Item Geometric-based spatial path planning(2008-08) March, Peter Setterlund, 1978-; Tesar, DelbertCartesian 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.Item Multi-robot system control using artificial immune system(2007-12) Hur, Jaeho, 1965-; Fernández, Benito R.For the successful deployment of task-achieving multi-robot systems (MRS), the interactions must be coordinated among the robots within the MRS and between the robots and the task environment. There have been a number of impressive experimentally demonstrated coordinated MRS. However it is still of a premature stage for real world applications. This dissertation presents an MRS control scheme using Artificial Immune Systems (AIS). This methodology is firmly grounded in the biological sciences and provides robust performance for the intertwined entities involved in any task-achieving MRS. Based on its formal foundation, it provides a platform to characterize interesting relationships and dependencies among MRS task requirements, individual robot control, capabilities, and the resulting task performance. The work presented in this dissertation is a first of its kind wherein the principles of AIS have been used to model and organize the group behavior of the MRS. This has been presented in the form of a novel algorithm. In addition to the above, generic environments for computer simulation and real experiment have been realized to demonstrate the working of an MRS. These could potentially be used as a test bed to implement other algorithms onto the MRS. The experiment in this research is a bomb disposal task which involves a team of three heterogeneous robots with different sensors and actuators. And the algorithm has been tested practically through computer simulations.Item Optimally-robust nonlinear control of a class of robotic underwater vehicles(2006) Josserand, Timothy Matthew; Fernandez, Benito R.The subject of this dissertation is the optimally-robust nonlinear control of a class of robotic underwater vehicles (RUVs). The RUV class is characterized by high fineness ratios (length-to-diameter), axial symmetry, and passive roll stability. These vehicles are optimized for robotic applications needing power efficiency for long-range autonomous operations and motion stability for sensor performance improvement. A familiar example is the REMUS vehicle. The particular robot class is further identified by an inconsistent actuator arrangement where the number of inputs is fewer than the number of degrees of freedom, by the loss of controllability at low surge speeds due to the use of fin-based control actuation, and by an inherent heading instability. Therefore, this important type of RUV comprises an interesting and challenging class of systems to study from a control theoretic perspective. The optimally-robust nonlinear control method combines sliding mode control with stochastic state and model uncertainty estimation. First a regular form sliding mode control law is developed for the heading and depth control of the RUV class. The Particle Filter algorithm is then modified and applied to the particular case of estimating not only the RUV state for control feedback but also the functional uncertainty associated with partially modeled shallow water wave disturbances. The functional uncertainty estimate is used to dynamically adjust the sliding mode controller performance term gain according to the estimate of the wave phase and the RUV’s orientation with respect to the predominate wave direction. As a result, the RUV experiences increased performance over constant gain and Kalman Filter methods in terms of heading stability which increases effectiveness and decreased actuator power consumption which increases the RUV mission time. The proposed technique is general enough to be applied to other systems. An experimental RUV was designed and constructed to compare the performance of the regular form sliding mode controller with the conventional PID-type controller. It is demonstrated that the more complicated formulas of the regular form sliding mode controller can still be implemented real-time in an embedded system and that the controller’s performance with regard to modeling uncertainty justifies the added complexity.Item Reinforcement learning in high-diameter, continuous environments(2007) Provost, Jefferson, 1968-; Kuipers, BenjaminMany important real-world robotic tasks have high diameter, that is, their solution requires a large number of primitive actions by the robot. For example, they may require navigating to distant locations using primitive motor control commands. In addition, modern robots are endowed with rich, high-dimensional sensory systems, providing measurements of a continuous environment. Reinforcement learning (RL) has shown promise as a method for automatic learning of robot behavior, but current methods work best on lowdiameter, low-dimensional tasks. Because of this problem, the success of RL on real-world tasks still depends on human analysis of the robot, environment, and task to provide a useful set of perceptual features and an appropriate decomposition of the task into subtasks. This thesis presents Self-Organizing Distinctive-state Abstraction (SODA) as a solution to this problem. Using SODA a robot with little prior knowledge of its sensorimotor system, environment, and task can automatically reduce the effective diameter of its tasks. First it uses a self-organizing feature map to learn higher level perceptual features while exploring using primitive, local actions. Then, using the learned features as input, it learns a set of high-level actions that carry the robot between perceptually distinctive states in the environment. Experiments in two robot navigation environments demonstrate that SODA learns useful features and high-level actions, that using these new actions dramatically speeds up learning for high-diameter navigation tasks, and that the method scales to large (buildingsized) robot environments. These experiments demonstrate SODAs effectiveness as a generic learning agent for mobile robot navigation, pointing the way toward developmental robots that learn to understand themselves and their environments through experience in the world, reducing the need for human engineering for each new robotic application.