| Description |
viii, 42 leaves : illustrations ; 28 cm. |
| Summary |
"A differentially steered nonholonomic mobile robot platform has been fabricated to implement and validate nonlinear control laws. The platform can also be used to validate hierarchical cooperative control techniques. As a first step towards building a fleet of autonomous robots, novel control methods are developed and implemented on the robot platform for trajectory tracking as well as point stabilization. As an extension to the development of nonlinear controllers, a novel reinforcement learning based neural network is developed to control a manipulation task for a micro-electro-mechanical systems (MEMS). The nonlinear controllers developed for both the robot and the MEMS have online neural networks to compensate for the unknown nonlinear system dynamics"--Abstract, leaf iv. |
|
