Control theory and engineering study how to produce the desired behavior in a variety of dynamical systems, e.g. the electro-mechanical systems in robots and the chemical systems in manufacturing plants. Such systems can be modeled mathematically in terms of state variables and how they change with respect to time and environmental conditions. The challenge is then to design the system component known as the controller such that the state variables change in desired and predictable ways. Our research in this area utilizes neural networks to implement controllers, and then optimizes those networks through learning and evolutionary algorithms. We have applied this approach to solve problems such as controlling the amount of thrust generated by rocket engines, regulating the complex biochemical processes in a bioreactor, and generating effective gaits for multilegged robots.