Adaptive Motion Planning for Complex Planning Problems

Motion planning has been used to solve problems of high complexity in both robotic and biological domains. In robotics, the topology of the planning environment often drives the problem’s complexity. Environments can consist of many different regions each of which may be well suited to a specific planning approach. In biological domains, problem complexity is primarily driven by the size of the moveable object. For example, small proteins have hundreds of degrees of freedom, medium proteins have thousands, and two proteins interacting can have even more. We present recent intelligent techniques applied to probabilistic roadmap methods (PRM) in order to efficiently and automatically solve complex motion planning problems. These techniques use automated methods to learn abut the problem space and then adapt based on the problem’s characteristics. We demonstrate the use of these automated methods in both robotics and protein folding applications.