Automatically composing and parameterizing skills by evolving Finite State Automata

We propose a robotics algorithm that is able to simultaneously combine, adapt and create actions to solve a task. The actions are combined in a Finite State Automaton whose structure is determined by a novel evolutionary algorithm. The actions parameters, or new actions, are evolved alongside the FSA topology. Actions can be combined together in a hierarchical fashion. This approach relies on skills that with which the robot is already provided, like grasping or motion planning. Therefore software reuse is an important advantage of our proposed approach. We conducted several experiments both in simulation and on a real mobile manipulator PR2 robot, where skills of increasing complexity are evolved. Our results show that (i) an FSA generated in simulation can be directly applied to a real robot without modifications and (ii) the evolved FSA is robust to the noise and the uncertainty arising from real-world sensors.

► A novel framework that simultaneously combines, adapts and creates robotics skills is proposed. Skills are represented as Finite State Automata.
► The new skills can be composed in a hierarchical fashion.
► A novel evolutionary algorithm to create Finite State Automata is proposed.
► The evolved automata are able to reliably control a real robot is a variety of scenarios.