Modelling of control skill by qualitative constraints

Controlling a complex dynamic system, such as a plane or a crane, usually requires a skilled operator . Such a control skill is typically hard to reconstruct through introspection . Therefore an attractive approach to the reconstruction of control skill involves machine learning from operators' control traces, also known as behavioural cloning . In the most common approach to behavioural cloning, a controller is induced as a direct mapping from system states to actions . Unfortunately, such controllers usually lack typical elements of human control strategies, such as subgoals or desired trajectory, and do not replicate the robustness of the human control skill . In this paper we investigate a novel approach, whereby qualitative constraints are induced from an operator's control traces . These constraints define a qualitative control strategy a qualitative model of the operator's skill . Such a qualitative control strategy defines a family of controllers and provides a space for controller optimization . Using the crane problem in a case study, this approach showed significant improvements over traditional approaches to skill reconstruction, both in terms of control performance and transparency of induced clones .