An Iterative Method for Inverse Optimal Control

Zihao Liang, Wanxin Jin, Shaoshuai Mou

Abstract: This paper proposes an iterative method to solve inverse optimal control with data segments provided at every iteration. The unknown objective function is parameterized as a weighted sum of features with unknown weights. Each trajectory segment is a small snippet of optimal trajectory. The proposed method shows that each trajectory segment, if effective, can pose a linear constraint to the unknown weights, thus, the unknown weight vector is estimated by iteratively incorporating all informative segments. Effectiveness of the method is shown on a simulated 2-link robot arm and a 6-DoF maneuvering quadrotor system, in each of which only small demonstration segments are available.