Inverse Optimal Control from Incomplete Trajectory Observations

TL;DR

This paper introduces a novel method for learning the objective function of an optimal control system from incomplete trajectory data using a recovery matrix, enabling incremental learning of feature weights.

Contribution

It presents the recovery matrix concept and an incremental algorithm to learn feature weights from partial trajectory observations, improving data efficiency.

Findings

Effective on linear quadratic regulator systems

Successfully applied to a simulated robot manipulator

Allows incremental learning with minimal observations

Abstract

This article develops a methodology that enables learning an objective function of an optimal control system from incomplete trajectory observations. The objective function is assumed to be a weighted sum of features (or basis functions) with unknown weights, and the observed data is a segment of a trajectory of system states and inputs. The proposed technique introduces the concept of the recovery matrix to establish the relationship between any available segment of the trajectory and the weights of given candidate features. The rank of the recovery matrix indicates whether a subset of relevant features can be found among the candidate features and the corresponding weights can be learned from the segment data. The recovery matrix can be obtained iteratively and its rank non-decreasing property shows that additional observations may contribute to the objective learning. Based on the recovery matrix, a method for using incomplete trajectory observations to learn the weights of selected features is established, and an incremental inverse optimal control algorithm is developed by automatically finding the minimal required observation. The effectiveness of the proposed method is demonstrated on a linear quadratic regulator system and a simulated robot manipulator.