On Convex Data-Driven Inverse Optimal Control for Nonlinear, Non-stationary and Stochastic Systems

TL;DR

This paper introduces a convex optimization-based method for inverse control that can reconstruct non-convex, non-stationary, and stochastic agent costs in nonlinear systems, validated through simulations and hardware tests.

Contribution

It presents a novel convex formulation for inverse control in complex nonlinear, non-stationary, and stochastic systems, enabling effective cost reconstruction.

Findings

Convex optimization approach successfully reconstructs agent costs.

Method effective in both simulated and hardware experiments.

Applicable to nonlinear, non-stationary, and stochastic dynamics.

Abstract

This paper is concerned with a finite-horizon inverse control problem, which has the goal of reconstructing, from observations, the possibly non-convex and non-stationary cost driving the actions of an agent. In this context, we present a result enabling cost reconstruction by solving an optimization problem that is convex even when the agent cost is not and when the underlying dynamics is nonlinear, non-stationary and stochastic. To obtain this result, we also study a finite-horizon forward control problem that has randomized policies as decision variables. We turn our findings into algorithmic procedures and show the effectiveness of our approach via in-silico and hardware validations. All experiments confirm the effectiveness of our approach.