Free-Gate: Planning, Control And Policy Composition via Free Energy Gating

TL;DR

This paper introduces Free-Gate, a novel control framework that combines primitives using free energy minimization, enabling effective planning and control in complex, nonlinear, and stochastic environments.

Contribution

We propose a convex formulation for policy composition via free energy gating, applicable to nonlinear and stochastic control tasks, with an efficient algorithm for optimal primitive combination.

Findings

Effective in robot navigation with obstacle avoidance

Enables composition of simple primitives for complex tasks

Demonstrates convexity in a non-convex control setting

Abstract

We consider the problem of optimally composing a set of primitives to tackle planning and control tasks. To address this problem, we introduce a free energy computational model for planning and control via policy composition: Free-Gate. Within Free-Gate, control primitives are combined via a gating mechanism that minimizes variational free energy. This composition problem is formulated as a finite-horizon optimal control problem, which we prove remains convex even when the cost is not convex in states/actions and the environment is nonlinear, stochastic and non-stationary. We develop an algorithm that computes the optimal primitives composition and demonstrate its effectiveness via in-silico and hardware experiments on an application involving robot navigation in an environment with obstacles. The experiments highlight that Free-Gate enables the robot to navigate to the destination despite only having available simple motor primitives that, individually, could not fulfill the task.