Constraint Learning for Control Tasks with Limited Duration Barrier Functions

TL;DR

This paper introduces a constraint-learning framework for control tasks focusing on limited-duration safety, enabling autonomous agents to maintain safety over finite horizons and transfer policies across tasks.

Contribution

It proposes a novel approach to safety constraints over finite horizons and demonstrates its effectiveness in robotic coverage, charging, and control policy transfer.

Findings

Limited-duration safe policies can ensure long-term autonomy.

Constraints naturally induce behaviors like battery charging.

Control policies can be transferred between related tasks.

Abstract

When deploying autonomous agents in unstructured environments over sustained periods of time, adaptability and robustness oftentimes outweigh optimality as a primary consideration. In other words, safety and survivability constraints play a key role and in this paper, we present a novel, constraint-learning framework for control tasks built on the idea of constraints-driven control. However, since control policies that keep a dynamical agent within state constraints over infinite horizons are not always available, this work instead considers constraints that can be satisfied over some finite time horizon T > 0, which we refer to as limited-duration safety. Consequently, value function learning can be used as a tool to help us find limited-duration safe policies. We show that, in some applications, the existence of limited-duration safe policies is actually sufficient for long-duration autonomy. This idea is illustrated on a swarm of simulated robots that are tasked with covering a given area, but that sporadically need to abandon this task to charge batteries. We show how the battery-charging behavior naturally emerges as a result of the constraints. Additionally, using a cart-pole simulation environment, we show how a control policy can be efficiently transferred from the source task, balancing the pole, to the target task, moving the cart to one direction without letting the pole fall down.