Constraint learning for control tasks with limited duration barrier functions. (May 2021)

• Record Type: Journal Article
• Authors: Ohnishi, Motoya; Notomista, Gennaro; Sugiyama, Masashi; Egerstedt, Magnus
• Is Part Of: Automatica. Volume 127(2021)
• Publication Date: 2021-05
• Subjects: Constraints -- Invariance -- Learning control -- Model-based control -- Knowledge transfer; Automatic control -- Periodicals; Automation -- Periodicals; 629.805
• DOI: 10.1016/j.automatica.2021.109504
• Languages: English
• ISSNs: 0005-1098

Abstract

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.