Opportunistic Intermittent Control with Safety Guarantees for Autonomous Systems



Huang, Chao ORCID: 0000-0002-9300-1787, Xu, Shichao, Wang, Zhilu, Lan, Shuyue, Li, Wenchao and Zhu, Qi
(2020) Opportunistic Intermittent Control with Safety Guarantees for Autonomous Systems. .

[img] Text
2005.03726v1.pdf - Submitted Version

Download (517kB) | Preview

Abstract

Control schemes for autonomous systems are often designed in a way that anticipates the worst case in any situation. At runtime, however, there could exist opportunities to leverage the characteristics of specific environment and operation context for more efficient control. In this work, we develop an online intermittent-control framework that combines formal verification with model-based optimization and deep reinforcement learning to opportunistically skip certain control computation and actuation to save actuation energy and computational resources without compromising system safety. Experiments on an adaptive cruise control system demonstrate that our approach can achieve significant energy and computation savings.

Item Type: Conference or Workshop Item (Unspecified)
Additional Information: Accepted by Design Automation Conference (DAC) 2020
Uncontrolled Keywords: eess.SY, eess.SY, cs.SY
Divisions: Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User: Symplectic Admin
Date Deposited: 22 Sep 2021 11:02
Last Modified: 06 May 2022 09:10
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3137908