A-EMS: An Adaptive Emergency Management System for Autonomous Agents in Unforeseen Situations - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2022

A-EMS: An Adaptive Emergency Management System for Autonomous Agents in Unforeseen Situations

Abstract

Reinforcement learning agents are unable to respond effectively when faced with novel, out-of-distribution events until they have undergone a significant period of additional training. For lifelong learning agents, which cannot be simply taken offline during this period, suboptimal actions may be taken that can result in unacceptable outcomes. This paper presents the Autonomous Emergency Management System (A-EMS)-an online, data-driven, emergency-response method that aims to provide autonomous agents the ability to react to unexpected situations that are very different from those it has been trained or designed to address. The proposed approach devises a customized response to the unforeseen situation sequentially, by selecting actions that minimize the rate of increase of the reconstruction error from a variational autoencoder. This optimization is achieved online in a data-efficient manner (on the order of 30 to 80 data-points) using a modified Bayesian optimization procedure. The potential of A-EMS is demonstrated through emergency situations devised in a simulated 3D car-driving application.
Fichier principal
Vignette du fichier
TAROS2022.pdf (976.86 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Licence

Dates and versions

hal-03949106 , version 1 (20-01-2023)

Licence

Identifiers

Cite

Glenn Maguire, Nicholas Ketz, Praveen Pilly, Jean-Baptiste Mouret. A-EMS: An Adaptive Emergency Management System for Autonomous Agents in Unforeseen Situations. TAROS 2022 - Towards Autonomous Robotic Systems, 2022, Abingdon, United Kingdom. pp.266-281, ⟨10.1007/978-3-031-15908-4_21⟩. ⟨hal-03949106⟩
14 View
45 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More