Probabilistic logic for multi-robot event recognition

José A. Gurzoni, Paulo E. Santos, Murilo F. Martins, Fabio G. Cozman

Research output: Contribution to conferenceConference Paper

Abstract

This paper presents initial results towards the development of a logic-based probabilistic event recognition system capable of learning and inferring high-level joint actions from simultaneous task execution demonstrations on a search and rescue scenario. We adopt the MLN-EC event recognition system, which extends probabilistically the Event Calculus using Markov Logic Networks, to learn and infer the intentions of the human operators teleoperating robots in a real-world robotic search and rescue task. Experimental results in both simulation and real robots show that the probabilistic event logic can recognise the actions taken by the human teleoperators in real world multi-robot domains, even with uncertain and noisy data. Copyright © 2014, Association for the Advancement of Artificial Intelligence. All rights reserved.
Original languageAmerican English
Pages50-56
Number of pages7
DOIs
StatePublished - 1 Jan 2014
Externally publishedYes
EventAAAI Spring Symposium - Technical Report -
Duration: 1 Jan 2014 → …

Conference

ConferenceAAAI Spring Symposium - Technical Report
Period1/01/14 → …

Fingerprint

Dive into the research topics of 'Probabilistic logic for multi-robot event recognition'. Together they form a unique fingerprint.

Cite this