Edinburgh Research Explorer

Learning effects of robot actions using temporal associations

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Related Edinburgh Organisations

Open Access permissions

Open

Original languageEnglish
Title of host publicationDevelopment and Learning, 2002. Proceedings. The 2nd International Conference on
Pages96-101
Number of pages6
DOIs
Publication statusPublished - 2002

Abstract

Agents need to know the effects of their actions. Strong associations between actions and effects can be found by counting how often they co-occur. We present an algorithm that learns temporal patterns expressed as fluents, i.e. propositions with temporal extent. The fluent-learning algorithm is hierarchical and unsupervised. It works by maintaining co-occurrence statistics on pairs of fluents. In experiments on a mobile robot, the fluent-learning algorithm found temporal associations that correspond to effects of the robot's actions.

    Research areas

  • mobile robots, temporal reasoning, time series, unsupervised learning, action-effect cooccurrence statistics, agent action-effect association, hierarchical unsupervised fluent-learning algorithm, mobile robot, propositions, robot action effects learning, temporal associations, temporal extent, temporal pattern learning algorithm, Calculus, Computer science, Frequency measurement, Grippers, Humans, Influenza, Logic, Mobile robots, Sonar measurements, Statistics

Download statistics

No data available

ID: 14901395