INTUIT-VLNCE: Autonomous Navigation through Vision-and-Language
Date
2024
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Tartu Ülikool
Abstract
The aim of this thesis was to developed an Embodied Agent with explicit intuition capable of
navigating indoor Continuous Environments based on provided Natural Language instruction
and Agent’s egocentric vision as part of a Vision-and-Language Navigation task. The thesis
proposes creating explicit intuition by making an Agent predict not only an action to perform at
a given time, but also predicting actions for the future.
An Agent’s policy was trained mimicking the training procedure from LAW-VLNCE project
[1]. Evaluations showed negative results after implementing proposed method.
Description
Käesoleva lõputöö eesmärk oli ilmse intuitsiooniga Kehastunud Agendi arendus. Kehastunud
Agent peab navigeerima läbi pideva siseruumi, kasutades antud Loomuliku Keele instruktsiooni
ja egotsentrilist nägemust, nagu on kirjeldatud Nägemus-ja-Keel ülesannes. Lõputöö pakub
välja luua ilmset intuitsiooni: Agent ennustab ette nii tegu, mida on vaja hetkseisul sooritada,
kui ka tegusid, mida kavatsetakse sooritada tulevikus.
Keywords
robotics, natural language, embodied agent, autonomy