Safe Visual Navigation via Deep Learning and Novelty Detection

Robots that use learned perceptual models in the real world must be able to safely handle cases where they are forced to make decisions in scenarios that are unlike any of their training examples. However, state-of-the-art deep learning methods are known to produce erratic or unsafe prediction...

Полное описание

Библиографические подробности
Главные авторы: Richter, Charles Andrew, Roy, Nicholas
Другие авторы: Massachusetts Institute of Technology. Department of Aeronautics and Astronautics
Формат: Статья
Опубликовано: Robotics: Science and Systems Foundation 2018
Online-ссылка:http://hdl.handle.net/1721.1/115978
https://orcid.org/0000-0003-3765-2021
https://orcid.org/0000-0002-8293-0492