What is it about?
A data-driven navigation architecture that uses state-of-the-art neural architectures, namely Conditional Neural Processes, to learn the mobile robot's global and local controllers from observations, demonstrating that the proposed framework can successfully carry out navigation tasks regarding social norms in the data.
Featured Image
Photo by Andy Kelly on Unsplash
Why is it important?
Sociability is essential for modern robots to increase their acceptance in human environments. Traditional techniques use manually engineered utility functions inspired by observing pedestrian behaviors to achieve social navigation. This paper presents a data-driven navigation architecture that uses state-of-the-art neural architectures to learn pedestrian behavior from observations.
Perspectives
In environments where mobile robots are used in public spaces, such as malls, airports, and hospitals, where they need to interact with and navigate around humans. Mobile robots that are able to navigate socially are better able to operate in these environments, without disrupting human activity.
Yigit YILDIRIM
Bogazici Universitesi
Read the Original
This page is a summary of: Learning social navigation from demonstrations with conditional neural processes, Interaction Studies Social Behaviour and Communication in Biological and Artificial Systems, December 2022, John Benjamins,
DOI: 10.1075/is.22018.yil.
You can read the full text:
Resources
Contributors
The following have contributed to this page
