SACSoN: Scalable Autonomous Control for Social Navigation

Machine learning provides a powerful tool for building socially compliant robotic systems that go beyond simple predictive models of human behavior. By observing and understanding human interactions from past experiences, learning can enable effective social navigation behaviors directly from data....

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE robotics and automation letters Ročník 9; číslo 1; s. 49 - 56
Hlavní autoři: Hirose, Noriaki, Shah, Dhruv, Sridhar, Ajay, Levine, Sergey
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 01.01.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Behavioral sciences
Data Sets for Robot Learning
Datasets
Human behavior
Machine learning
Machine Learning for Robot Control
Navigation
Pedestrians
Perturbation
Perturbation methods
Policies
Prediction models
Predictive models
Robot control
Robot learning
Robots
social navigation
Social robots
Visual observation
Visualization
ISSN:2377-3766, 2377-3766
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Machine learning provides a powerful tool for building socially compliant robotic systems that go beyond simple predictive models of human behavior. By observing and understanding human interactions from past experiences, learning can enable effective social navigation behaviors directly from data. In this letter, our goal is to develop methods for training policies for socially unobtrusive behavior, such that robots can navigate among humans in ways that don't disturb human behavior in visual navigation using only onboard RGB observations. We introduce a definition for such behavior based on the counterfactual perturbation of the human: If the robot had not intruded into the space, would the human have acted in the same way? By minimizing this counterfactual perturbation, we can induce robots to behave in ways that do not alter the natural behavior of humans in the shared space. Instantiating this principle requires training policies to minimize their effect on human behavior, and this in turn requires data that allows us to model the behavior of humans in the presence of robots. Therefore, our approach is based on two key contributions. First, we collect a large dataset where an indoor mobile robot interacts with human bystanders. Second, we utilize this dataset to train policies that minimize counterfactual perturbation. We provide supplementary videos and make publicly available the visual navigation dataset on our project page.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2377-3766
2377-3766
DOI:10.1109/LRA.2023.3329626