Dataset enables mapless robot navigation using human signs indoors
SiGNgapore - An Interactive Dataset for Sign-based Visual Navigation
Robotics
Summary
Navigating indoor spaces without maps is hard for robots. This paper presents a new dataset collected from real places in Singapore that helps robots learn to use human-made signs for navigation. The data includes videos, depth, and movement info focused on signs and their surroundings. The authors also provide tools to work with the data and maps of the locations. This resource can help build robots that find their way like humans do, by following signs.
What this means in practice
- •For robotics engineers: Enable development of indoor autonomous robots that navigate by recognizing and following human signage without relying on prebuilt maps.
- •For smart building developers: Create assistive indoor navigation systems that utilize existing signs to guide robots or devices within public spaces like airports or malls.
Authors
Nicky Zimmerman, Joel Loo, Zishuo Wang, David Hsu
Abstract
The future of autonomous robots in human-oriented environments depends on their ability to navigate in the absence of prebuilt maps; exploiting navigational aids, such as navigational signs, designed by humans for humans is critical for enabling autonomy. This manuscript introduces a unique dataset collected using a handheld device, at various public spaces across Singapore, representing environments that humans frequent daily, and focusing on sign-centric decision making for mapless navigation. The dataset includes RGB, sparse depth, odometry and IMU measurements of scenarios centered around navigational signs and the complex environments where they are placed. Additionally, we provide 56 long-horizon navigation missions and over 450 sign-centric scenarios. All data is provided in a human- readable format, as well as utility scripts for conversion to ROS 2. Lastly, we provide venue maps and GPS aligned scene graphs of the test environments. We discuss the potential use cases for this dataset.