Problem
Research questions and friction points this paper is trying to address.
mapless navigation
sign-based visual navigation
autonomous robots
navigational signs
SiGNgapore - An Interactive Dataset for Sign-based Visual Navigation
🤖 AI Summary
This study addresses the challenge of robot localization and decision-making relying on human navigation signs in environments without pre-built maps, proposing the first sign-centric multimodal dataset for mapless navigation. Methodologically, RGB-D and IMU data are captured using handheld devices, and scene graphs are constructed by integrating visual SLAM with GPS alignment techniques, further supporting conversion to ROS 2 formats. The released interactive dataset encompasses complex public spaces in Singapore, comprising over 450 sign scenarios and 56 long-horizon navigation tasks. By providing a critical benchmark and robust data support, this work significantly advances research on autonomous robot navigation in real-world, unstructured environments.
📝 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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
mapless navigation
sign-centric dataset
multimodal sensor fusion
long-horizon missions
scene graphs
🔎 Similar Papers
No similar papers found.
