Skip to end of metadata
Go to start of metadata

 

Place Categorization and Semantic Mapping on a Mobile Robot

Niko Sünderhauf, Feras Dayoub, Sean McMahon, Ben Talbot, Ruth Schulz, Peter Corke, Gordon Wyeth, Ben Upcroft, and Michael Milford

 

@inproceedings{95288,
booktitle = {IEEE International Conference on Robotics and Automation (ICRA 2016)},
month = {May},
title = {Place categorization and semantic mapping on a mobile robot},
author = {Niko Sunderhauf and Feras Dayoub and Sean McMahon and Ben Talbot and Ruth Schulz and Peter Corke and Gordon Wyeth and Ben Upcroft and Michael Milford},
address = {Stockholm, Sweden},
publisher = {IEEE},
year = {2016}
}

 

Abstract

In this paper we focus on the challenging problem of place categorization and semantic mapping on a robot without environment-specific training.

Motivated by their ongoing success in various visual recognition tasks, we build our system upon a state-of-the-art convolutional network. We overcome its closed-set limitations by complementing the network with a series of one-vs-all classifiers that can learn to recognize new semantic classes online. Prior domain knowledge is incorporated by embedding the classification system into a Bayesian filter framework that also ensures temporal coherence.

We evaluate the classification accuracy of the system on a robot that maps a variety of places on our campus in real-time. We show how semantic information can boost robotic object detection performance and how the semantic map can be used to modulate the robot's behaviour during navigation tasks. The system is made available to the community as a ROS module.


Videos

The following videos demonstrate the semantic categorization and mapping system running on a mobile robot in different environments on the campus of our university. Watch the videos in fullscreen resolution for more details.

OfficeSupermarketCorridor
Parking GarageCampus OutdoorsCafe
Lecture TheatreFood CourtLobby




Source code

https://github.com/fdayoub/ros-semantic-mapper

rosbag files and network model available to download from (https://cloudstor.aarnet.edu.au/plus/index.php/s/n63jLJyL2JjcCHq)

@inproceedings{quteprints95288,
booktitle = {IEEE International Conference on Robotics and Automation (ICRA 2016)},
month = {May},
title = {Place categorization and semantic mapping on a mobile robot},
author = {Niko Sunderhauf and Feras Dayoub and Sean McMahon and Ben Talbot and Ruth Schulz and Peter Corke and Gordon Wyeth and Ben Upcroft and Michael Milford},
address = {Stockholm, Sweden},
publisher = {IEEE},
year = {2016}
}


  • No labels