Applying 3D Object Detection from Self-Driving Cars to Mobile Robots: A Survey and Experiments

Publikationstyp
Conference Paper
Date Issued
2023-04
Sprache
English
Author(s)
Wozniak, Maciej  
Karefjard, Viktor
Hansson, Mattias
Thiel, Marko  orcid-logo
Technische Logistik W-6  
Jensfelt, Patric  
TORE-URI
https://hdl.handle.net/11420/42354
Citation
IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC 2023)
Contribution to Conference
2023 IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2023
Publisher DOI
10.1109/ICARSC58346.2023.10129637
Scopus ID
2-s2.0-85161974029
ISBN
9798350301212
3D object detection is crucial for the safety and reliability of mobile robots. Mobile robots must understand dynamic environments to operate safely and successfully carry out their tasks. However, most of the open-source datasets and methods are built for autonomous driving. In this paper, we present a detailed review of available 3D object detection methods, focusing on the ones that could be easily adapted and used on mobile robots. We show that the methods do not perform well if used off-the-shelf on mobile robots or are too computationally expensive to run on mobile robotic platforms. Therefore, we propose a domain adaptation approach to use publicly available data to retrain the perception modules of mobile robots, resulting in higher performance. Finally, we run the tests on the real-world robot and provide data for testing our approach.
Subjects
mobile robots
object detection
perception