Object-Oriented Semantic Mapping for Reliable UAVs Navigation

Thanh Nguyen Canh

Armagan Elibol

Nak Young Chong

Xiem HoangVan

School of Information Science, JAIST, Japan
VNU University of Engineering and Technology, Vietnam
ICCAIS, 2023.

[Paper]

[Code]

To autonomously navigate in real-world environments, special in search and rescue operations, Unmanned Aerial Vehicles (UAVs) necessitate comprehensive maps to ensure safety. However, the prevalent metric map often lacks semantic information crucial for holistic scene comprehension. In this paper, we proposed a system to construct a probabilistic metric map enriched with object information extracted from the environment from RGB-D images. Our approach combines a state-of-the-art YOLOv8-based object detection framework at the front end and a 2D SLAM method - CartoGrapher at the back end. To effectively track and position semantic object classes extracted from the front-end interface, we employ the innovative BoT-SORT methodology. A novel association method is introduced to extract the position of objects and then project it with the metric map. Unlike previous research, our approach takes into reliable navigating in the environment with various hollow bottom objects. The output of our system is a probabilistic map, which significantly enhances the map's representation by incorporating object-specific attributes, encompassing class distinctions, accurate positioning, and object heights. A number of experiments have been conducted to evaluate our proposed approach. The results show that the robot can effectively produce augmented semantic maps containing several objects (notably chairs and desks). Furthermore, our system is evaluated within an embedded computer - Jetson Xavier AGX unit to demonstrate the use case in real-world applications.

Paper

Thanh Nguyen Canh, Armagan Elibol, Nak Young Chong, Xiem HoangVan

Object-Oriented Semantic Mapping for Reliable UAVs Navigation

ICCAIS 2024.

[pdf]

Overview and Results

Overview

The overview of our proposal, front-end procedures: object detection, tracking, association; Back-end procedures: local mapping, loop closing, and global optimization based on CartoGrapher.

Semantic Knowledge Understanding

Semantic Association.

Experiments

Semantic Mapping.

Safety Navigation.

Code

[github]

Citation

1. Canh T. N., Elibol A., Chong A.Y., HoangVan X. Object-Oriented Semantic Mapping for Reliable UAVs Navigation. International Conference on Control, Automation and Information Sciences (ICCAIS), 2023.

@inproceedings{canh2023object, 
                                  

                                    author    = {Canh, Thanh Nguyen and Elibol, Armagan and Chong, Nak Young and HoangVan, Xiem}, 
                                  

                                    title     = {{Object-Oriented Semantic Mapping for Reliable UAVs Navigation}}, 
                                  

                                    booktitle = {2023 12th International Conference on Control, Automation and Information Sciences (ICCAIS)}, 
                                  

                                    year      = {2023}, 
                                  

                                    address   = {Vietnam}, 
                                  

                                    pages     = {139--144}, 
                                  

                                    DOI       = {10.1109/ICCAIS59597.2023.10382351}
                                  

                                }

Acknowledgements

We gratefully acknowledge support fromthe Asian Office of Aerospace Research and Development under Grant/Cooperative Agreement Award No. FA2386-22-1-4042.
This webpage template was borrowed from https://akanazawa.github.io/cmr/.