Education, Science, Technology, Innovation and Life
Open Access
Sign In

Research on Path Planning Algorithm Based on Fast Target Detection

Download as PDF

DOI: 10.23977/jaip.2024.070223 | Downloads: 2 | Views: 49

Author(s)

Wei Zhang 1, Zhigao Cui 1, Nian Wang 1, Yunwei Lan 1

Affiliation(s)

1 Xi'an Research Institute of High-Tech, Xi'an, 710025, China

Corresponding Author

Wei Zhang

ABSTRACT

As a key technology of robot navigation, path planning has garnered widespread attention and has been utilized in various applications such as mobile robots, unmanned aerial vehicles, and human-computer interaction. Recently, several studies advocate constructing semantic maps for path planning in the laboratory stage. However, these approaches require large storage space and high computing resource consumption, making it difficult to meet real-time requirements. We tackle this issue by building real-time semantic navigation map and propose a real-time path planning algorithm based on fast target detection. Specially, we first construct two-dimensional grid map using the Gamapping method and locate the target objection utilizing the object detection algorithm YOLOv3 retrained in an indoor experimental environment. Furthermore, by incorporating the category information and position information of the detected object into the two-dimensional grid map through a coordinate mapping mechanism, we combine the geometric metric information and visual detection information to build semantic navigation map for automatically planning a reasonable path.  The experiments conducted on both qualitative and quantitative levels have demonstrated that our method achieves superior performance and practical application value.

KEYWORDS

Mobile robot; Object detection; Two-dimensional grid map; Semantic navigation mapping

CITE THIS PAPER

Wei Zhang, Zhigao Cui, Nian Wang, Yunwei Lan, Research on Path Planning Algorithm Based on Fast Target Detection. Journal of Artificial Intelligence Practice (2024) Vol. 7: 173-181. DOI: http://dx.doi.org/10.23977/jaip.2024.070223.

REFERENCES

[1] B. Kuipers. Modeling spatial knowledge. Cognitive Science, 1978, 2(2): 129-153.
[2] J. Civera, D. Gálvez-López, L. Riazuelo, et al. Towards semantic SLAM using a monocular camera. International Conference on Intelligent Robots and Systems, 2011: 1277-1284.
[3] Z. Liu, G. V. Wichert. Extracting semantic indoor maps from occupancy grids. Robotics & Autonomous Systems, 2014, 62(5): 663-674.
[4] W. T. Jiang, X. J. Gong, J. L. Liu. Dense semantic map construction of large-scale scene based on incremental computing. Journal of Zhejiang University, 2016, 50(2):385-391.
[5] J. S. Yu, H. Wu, G. H. Tian Cloud-based semantic library design and robot semantic map construction. Robot, 2016, 38(4):410-419.
[6] X. Y. Zhan. Research on Simultaneous localization and indoor map Construction Algorithm based on Lidar. Harbin Insitute of Techmology, 2017
[7] H. Chou, X. L. Ping W. Y. Gao, et al. Research on multi-sensor information fusion algorithm for constructing mobile robot map. Mechanical manufacturing, 2017, 55(8):1-4.
[8] J. Redmon, A. Farhadi. YOLOv3: An Incremental Improvement. 2018, arXiv, 4.
[9] M. Everingham, L. V. Gool, C. K. Williams, et al. The Pascal Visual Object Classes (VOC) Challenge. International Journal of Computer Vision, 2010, 88(2): 303-338.

Downloads: 8083
Visits: 213414

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.