Gao, Yu, Huo, Jing, Li, Wen-Nin, Wu, Jing ![]() ![]() ![]() |
Preview |
PDF
- Accepted Post-Print Version
Download (950kB) | Preview |
Abstract
To solve the problems of low exploration efficiency and imprecise depth in object goal navigation, this article constructs a framework to solve object goal navigation. Depth map edge processing and map error correction mechanisms were introduced in the semantic map construction module; a coverage maximization algorithm was introduced in the exploration module; alternative point mechanisms was introduced in the path planning module. This article conducted experiments in a 3D simulation environment. The experimental results show that the new solution proposed in this article significantly improves the performance of object goal navigation. In addition, the method proposed in this article was successfully applied to quadruped robots, thereby verifying its generalization in real-world scenarios.
Item Type: | Article |
---|---|
Date Type: | Publication |
Status: | Published |
Schools: | Schools > Computer Science & Informatics |
Language other than English: | Chinese |
Publisher: | IET - Institution of Engineering and Technology |
Date of First Compliant Deposit: | 9 June 2024 |
Date of Acceptance: | 4 December 2023 |
Last Modified: | 19 Jun 2025 15:00 |
URI: | https://orca.cardiff.ac.uk/id/eprint/169622 |
Actions (repository staff only)
![]() |
Edit Item |