Research on autonomous obstacle avoidance of mountainous tractors based on semantic neural network and laser SLAM

Ningjie Chang, Xianghai Yan, Bingxin Chen, Yiwei Wu and Liyou Xu

PLOS ONE, 2025, vol. 20, issue 5, 1-20

Abstract: The accuracy and consistency of obstacle avoidance map construction are poor in complex and changeable dynamic environment. In order to improve the driving safety of mountain tractors in complex mountain environment, an autonomous obstacle avoidance method for mountain tractors based on semantic neural network and laser SLAM was studied. Firstly, the RPLIDAR-A1 lidar sensor is used to realize high-precision scanning of mountain environment and construction of observation model. Then, the observed data is input into the lightweight convolutional neural network, and obstacles in the mountain environment are detected and semantic information is extracted through layer pruning and channel pruning strategies, and key information such as the type, size, and location of obstacles is output. Finally, the 3D map of mountain environment containing semantic information is further constructed by combining laser SLAM technology. A* algorithm is used on the map for global path planning to realize the autonomous obstacle avoidance function of mountain tractors. Experimental results show that this method can accurately detect obstacles in mountain environment, identify steep hillsides, rock piles and densely vegetated areas in mountain environment, plan the shortest and optimal driving path, and flexibly avoid diverse obstacles.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0323631 (text/html)
https://journals.plos.org/plosone/article/file?id= ... 23631&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pone00:0323631

DOI: 10.1371/journal.pone.0323631

Access Statistics for this article

More articles in PLOS ONE from Public Library of Science
Bibliographic data for series maintained by plosone ().