Fuzzy Terrain Traversability Assessment and Adaptive Artificial Potential Field for Unmanned Ground Vehicle Control Based on Light Detection and Ranging
- 1Department of Computer Science & Information Engineering, National Chin-Yi University of Technology, No. 57, Sec. 2, Zhongshan Road, Taiping District, Taichung 411030, Taiwan
Abstract
Unmanned ground vehicle control in unknown environments is hindered by terrain variation, obstacle complexity, and sensor noise. This study proposes a light-detection-and-ranging-based control system that integrates fuzzy terrain traversability assessment (FTTA) and adaptive artificial potential field (AAPF) algorithms for terrain detection and obstacle avoidance. Cloth simulation filtering (CSF) is used to preprocess point clouds for distinguishing between terrain and aboveground points. The FTTA algorithm then identifies terrain obstacles using slope and height features, with aboveground points classified as obstacles by height. Moreover, the AAPF algorithm integrates both terrain and aboveground points to adaptively adjust the exclusion radius and improve path planning. Experimental analysis revealed that FTTA with CSF achieved a ground point retention rate of 0.682, a height variance of 0.087, and a processing time of 0.016 s. These values maintained the slope estimation angles close to the true values and ensured stable and rapid computation. In navigation experiments, the AAPF algorithm achieved a reduced travel distance of 62.4 ± 3.2 m and a reduced travel time of 154 ± 5 s. Compared with the baseline APF method, this represents a reduction of 21% in navigation time, indicating improved efficiency and stability.
Related
- A comparison of artificial neural networks and partial least squares modelling for the rapid detection of the microbial spoilage of beef fillets based on Fourier transform infrared spectral fingerprints
- Real-time and adaptive anomaly detection algorithm for cyclostationary models
- Adaptive online kernel changepoint detection
- Nonparametric framework for the definition, adaptive detection and probabilistic interpretation of outliers
- An optimization-based waypoint generation method for overcoming local minima in artificial potential field navigation
BibTeX
@article{lin2026fuzzy,
title = {{Fuzzy Terrain Traversability Assessment and Adaptive Artificial Potential Field for Unmanned Ground Vehicle Control Based on Light Detection and Ranging}},
author = {Cheng-Hsien Lin and Xue-Qian Lin and Cheng-Jian Lin and Jun-Wei Lu},
journal = {Mathematics},
year = {2026},
month = nov,
doi = {10.3390/math14214022},
url = {https://www.mdpi.com/2227-7390/14/21/4022},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Fuzzy Terrain Traversability Assessment and Adaptive Artificial Potential Field for Unmanned Ground Vehicle Control Based on Light Detection and Ranging
AU - Cheng-Hsien Lin
AU - Xue-Qian Lin
AU - Cheng-Jian Lin
AU - Jun-Wei Lu
PY - 2026
DA - 2026/11/03
JO - Mathematics
DO - 10.3390/math14214022
UR - https://www.mdpi.com/2227-7390/14/21/4022
AB - Unmanned ground vehicle control in unknown environments is hindered by terrain variation, obstacle complexity, and sensor noise. This study proposes a light-detection-and-ranging-based control system that integrates fuzzy terrain traversability assessment (FTTA) and adaptive artificial potential field (AAPF) algorithms for terrain detection and obstacle avoidance. Cloth simulation filtering (CSF) is used to preprocess point clouds for distinguishing between terrain and aboveground points. The FTTA algorithm then identifies terrain obstacles using slope and height features, with aboveground points classified as obstacles by height. Moreover, the AAPF algorithm integrates both terrain and aboveground points to adaptively adjust the exclusion radius and improve path planning. Experimental analysis revealed that FTTA with CSF achieved a ground point retention rate of 0.682, a height variance of 0.087, and a processing time of 0.016 s. These values maintained the slope estimation angles close to the true values and ensured stable and rapid computation. In navigation experiments, the AAPF algorithm achieved a reduced travel distance of 62.4 ± 3.2 m and a reduced travel time of 154 ± 5 s. Compared with the baseline APF method, this represents a reduction of 21% in navigation time, indicating improved efficiency and stability.
SN - 2227-7390
ER -