Random Mapping Method for Large-Scale Terrain Modeling

Authors: Xu Liu, Decai Li, Yuqing He5395-5403

AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments show the effectiveness of the random mapping method and the effects of some important parameters on its performance. Moreover, we evaluate the proposed terrain modeling method based on the random mapping method and compare its performances with popular typical methods and state-of-art methods.
Researcher Affiliation Academia 1State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences 2Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences 3University of Chinese Academy of Sciences
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code Yes Datasets and code are open source in https://github.com/LiuXuSIA/rmm.
Open Datasets Yes Planet (Tong et al. 2013) and quarry are publicly available in http://asrl.utias.utoronto.ca/datasets/3dmap/index.html and http://www.pointcab-software.com/en/downloads/, respectively.
Dataset Splits Yes The results are averaged of 10-fold cross-validation.
Hardware Specification Yes The experiments are conducted on a computer having an Intel i7 CPU with 16 cores of 3.8GHz, 64GB memory, and Windows 10 OS.
Software Dependencies No The paper mentions "Windows 10 OS" but does not specify any other software dependencies with version numbers, such as programming languages, libraries, or frameworks.
Experiment Setup Yes The model weight parameters β are solved by SVD. The models are trained by the terrain surfaces extracted from the noisy original data (Liu, Li, and He 2021). ...the mapping dimension used by RMR is 850 and the random weights are sampled from the uniform distribution [-4,4]. In our implementation, we divide the whole areas into several sub-regions, using GMM, and train an individual GP model for each sub-region.