Energy-Efficient Automatic Train Driving by Learning Driving Patterns
Authors: Jin Huang, Yue Gao, Sha Lu, Xibin Zhao, Yangdong Deng, Ming Gu
AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Validation experiments proved that the energy consumption of the proposed solution is around 10% lower than that of average human drivers. |
| Researcher Affiliation | Academia | Jin Huang, Yue Gao, Sha Lu, Xibin Zhao, Yangdong Deng, Ming Gu School of Software/KLISS/TNList Tsinghua University, Beijing, 100084, China. indicates corresponding authors, emails: {gaoyue,zxb}@tsinghua.edu.cn |
| Pseudocode | Yes | Algorithm 1: The high-order correlation reinforcement updating process |
| Open Source Code | No | The paper does not provide any explicit statements or links indicating that the source code for the described methodology is publicly available. |
| Open Datasets | No | The paper uses a dataset collected from 'driving data of experienced human drivers' and 'records data from experienced human drivers'. It explicitly states 'we choose 400 best valued trips from thousands of records' but does not provide any link, citation to a public source, or statement of public availability for this dataset. |
| Dataset Splits | No | The paper does not explicitly provide details about a validation dataset split (e.g., specific percentages or sample counts for training, validation, and testing sets) for reproducibility. While it mentions 'Validation experiments', this refers to the overall experimental process, not a distinct dataset split. |
| Hardware Specification | No | The paper describes the 'Hardware-in-Loop test platform' and details of the 'experimental locomotive' and its gear system (e.g., 'a gear of 17 levels'), but it does not specify the computing hardware such as CPU, GPU, or RAM used for training or inference of the model. |
| Software Dependencies | No | The paper mentions 'Mapminmax method in Matlab' but does not provide specific version numbers for Matlab or any other software libraries or dependencies used. |
| Experiment Setup | Yes | The parameter λ was tuned to 0.1 according to the tested results from a value set of [0.001, 0.01, 0.1, 1, 10, 100, 1000], and the Mapminmax method in Matlab were employed for normalization. Extra training and simulation are also needed to tune the weights on the key parameters, e.g., the weight and length of the train, the slope of the railway, the speed limit. |