Summary of Towards Robust Car Following Dynamics Modeling Via Blackbox Models: Methodology, Analysis, and Recommendations, by Muhammad Bilal Shahid et al.
Towards Robust Car Following Dynamics Modeling via Blackbox Models: Methodology, Analysis, and Recommendations
by Muhammad Bilal Shahid, Cody Fleming
First submitted to arxiv on: 11 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Robotics (cs.RO); Systems and Control (eess.SY)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper investigates the selection of optimal target variables for black-box models, such as LSTM, GP, and Kernel Ridge Regression, used to model car following behavior. Unlike classical car following models like GIPPS and IDM, these black-box models do not rely on wise selection of target variables. The study evaluates different target variables, including acceleration, velocity, and headway, for each model type. The results show that the optimal target variable recommendations differ depending on the objective function and vector space used by the model. This research contributes to a better understanding of how to choose effective target variables for black-box models in car following applications. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper looks at which numbers to focus on when using special computer programs (called black-box models) to study how cars follow each other. These programs are different from usual car-following models because they don’t need to make smart choices about what numbers to look at. The researchers tried out different important numbers, like acceleration and speed, with three types of black-box models. They found that the best choice depends on what the model is trying to do and how it works. |
Keywords
* Artificial intelligence * Lstm * Objective function * Regression * Vector space
