Summary of Vehicle Lateral Control Using Machine Learning For Automated Vehicle Guidance, by Akash Fogla et al.
Vehicle lateral control using Machine Learning for automated vehicle guidance
by Akash Fogla, Kanish Kumar, Sunnay Saurav, Bishnu ramanujan
First submitted to arxiv on: 14 Mar 2023
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 This research proposes a machine-learning-based lateral controller for a safety-critical system operating in the real world. The controller is designed to handle uncertainty gracefully, ensuring safe operation. Two models are trained: a random forest model, which provides confidence/uncertainty predictions due to its ensemble nature, and a deep neural network model. The controller is tested on data from one track and validated on other tracks. The study highlights the benefits of using a random forest-based regressor, showcasing improved generalization capabilities compared to a deep neural network. Furthermore, the confidence in predictions enables the creation of a threshold for taking control when the controller is not confident, preventing potential failures. This work demonstrates the potential of machine learning in safety-critical systems. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research creates a smart car that can drive safely on different roads by using special computer programs called models. The program looks at what the car has learned from driving on one road and then tries to apply it to other roads. But sometimes, the program might not be sure about what to do, so it needs to make a decision quickly. This is important because if the program makes a mistake, someone could get hurt. The researchers found that using a special type of model called random forest can help the car drive safely even when it’s not sure. They also created a way for the car to know when it’s not confident and take control before things go wrong. |
Keywords
* Artificial intelligence * Generalization * Machine learning * Neural network * Random forest
