A Proactive Longitudinal Control of Automated Vehicle Using Machine Learning-based Motion Prediction of Cut-In Vehicles
- Delivery
- Available on this site
- Format
- Price
- Non-members (tax incl.):¥1,100 Members (tax incl.):¥880
- Publication code
- 20219006
- Paper/Info type
- Other International Conferences
- Pages
- 1-6(Total 6 p)
- Date of publication
- Sep 2021
- Publisher
- JSAE
- Language
- English
Detailed Information
Author(E) | 1) Youngmin Yoon, 2) Kyongsu Yi |
---|---|
Affiliation(E) | 1) Seoul National University, 2) Seoul National University |
Abstract(E) | This paper presents a motion prediction of cut-in vehicles and longitudinal control of autonomous vehicle for proactive response to cut-in preceding vehicles. A Support Vector Machine (SVM) and a Multi-Layer Perceptron (MLP) have been used to estimate the cut-in intention and future trajectory of cut-in motion of preceding vehicles, respectively. A Model Predictive Control (MPC) has been designed to derive a longitudinal control input of autonomous vehicle considering proactive response to cut-in. The proposed motion prediction algorithm has been evaluated according to its intention classification accuracy and state prediction error. Also, the performance of the control algorithm has been investigated in cutin scenarios via computer simulations. The evaluation results show that the application of the proposed method in autonomous vehicle provides proper ride quality and safety for passengers. |