Artificial Intelligence for Vehicle Behavior Anticipation: Hybrid Approach Based on Maneuver Classification and Trajectory Prediction
| Autor: | Choubeila Maaoui, Abdelmoudjib Benterki, Vincent Judalet, Moussa Boukhnifer |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Artificial intelligence
General Computer Science Computer science Real-time computing 02 engineering and technology Track (rail transport) Motion (physics) law.invention Position (vector) law 0202 electrical engineering electronic engineering information engineering General Materials Science intention prediction Radar Artificial neural network autonomous vehicle 020208 electrical & electronic engineering General Engineering neural networks Lidar Anticipation (artificial intelligence) maneuver classification Trajectory 020201 artificial intelligence & image processing lcsh:Electrical engineering. Electronics. Nuclear engineering LSTM lcsh:TK1-9971 |
| Zdroj: | IEEE Access, Vol 8, Pp 56992-57002 (2020) |
| ISSN: | 2169-3536 |
| Popis: | Innovative technologies and naturalistic driving data sources provide a great potential to develop reliable autonomous driving systems. Understanding the behaviors of surrounding vehicles is essential for improving safety and mobility of autonomous vehicles. Onboard sensors like Radar, Lidar and Camera are able to track surrounding vehicles motion and to get different features like position, velocity and yaw. This paper proposes a hybrid approach to integrate maneuver classification using neural networks and trajectory prediction using Long Short-term Memory (LSTM) networks to get the future positions of adjacent vehicles. In this study we use the Next Generation Simulation (NGSIM) public dataset that provides a real driving data. The proposed approach is validated experimentally using VEDECOM demonstrator data. The results demonstrate that the proposed approach is able to predict driver intention to change lanes on average 2.2 seconds in advance. The Root Mean Square (RMS) errors of lateral and longitudinal positions are 0.30 m and 3.1 m respectively. The results demonstrate a high performance compared to various existing methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|