Details
| Original language | English |
|---|---|
| Title of host publication | 2022 The 3rd International Conference on Robotics Systems and Vehicle Technology (RSVT) |
| Place of Publication | New York, NY, United States |
| Publisher | Association for Computing Machinery (ACM) |
| Pages | 28-35 |
| Number of pages | 8 |
| ISBN (electronic) | 9781450396783 |
| Publication status | Published - 31 Oct 2022 |
| Event | 3rd International Conference on Robotics Systems and Vehicle Technology, RSVT 2022 - Virtual, Online, Singapore Duration: 22 Jul 2022 → 24 Jul 2022 |
Abstract
Knowledge of vehicle dynamics and in particular the maximum friction coefficient is required for the optimization of advanced driver assistance systems and the implementation of autonomous driving. Since the maximum friction coefficient cannot be measured directly, estimating this coefficient based on available sensors is a field of interest. In particular, model-based approaches based on Kalman filter derivates are used. However, their accuracy is limited by the accuracy of the physical model. Due to the real-time capability required, more detailed modeling is not possible. In addition, system identification and a robust filter design are needed. As a result, data-based approaches are gaining popularity in vehicle dynamics, which are also suitable for estimating the maximum friction coefficient. In this paper, maximum friction coefficient estimation is presented using recurrent artificial neural networks (RANN) based on vehicle sensors. In order to avoid incorrect estimations during low vehicle excitation, an excitation monitoring approach is introduced. Typical longitudinal and lateral driving maneuvers on different road surfaces simulated in IPG CarMaker with a Dacia Duster are used for training, validation and testing of the RANN. Finally, the data-based approach shows improved results compared to the model-based approach of a sensitivity-based unscented Kalman filter (sUKF) from previous works.
Keywords
- automotive, maximum friction coefficient, neural networks, parameter estimation, vehicle dynamics
ASJC Scopus subject areas
- Computer Science(all)
- Human-Computer Interaction
- Computer Science(all)
- Computer Networks and Communications
- Computer Science(all)
- Computer Vision and Pattern Recognition
- Computer Science(all)
- Software
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2022 The 3rd International Conference on Robotics Systems and Vehicle Technology (RSVT). New York, NY, United States: Association for Computing Machinery (ACM), 2022. p. 28-35.
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Estimation of Maximum Friction Coefficient Using Recurrent Artificial Neural Networks
AU - Lampe, Nicolas
AU - Ziaukas, Zygimantas
AU - Westerkamp, Clemens
AU - Jacob, Hans-Georg
N1 - Funding Information: The authors would like to thank the Dr. Jürgen and Irmgard Ulderup foundation for funding this project.
PY - 2022/10/31
Y1 - 2022/10/31
N2 - Knowledge of vehicle dynamics and in particular the maximum friction coefficient is required for the optimization of advanced driver assistance systems and the implementation of autonomous driving. Since the maximum friction coefficient cannot be measured directly, estimating this coefficient based on available sensors is a field of interest. In particular, model-based approaches based on Kalman filter derivates are used. However, their accuracy is limited by the accuracy of the physical model. Due to the real-time capability required, more detailed modeling is not possible. In addition, system identification and a robust filter design are needed. As a result, data-based approaches are gaining popularity in vehicle dynamics, which are also suitable for estimating the maximum friction coefficient. In this paper, maximum friction coefficient estimation is presented using recurrent artificial neural networks (RANN) based on vehicle sensors. In order to avoid incorrect estimations during low vehicle excitation, an excitation monitoring approach is introduced. Typical longitudinal and lateral driving maneuvers on different road surfaces simulated in IPG CarMaker with a Dacia Duster are used for training, validation and testing of the RANN. Finally, the data-based approach shows improved results compared to the model-based approach of a sensitivity-based unscented Kalman filter (sUKF) from previous works.
AB - Knowledge of vehicle dynamics and in particular the maximum friction coefficient is required for the optimization of advanced driver assistance systems and the implementation of autonomous driving. Since the maximum friction coefficient cannot be measured directly, estimating this coefficient based on available sensors is a field of interest. In particular, model-based approaches based on Kalman filter derivates are used. However, their accuracy is limited by the accuracy of the physical model. Due to the real-time capability required, more detailed modeling is not possible. In addition, system identification and a robust filter design are needed. As a result, data-based approaches are gaining popularity in vehicle dynamics, which are also suitable for estimating the maximum friction coefficient. In this paper, maximum friction coefficient estimation is presented using recurrent artificial neural networks (RANN) based on vehicle sensors. In order to avoid incorrect estimations during low vehicle excitation, an excitation monitoring approach is introduced. Typical longitudinal and lateral driving maneuvers on different road surfaces simulated in IPG CarMaker with a Dacia Duster are used for training, validation and testing of the RANN. Finally, the data-based approach shows improved results compared to the model-based approach of a sensitivity-based unscented Kalman filter (sUKF) from previous works.
KW - automotive
KW - maximum friction coefficient
KW - neural networks
KW - parameter estimation
KW - vehicle dynamics
UR - http://www.scopus.com/inward/record.url?scp=85142181620&partnerID=8YFLogxK
U2 - 10.1145/3560453.3560459
DO - 10.1145/3560453.3560459
M3 - Conference contribution
AN - SCOPUS:85142181620
SP - 28
EP - 35
BT - 2022 The 3rd International Conference on Robotics Systems and Vehicle Technology (RSVT)
PB - Association for Computing Machinery (ACM)
CY - New York, NY, United States
T2 - 3rd International Conference on Robotics Systems and Vehicle Technology, RSVT 2022
Y2 - 22 July 2022 through 24 July 2022
ER -