Sage Journals: Discover world-class research

Abstract

The influence of complex nonlinear factors and the coupling characteristics of the vehicle’s lateral and longitudinal directions must be addressed in analyzing and modeling the physical mechanisms of autonomous vehicle dynamics. Otherwise, this will lead to errors between the actual vehicle dynamics and the model when the operating condition changes. This paper proposes a nonlinear proxy modeling method (MTSSF-GRU-FNN) to characterize the complex vehicle dynamics. The Gated Recurrent Units (GRUs) construct a memory-enhanced network that recognizes the continuous variability and strong temporal dependencies inherent in the real-world operation. Moreover, the feedforward neural network (FNN) is introduced in this paper to enhance the fitting performance for multi-input, multi-output nonlinear relationships caused by lateral and longitudinal coupling. Finally, the historical information is integrated into the network using the Multi Time Step State Feature (MTSSF) sliding window method. Simulation results based on a four-wheel dynamic model in the Carsim/Simulink environment under different road adhesion coefficients show the high accuracy and superiority of the proposed method that 0.2595 in average MAE, 0.6482 in average RMSE, and 142.542 ms in Computing time.

Keywords

Vehicle dynamics lateral and longitudinal coupling data driven modeling gate recurrent unit feedforward neural network

Get full access to this article

View all access options for this article.

References

Funahashi

Nakamura

Approximation of dynamical-systems by continuous-time recurrent neural networks. Neural Netw 1993; 6: 801–806.

Dynamic system identification via recurrent multilayer perceptrons. Inf Sci 2002; 147: 45–63.

Ghazizadeh

Fahim

ElGindy

Neural networks representation of a vehicle model: Neuro-Vehicle (NV). Int J Veh Des 1996; 17: 55–75.

Punjani

Abbeel

Deep learning helicopter dynamics models. In: 2015 IEEE international conference on robotics and automation (ICRA), Seattle, WA, USA, 26–30 May 2015, pp.3223–3230. New York: IEEE.

Bansal

Akametalu

Jiang

, et al. Learning quadrotor dynamics using neural network for flight control. In: 2016 IEEE 55th conference on decision and control (CDC), Las Vegas, NV, USA, 12–14 December 2016, pp.4653–4660. New York: IEEE.

Albeaik

Chou

F-C

X-Y

, et al. Deep Truck: a deep neural network model for longitudinal dynamics of heavy duty trucks. In: 2019 IEEE intelligent transportation systems conference, ITSC, Auckland, New Zealand, 27–30 October 2019, pp.4158–4163. New York: IEEE.

Sun

Wei

Yan

, et al. Artificial neural network-based performance modeling of a diesel engine within the whole operating region considering dynamic conditions. Proc IMechE, Part D: J Automobile Engineering 2019; 233: 2970–2984.

Garimella

Funke

Wang

, et al. Neural network modeling for steering control of an autonomous vehicle. In: 2017 IEEE/RSJ international conference on intelligent robots and systems (IROS), Vancouver, BC, Canada, 24–28 September 2017, pp.2609–2615. New York: IEEE.

Spielberg

Brown

Kapania

, et al. Neural network vehicle models for high-performance automated driving. Sci Robot 2019; 4: eaaw1975.

10.

Da Lio

Bortoluzzi

Papini

GPR

. Modelling longitudinal vehicle dynamics with neural networks. Veh Syst Dyn 2020; 58: 1675–1693.

11.

Pan

Nie

, et al. Data-driven vehicle modeling of longitudinal dynamics based on a multibody model and deep neural networks. Measurement 2021; 180: 109541.

12.

Xiao

Zhang

, et al. Deep neural networks with Koopman operators for modeling and control of autonomous vehicles. IEEE Trans Intell Veh 2023; 8: 135–146.

13.

Fraikin

Funk

Frey

, et al. A fast and accurate hybrid simulation model for the large-scale testing of automated driving functions. Proc IMechE, Part D: J Automobile Engineering 2020; 234: 1183–1196.

14.

Fang

Cai

Chen

, et al. Neural network lateral dynamics modeling and control based on ED-LSTM for intelligent vehicle. Chin J Theor Appl Mech 2022; 54: 1896–1908.

15.

Fang

Cai

Chen

, et al. A high-performance neural network vehicle dynamics model for trajectory tracking control. Proc IMechE, Part D: J Automobile Engineering 2023; 237: 1695–1709.

16.

Huang

Xiao

, et al. Dynamic model construction and simulation based on intelligent driving vehicle. In: 4th IEEE advanced information management, communicates, electronic and automation control conference, IMCEC 2021, Chongqing, China, 18–20 June 2021, pp.1407–1411. New York: IEEE.

17.

Lai

Huang

Analysis of vehicle driving stability based on longitudinal-lateral and vertical unified dynamics model. Int J Automot Technol 2022; 23: 73–87.

18.

Vielma

Verma

Bein

Sentiment analysis with novel GRU based deep learning networks. In: 2023 IEEE World AI IoT Congress, AIIoT 2023, Seattle, WA, USA, 7–10 June 2023, pp.440–446. New York: IEEE.

19.

Zhou

Zhang

Yin

, et al. Research on short-term traffic flow prediction based on KNN-GRU. In: 2022 Chinese Automation Congress, CAC 2022, Xiamen, China, 25–27 November 2022, pp.1924–1928. New York: IEEE.

20.

Lee

Kim

Bae

Efficient design method for a forward-converter transformer based on a KNN-GRU-DNN model. IEEE Trans Power Electron 2023; 38: 73–78.

21.

Tang

IBM stock forecast using LSTM, GRU, attention and transformer models. In: 2023 IEEE international conference on control, electronics and computer technology, ICCECT 2023, Jilin, China, 28–30 April 2023, pp.167–172. New York: IEEE.

22.

Zhang

Dou

Wang

, et al. Neural network optimized by genetic algorithm for predicting single well production in high water cut reservoir. In: 3rd international conference on intelligent control, measurement and signal processing and intelligent oil field, ICMSP 2021, Xi’an, China, 23–25 July 2021, pp.297–306. New York: IEEE.

23.

Zarzycki

Lawrynczuk

Advanced predictive control for GRU and LSTM networks. Inf Sci 2022; 616: 229–254.

MTSSF-GRU-FNN based modeling of vehicle lateral and longitudinal coupling dynamics

Abstract

Keywords

Get full access to this article

References