Identification of the nonlinear steering dynamics of an autonomous vehicle

05/10/2021
by   G. Rödönyi, et al.
0

Automated driving applications require accurate vehicle specific models to precisely predict and control the motion dynamics. However, modern vehicles have a wide array of digital and mechatronic components that are difficult to model, manufactures do not disclose all details required for modelling and even existing models of subcomponents require coefficient estimation to match the specific characteristics of each vehicle and their change over time. Hence, it is attractive to use data-driven modelling to capture the relevant vehicle dynamics and synthesise model-based control solutions. In this paper, we address identification of the steering system of an autonomous car based on measured data. We show that the underlying dynamics are highly nonlinear and challenging to be captured, necessitating the use of data-driven methods that fuse the approximation capabilities of learning and the efficiency of dynamic system identification. We demonstrate that such a neural network based subspace-encoder method can successfully capture the underlying dynamics while other methods fall short to provide reliable results.

READ FULL TEXT
research
08/27/2021

Identification of Vehicle Dynamics Parameters Using Simulation-based Inference

Identifying tire and vehicle parameters is an essential step in designin...
research
07/21/2023

Data-Driven Cooperative Adaptive Cruise Control for Unknown Nonlinear Vehicle Platoons

This paper studies cooperative adaptive cruise control (CACC) for vehicl...
research
01/04/2023

Data-Driven Model Identification via Hyperparameter Optimization for Autonomous Racing Systems

In this letter, we propose a model identification method via hyperparame...
research
05/10/2020

BayesRace: Learning to race autonomously using prior experience

Learning to race autonomously is a challenging problem. It requires perc...
research
05/27/2021

LVD-NMPC: A Learning-based Vision Dynamics Approach to Nonlinear Model Predictive Control for Autonomous Vehicles

In this paper, we introduce a learning-based vision dynamics approach to...
research
12/23/2020

Data-driven extrapolation via feature augmentation based on variably scaled thin plate splines

The data driven extrapolation requires the definition of a functional mo...
research
02/09/2022

Terrain parameter estimation from proprioceptive sensing of the suspension dynamics in offroad vehicles

Offroad vehicle movement has to contend with uneven and uncertain terrai...

Please sign up or login with your details

Forgot password? Click here to reset