Identification of Vehicle Dynamics Parameters Using Simulation-based Inference
This addresses parameter identification for autonomous vehicle control and planning, but appears incremental as it applies an emerging method to a specific domain.
The paper tackled the problem of identifying tire and vehicle parameters for autonomous vehicles by proposing Simulation-Based Inference (SBI), a modern interpretation of Approximate Bayesian Computation, and demonstrated that it yields accurate estimates for highly nonlinear dynamics parameters.
Identifying tire and vehicle parameters is an essential step in designing control and planning algorithms for autonomous vehicles. This paper proposes a new method: Simulation-Based Inference (SBI), a modern interpretation of Approximate Bayesian Computation methods (ABC) for parameter identification. The simulation-based inference is an emerging method in the machine learning literature and has proven to yield accurate results for many parameter sets in complex problems. We demonstrate in this paper that it can handle the identification of highly nonlinear vehicle dynamics parameters and gives accurate estimates of the parameters for the governing equations.