An Expeditious and Expressive Vehicle Dynamics Model for Applications in Controls and Reinforcement Learning
We present a Vehicle Model (VM) that has 17 degrees of freedom and includes nonlinear tire and powertrain subsystems. Implemented as a relatively small piece of C++ code, the model runs vehicle dynamics 2000 times faster than real time at a simulation time step of <inline-fo...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10443432/ |
| _version_ | 1797268008392982528 |
|---|---|
| author | Huzaifa Unjhawala Thomas Hansen Harry Zhang Stefan Caldraru Shouvik Chatterjee Luning Bakke Jinlong Wu Radu Serban Dan Negrut |
| author_facet | Huzaifa Unjhawala Thomas Hansen Harry Zhang Stefan Caldraru Shouvik Chatterjee Luning Bakke Jinlong Wu Radu Serban Dan Negrut |
| author_sort | Huzaifa Unjhawala |
| collection | DOAJ |
| description | We present a Vehicle Model (VM) that has 17 degrees of freedom and includes nonlinear tire and powertrain subsystems. Implemented as a relatively small piece of C++ code, the model runs vehicle dynamics 2000 times faster than real time at a simulation time step of <inline-formula> <tex-math notation="LaTeX">$1 \times 10^{-3}, \text {s}$ </tex-math></inline-formula> on a single core of a commodity CPU. When executed on the GPU, one can perform 300000 vehicle simulations in real-time. These properties make the model a good candidate for reinforcement learning, model predictive control, model predictive path integral control, path planning, state estimation, and traffic simulation tasks. The model is expressive in that it can capture the dynamics of vastly different vehicles. This is demonstrated by first calibrating the model to mimic the dynamics of a 1/<inline-formula> <tex-math notation="LaTeX">$6^{th}$ </tex-math></inline-formula> scale vehicle called the Autonomy Research Testbed (ART) vehicle, which has a mass of approximately 5.8 kg. Subsequently, the model is calibrated to mimic the dynamics of a heavy-duty High Mobility Multipurpose Wheeled Vehicle (HMMWV), which has a mass of 2097 kg. The Bayesian calibration process discussed can <inline-formula> <tex-math notation="LaTeX">$(i)$ </tex-math></inline-formula> handle real-life measurement noise, and <inline-formula> <tex-math notation="LaTeX">$(ii)$ </tex-math></inline-formula> provide model parameter probability distributions. The vehicle model, which is open source and freely available in a public repository, can also be imported into Python owing to SWIG wrapping. |
| first_indexed | 2024-03-07T14:04:53Z |
| format | Article |
| id | doaj.art-554aece4d56546ef9dac008cf2e9d873 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-25T01:25:39Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-554aece4d56546ef9dac008cf2e9d8732024-03-09T00:01:34ZengIEEEIEEE Access2169-35362024-01-0112330003301510.1109/ACCESS.2024.336887410443432An Expeditious and Expressive Vehicle Dynamics Model for Applications in Controls and Reinforcement LearningHuzaifa Unjhawala0https://orcid.org/0009-0004-4273-1212Thomas Hansen1Harry Zhang2https://orcid.org/0009-0003-1903-274XStefan Caldraru3Shouvik Chatterjee4Luning Bakke5https://orcid.org/0000-0002-9650-6959Jinlong Wu6https://orcid.org/0000-0001-7438-4228Radu Serban7https://orcid.org/0000-0002-4219-905XDan Negrut8https://orcid.org/0000-0003-1565-2784Department of Mechanical Engineering, University of Wisconsin-Madison, Madison, WI, USADepartment of Electrical and Computer Engineering, University of Wisconsin-Madison, Madison, WI, USADepartment of Mechanical Engineering, University of Wisconsin-Madison, Madison, WI, USADepartment of Computer Science, University of Wisconsin-Madison, Madison, WI, USADepartment of Mechanical Engineering, University of Wisconsin-Madison, Madison, WI, USADepartment of Mechanical Engineering, University of Wisconsin-Madison, Madison, WI, USADepartment of Mechanical Engineering, University of Wisconsin-Madison, Madison, WI, USADepartment of Mechanical Engineering, University of Wisconsin-Madison, Madison, WI, USADepartment of Mechanical Engineering, University of Wisconsin-Madison, Madison, WI, USAWe present a Vehicle Model (VM) that has 17 degrees of freedom and includes nonlinear tire and powertrain subsystems. Implemented as a relatively small piece of C++ code, the model runs vehicle dynamics 2000 times faster than real time at a simulation time step of <inline-formula> <tex-math notation="LaTeX">$1 \times 10^{-3}, \text {s}$ </tex-math></inline-formula> on a single core of a commodity CPU. When executed on the GPU, one can perform 300000 vehicle simulations in real-time. These properties make the model a good candidate for reinforcement learning, model predictive control, model predictive path integral control, path planning, state estimation, and traffic simulation tasks. The model is expressive in that it can capture the dynamics of vastly different vehicles. This is demonstrated by first calibrating the model to mimic the dynamics of a 1/<inline-formula> <tex-math notation="LaTeX">$6^{th}$ </tex-math></inline-formula> scale vehicle called the Autonomy Research Testbed (ART) vehicle, which has a mass of approximately 5.8 kg. Subsequently, the model is calibrated to mimic the dynamics of a heavy-duty High Mobility Multipurpose Wheeled Vehicle (HMMWV), which has a mass of 2097 kg. The Bayesian calibration process discussed can <inline-formula> <tex-math notation="LaTeX">$(i)$ </tex-math></inline-formula> handle real-life measurement noise, and <inline-formula> <tex-math notation="LaTeX">$(ii)$ </tex-math></inline-formula> provide model parameter probability distributions. The vehicle model, which is open source and freely available in a public repository, can also be imported into Python owing to SWIG wrapping.https://ieeexplore.ieee.org/document/10443432/Vehicle modelsBayesian inferencecalibrationstate estimationcontrolmachine learning |
| spellingShingle | Huzaifa Unjhawala Thomas Hansen Harry Zhang Stefan Caldraru Shouvik Chatterjee Luning Bakke Jinlong Wu Radu Serban Dan Negrut An Expeditious and Expressive Vehicle Dynamics Model for Applications in Controls and Reinforcement Learning IEEE Access Vehicle models Bayesian inference calibration state estimation control machine learning |
| title | An Expeditious and Expressive Vehicle Dynamics Model for Applications in Controls and Reinforcement Learning |
| title_full | An Expeditious and Expressive Vehicle Dynamics Model for Applications in Controls and Reinforcement Learning |
| title_fullStr | An Expeditious and Expressive Vehicle Dynamics Model for Applications in Controls and Reinforcement Learning |
| title_full_unstemmed | An Expeditious and Expressive Vehicle Dynamics Model for Applications in Controls and Reinforcement Learning |
| title_short | An Expeditious and Expressive Vehicle Dynamics Model for Applications in Controls and Reinforcement Learning |
| title_sort | expeditious and expressive vehicle dynamics model for applications in controls and reinforcement learning |
| topic | Vehicle models Bayesian inference calibration state estimation control machine learning |
| url | https://ieeexplore.ieee.org/document/10443432/ |
| work_keys_str_mv | AT huzaifaunjhawala anexpeditiousandexpressivevehicledynamicsmodelforapplicationsincontrolsandreinforcementlearning AT thomashansen anexpeditiousandexpressivevehicledynamicsmodelforapplicationsincontrolsandreinforcementlearning AT harryzhang anexpeditiousandexpressivevehicledynamicsmodelforapplicationsincontrolsandreinforcementlearning AT stefancaldraru anexpeditiousandexpressivevehicledynamicsmodelforapplicationsincontrolsandreinforcementlearning AT shouvikchatterjee anexpeditiousandexpressivevehicledynamicsmodelforapplicationsincontrolsandreinforcementlearning AT luningbakke anexpeditiousandexpressivevehicledynamicsmodelforapplicationsincontrolsandreinforcementlearning AT jinlongwu anexpeditiousandexpressivevehicledynamicsmodelforapplicationsincontrolsandreinforcementlearning AT raduserban anexpeditiousandexpressivevehicledynamicsmodelforapplicationsincontrolsandreinforcementlearning AT dannegrut anexpeditiousandexpressivevehicledynamicsmodelforapplicationsincontrolsandreinforcementlearning AT huzaifaunjhawala expeditiousandexpressivevehicledynamicsmodelforapplicationsincontrolsandreinforcementlearning AT thomashansen expeditiousandexpressivevehicledynamicsmodelforapplicationsincontrolsandreinforcementlearning AT harryzhang expeditiousandexpressivevehicledynamicsmodelforapplicationsincontrolsandreinforcementlearning AT stefancaldraru expeditiousandexpressivevehicledynamicsmodelforapplicationsincontrolsandreinforcementlearning AT shouvikchatterjee expeditiousandexpressivevehicledynamicsmodelforapplicationsincontrolsandreinforcementlearning AT luningbakke expeditiousandexpressivevehicledynamicsmodelforapplicationsincontrolsandreinforcementlearning AT jinlongwu expeditiousandexpressivevehicledynamicsmodelforapplicationsincontrolsandreinforcementlearning AT raduserban expeditiousandexpressivevehicledynamicsmodelforapplicationsincontrolsandreinforcementlearning AT dannegrut expeditiousandexpressivevehicledynamicsmodelforapplicationsincontrolsandreinforcementlearning |