Computationally Efficient Minimum-Time Motion Primitives for Vehicle Trajectory Planning
In the context of vehicle trajectory planning, motion primitives are trajectories connecting pairs of boundary conditions. In autonomous racing, motion primitives have been used as computationally faster alternatives to model predictive control, for online obstacle avoidance. However, the existing m...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of Intelligent Transportation Systems |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10711857/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590303892078592 |
|---|---|
| author | Mattia Piccinini Simon Gottschalk Matthias Gerdts Francesco Biral |
| author_facet | Mattia Piccinini Simon Gottschalk Matthias Gerdts Francesco Biral |
| author_sort | Mattia Piccinini |
| collection | DOAJ |
| description | In the context of vehicle trajectory planning, motion primitives are trajectories connecting pairs of boundary conditions. In autonomous racing, motion primitives have been used as computationally faster alternatives to model predictive control, for online obstacle avoidance. However, the existing motion primitive formulations are either simplified and suboptimal, or computationally expensive for accurate collision avoidance. This paper introduces new motion primitives for autonomous racing, aiming to accurately approximate the minimum-time vehicle trajectories while ensuring computational efficiency. We present a novel neural network, named PathPoly-NN, whose internal architecture is designed to learn the minimum-time vehicle path. Our motion primitives combine PathPoly-NN with a fast forward-backward method to compute the minimum-time speed profile. Compared to existing neural networks, PathPoly-NN generalizes better with small training sets, and it has better accuracy in approximating the minimum-time path. Additionally, our motion primitives have lower computational burden and higher accuracy than existing methods based on cubic polynomials and <inline-formula> <tex-math notation="LaTeX">$G^{2}$ </tex-math></inline-formula> clothoid curves. Finally, the motion primitives of this paper achieve similar maneuver times as minimum-time economic nonlinear model predictive control (E-NMPC), but with significantly lower computational load (two orders of magnitude). The results open promising perspectives of applications in graph-based trajectory planners for autonomous racing. |
| format | Article |
| id | doaj-art-076a0bab93824097a0144dcbe1924876 |
| institution | Kabale University |
| issn | 2687-7813 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Intelligent Transportation Systems |
| spelling | doaj-art-076a0bab93824097a0144dcbe19248762025-01-24T00:02:55ZengIEEEIEEE Open Journal of Intelligent Transportation Systems2687-78132024-01-01564265510.1109/OJITS.2024.347654010711857Computationally Efficient Minimum-Time Motion Primitives for Vehicle Trajectory PlanningMattia Piccinini0https://orcid.org/0000-0003-0457-8777Simon Gottschalk1https://orcid.org/0000-0003-4305-5290Matthias Gerdts2https://orcid.org/0000-0001-8674-5764Francesco Biral3https://orcid.org/0000-0001-8098-7965Department of Industrial Engineering, University of Trento, Trento, ItalyInstitute for Applied Mathematics and Scientific Computing, Department of Aerospace Engineering, Universität der Bundeswehr München, Neubiberg, GermanyInstitute for Applied Mathematics and Scientific Computing, Department of Aerospace Engineering, Universität der Bundeswehr München, Neubiberg, GermanyDepartment of Industrial Engineering, University of Trento, Trento, ItalyIn the context of vehicle trajectory planning, motion primitives are trajectories connecting pairs of boundary conditions. In autonomous racing, motion primitives have been used as computationally faster alternatives to model predictive control, for online obstacle avoidance. However, the existing motion primitive formulations are either simplified and suboptimal, or computationally expensive for accurate collision avoidance. This paper introduces new motion primitives for autonomous racing, aiming to accurately approximate the minimum-time vehicle trajectories while ensuring computational efficiency. We present a novel neural network, named PathPoly-NN, whose internal architecture is designed to learn the minimum-time vehicle path. Our motion primitives combine PathPoly-NN with a fast forward-backward method to compute the minimum-time speed profile. Compared to existing neural networks, PathPoly-NN generalizes better with small training sets, and it has better accuracy in approximating the minimum-time path. Additionally, our motion primitives have lower computational burden and higher accuracy than existing methods based on cubic polynomials and <inline-formula> <tex-math notation="LaTeX">$G^{2}$ </tex-math></inline-formula> clothoid curves. Finally, the motion primitives of this paper achieve similar maneuver times as minimum-time economic nonlinear model predictive control (E-NMPC), but with significantly lower computational load (two orders of magnitude). The results open promising perspectives of applications in graph-based trajectory planners for autonomous racing.https://ieeexplore.ieee.org/document/10711857/Autonomous drivingautonomous racingoptimal controlmotion primitivesminimum-lap-time simulationsneural networks |
| spellingShingle | Mattia Piccinini Simon Gottschalk Matthias Gerdts Francesco Biral Computationally Efficient Minimum-Time Motion Primitives for Vehicle Trajectory Planning IEEE Open Journal of Intelligent Transportation Systems Autonomous driving autonomous racing optimal control motion primitives minimum-lap-time simulations neural networks |
| title | Computationally Efficient Minimum-Time Motion Primitives for Vehicle Trajectory Planning |
| title_full | Computationally Efficient Minimum-Time Motion Primitives for Vehicle Trajectory Planning |
| title_fullStr | Computationally Efficient Minimum-Time Motion Primitives for Vehicle Trajectory Planning |
| title_full_unstemmed | Computationally Efficient Minimum-Time Motion Primitives for Vehicle Trajectory Planning |
| title_short | Computationally Efficient Minimum-Time Motion Primitives for Vehicle Trajectory Planning |
| title_sort | computationally efficient minimum time motion primitives for vehicle trajectory planning |
| topic | Autonomous driving autonomous racing optimal control motion primitives minimum-lap-time simulations neural networks |
| url | https://ieeexplore.ieee.org/document/10711857/ |
| work_keys_str_mv | AT mattiapiccinini computationallyefficientminimumtimemotionprimitivesforvehicletrajectoryplanning AT simongottschalk computationallyefficientminimumtimemotionprimitivesforvehicletrajectoryplanning AT matthiasgerdts computationallyefficientminimumtimemotionprimitivesforvehicletrajectoryplanning AT francescobiral computationallyefficientminimumtimemotionprimitivesforvehicletrajectoryplanning |