Kino-PAX$^+$: Near-Optimal Massively Parallel Kinodynamic Sampling-based Motion Planner
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910009810485248 |
|---|---|
| author | Perrault, Nicolas Ho, Qi Heng Lahijanian, Morteza |
| author_facet | Perrault, Nicolas Ho, Qi Heng Lahijanian, Morteza |
| contents | Sampling-based motion planners (SBMPs) are widely used for robot motion planning with complex kinodynamic constraints in high-dimensional spaces, yet they struggle to achieve \emph{real-time} performance due to their serial computation design. Recent efforts to parallelize SBMPs have achieved significant speedups in finding feasible solutions; however, they provide no guarantees of optimizing an objective function. We introduce Kino-PAX$^{+}$, a massively parallel kinodynamic SBMP with asymptotic near-optimal guarantees. Kino-PAX$^{+}$ builds a sparse tree of dynamically feasible trajectories by decomposing traditionally serial operations into three massively parallel subroutines. The algorithm focuses computation on the most promising nodes within local neighborhoods for propagation and refinement, enabling rapid improvement of solution cost. We prove that, while maintaining probabilistic $δ$-robust completeness, this focus on promising nodes ensures asymptotic $δ$-robust near-optimality. Our results show that Kino-PAX$^{+}$ finds solutions up to three orders of magnitude faster than existing serial methods and achieves lower solution costs than a state-of-the-art GPU-based planner. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_02846 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Kino-PAX$^+$: Near-Optimal Massively Parallel Kinodynamic Sampling-based Motion Planner Perrault, Nicolas Ho, Qi Heng Lahijanian, Morteza Robotics Distributed, Parallel, and Cluster Computing Sampling-based motion planners (SBMPs) are widely used for robot motion planning with complex kinodynamic constraints in high-dimensional spaces, yet they struggle to achieve \emph{real-time} performance due to their serial computation design. Recent efforts to parallelize SBMPs have achieved significant speedups in finding feasible solutions; however, they provide no guarantees of optimizing an objective function. We introduce Kino-PAX$^{+}$, a massively parallel kinodynamic SBMP with asymptotic near-optimal guarantees. Kino-PAX$^{+}$ builds a sparse tree of dynamically feasible trajectories by decomposing traditionally serial operations into three massively parallel subroutines. The algorithm focuses computation on the most promising nodes within local neighborhoods for propagation and refinement, enabling rapid improvement of solution cost. We prove that, while maintaining probabilistic $δ$-robust completeness, this focus on promising nodes ensures asymptotic $δ$-robust near-optimality. Our results show that Kino-PAX$^{+}$ finds solutions up to three orders of magnitude faster than existing serial methods and achieves lower solution costs than a state-of-the-art GPU-based planner. |
| title | Kino-PAX$^+$: Near-Optimal Massively Parallel Kinodynamic Sampling-based Motion Planner |
| topic | Robotics Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2602.02846 |