A Semantic-Aware Integrated A${*}$ and Artificial Potential Field Path Planning Framework

Wei Zhou; Zhouyingmiao Chen

RA-L 20260 citations

A Semantic-Aware Integrated A${*}$ and Artificial Potential Field Path Planning Framework

Abstract

This letter addresses the challenge of reliable path planning for mobile robots navigating complex, semantically constrained environments. We propose a systematically integrated path planning framework that combines the A<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^*$</tex-math></inline-formula> algorithm with the artificial potential field (APF) method. Planning efficiency is improved through an adaptive cost function and an Environment-Aware Adaptive Robot Motion Block (EA-RMB) strategy, while navigation safety is reinforced by incorporating high-level semantic constraints, such as prohibited zones, via cost penalization. Furthermore, the repulsive component of the APF is integrated into the heuristic method of the proposed algorithm, enabling the planner to proactively avoid zones with dense obstacles during the global search process. Extensive simulations and experiments demonstrate that the proposed algorithm significantly improves planning efficiency while maintaining highly competitive path quality. Furthermore, it rigorously enforces semantic constraints, ensuring safe and reliable navigation in complex environments.

BibTeX

@inproceedings{ral2026_asemanticawarein,
  title = {A Semantic-Aware Integrated A${*}$ and Artificial Potential Field Path Planning Framework},
  author = {Wei Zhou and Zhouyingmiao Chen},
  booktitle = {RA-L 2026},
  year = {2026}
}