Metraipolis › archive › dc_dfd5f2119fe6
Forward Trajectory Steering for Hamilton-Jacobi Reachability Analysis — arXiv:2608.11480
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.11480
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T05:40:14.515Z
- SHA-256 of the archived text
8487e0d267ec2a4bba40b4f294553a83cacfce3f68fc82c4b9a80a23a669d789- Stable URL of this page
https://metraipolis.com/documento/dc_dfd5f2119fe6
How to cite
Forward Trajectory Steering for Hamilton-Jacobi Reachability Analysis — arXiv:2608.11480 — arXiv (en), https://arxiv.org/abs/2608.11480 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dfd5f2119fe6 (Metraipolis archive dc_dfd5f2119fe6, sha256 8487e0d267ec2a4bba40b4f294553a83cacfce3f68fc82c4b9a80a23a669d789)
BibTeX
@misc{dcdfd5f2119fe6,
title = {Forward Trajectory Steering for Hamilton-Jacobi Reachability Analysis — arXiv:2608.11480},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.11480},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dfd5f2119fe6; sha256 8487e0d267ec2a4bba40b4f294553a83cacfce3f68fc82c4b9a80a23a669d789},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11480. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Hamilton-Jacobi (HJ) reachability provides a mathematically rigorous framework for safe control of dynamical systems, but its practical application is bottlenecked by the computational complexity of solving Hamilton-Jacobi-Isaacs variational inequality PDEs in high dimensions. Physics-informed neural networks (PINNs) have recently emerged as a promising alternative to classical mesh-based solvers, yet their performance is highly sensitive to the choice of collocation sampling. In order to learn accurate safety value functions, existing PINNs-based HJ reachability solvers must rely on complex training pipelines and auxiliary supervision. In this work, we propose STEER2REACH (S2R), a PINNs-based HJ reachability solver that requires minimal modification on top of standard PINNs training. S2R's key contribution is a lightweight, low-overhead adaptive collocation sampling distribution constructed by steering forward trajectories using a combination of the optimal control and disturbance signals induced by the current value function, with injected stochastic exploration noise. We demonstrate that despite its simplicity, S2R achieves competitive--and in some cases improved--performance on safety metrics while reducing relative L2 error across a range of reachability benchmarks compared with SoTA MPC-guided HJ reachability solvers, all without requiring multi-stage training or MPC-based supervision. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.LG). Categorie arXiv: Systems and Control (eess.SY) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.11480 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T05:18:32.534Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).